Cross-platform remote power transmission channel forest fire monitoring and early warning system and method

Abstract

The invention provides a cross-platform remote power transmission channel forest fire monitoring and early warning system and method, and relates to the technical field of power systems, and the system comprises an adaptive sensing network unit, a data processing unit, a visual display unit, a fire early warning unit and a collaborative decision module. Various environmental parameters including temperature, humidity, wind speed, soil humidity, illumination intensity, air pressure and the like can be collected in real time. And an information fusion algorithm is adopted to carry out weighted integration on the data to generate a comprehensive environmental risk index, so that more comprehensive and accurate environmental monitoring is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a cross-platform remote power transmission channel wildfire monitoring and early warning system and method. Background Art

[0002] Wildfire monitoring is an important basic work to ensure the safe and stable operation of power transmission channels. Wildfire monitoring in power transmission channels can be mainly divided into monitoring methods based on satellite remote sensing technology and monitoring methods based on distributed wireless sensor networks (WSN). The main detection methods in the remote real-time line monitoring and wildfire monitoring and early warning of power transmission channels at short-range terminals include smoke detection, video monitoring, infrared temperature detection and lidar monitoring using sensor terminal networks configured along the line. The detection method based on satellite remote sensing has low cost, high efficiency and a large detectable area and wide range, but it cannot be detected in real time due to the restrictions of satellite orbiting rules, and is greatly affected by the weather environment; the sensor network detection method is better in terms of real-time and comprehensiveness, but it is costly and difficult to implement. It is only suitable for setting up high-precision, long-distance detectors (such as lidar detectors) in high-level fire risk areas for key prevention.

[0003] According to a power transmission line wildfire monitoring, early warning and positioning system and method disclosed in Chinese patent publication number "CN112802287B", the system includes the following steps: S1. Determine whether there is a possibility of fire based on remote sensing data from a synchronous orbit satellite. If so, locate the fire scene through a remote sensing image target positioning algorithm and execute step S2; S2. Drive at least one monitoring drone to the fire scene; S3. Obtain the pictures sent back by the monitoring drone and display them on the GIS monitoring platform; S4. Confirm the possibility of fire based on the pictures, and when confirming the existence of a fire, circle the fire area based on the pictures.

[0004] The method for controlling the risk of wildfire tripping of power lines based on integrated meteorological and artificial fire prevention measures disclosed in Chinese Patent Publication No. "CN105243459A" includes the following steps: firstly, the historical wildfire disaster monitoring data near the transmission line corridor is obtained through the transmission line wildfire monitoring and early warning system, and according to the obtained data, a transmission line wildfire tripping probability model PR considering precipitation factors, a transmission line wildfire tripping probability model PT considering vegetation conditions, a transmission line wildfire tripping probability model PF considering wildfire distance and fire prevention measures, and a transmission line wildfire tripping probability model PV considering breakdown type are established, and finally a transmission line wildfire tripping comprehensive probability model P = PR PT PF PV is obtained, and corresponding control measures are taken according to the comprehensive probability of wildfire tripping of the transmission line obtained by real-time monitoring to deal with the transmission line wildfire tripping accident.

[0005] The above patent documents and prior art have the following technical problems when used:

[0006] 1. Traditional fire monitoring systems often rely only on a single parameter such as temperature or smoke concentration, and the data collection coverage is narrow, resulting in low fire monitoring sensitivity.

[0007] 2. The early warning mechanism of traditional fire monitoring systems is mostly based on threshold judgment. An alarm will only be triggered when a monitored parameter exceeds a preset threshold, which is prone to missed alarms and false alarms. Summary of the invention

[0008] In view of the deficiencies in the prior art, the present invention provides a cross-platform remote power transmission channel wildfire monitoring and early warning system, which solves the problem that traditional fire monitoring systems have low fire monitoring sensitivity and are prone to missed reports and false alarms.

[0009] Another object of the present invention is to provide a cross-platform remote power transmission channel wildfire monitoring and early warning method.

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0011] Cross-platform remote power transmission channel wildfire monitoring and early warning system, including:

[0012] An adaptive sensor network unit is used to collect environmental parameters, and weightedly integrate the collected environmental parameters to obtain integrated data;

[0013] A data processing unit, used for verifying, storing and classifying the received integrated data;

[0014] A fire warning unit is used to integrate and train the stored historical fire data and the received integrated data to form a training data set and output the generated potential fire prediction data;

[0015] A visual display unit, used to display the integrated data and potential fire prediction data, and generate a fire risk assessment interface;

[0016] The collaborative decision-making unit is used to collaboratively calculate the integrated data, generate a dynamically adjusted monitoring strategy and an early warning threshold, and feed back the calculation results to the adaptive sensor network unit.

[0017] Cross-platform remote power transmission channel wildfire monitoring and early warning method, including:

[0018] Collect environmental parameters, perform weighted integration on the collected environmental parameters, and obtain integrated data;

[0019] The integrated data is verified, stored and classified;

[0020] Performing integrated training on the stored historical fire data and the received integrated data to form a training data set and outputting the generated potential fire prediction data;

[0021] Displaying the integrated data and potential fire prediction data to generate a fire risk assessment interface;

[0022] The integrated data is collaboratively calculated to generate dynamically adjusted monitoring strategies and early warning thresholds, and the calculation results are fed back for information sharing.

[0023] The present invention has the following beneficial effects:

[0024] 1. The present invention deploys multimodal sensor nodes to collect multiple environmental parameters including temperature, humidity, wind speed, soil moisture, light intensity and air pressure in real time. The information fusion algorithm is used to weight and integrate these data to generate a comprehensive environmental risk index, thereby providing more comprehensive and accurate environmental monitoring.

[0025] 2. The present invention adopts a self-organizing network protocol based on a bio-inspired algorithm. The adaptive sensor network can dynamically adjust the network topology according to environmental changes and node health status. This mechanism enables the system to self-repair and reconfigure network connections in the event of sensor node failure, ensuring the continuity and stability of the system.

[0026] 3. The fire warning unit of the present invention uses a generative adversarial network (GAN) to conduct in-depth analysis of historical data and real-time data, which can accurately predict potential fire situations and generate warning signals in a timely manner. This method improves the accuracy of fire prediction and the timeliness of warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the working process of the method of the present invention;

[0028] Figure 2 It is a block diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Specific embodiment 1

[0031] As shown in the figure, the cross-platform remote power transmission channel wildfire monitoring and early warning system includes the following components:

[0032] Adaptive sensor network unit, the adaptive sensor network unit includes sensors, each sensor constitutes a sensor node, the sensor node also includes multimodal sensors, environmental parameters are collected using multimodal sensors, the multimodal sensors include temperature, humidity, wind speed, soil moisture, light intensity, vegetation type sensors, the multimodal sensors weightedly integrate various parameters through information fusion algorithm, each sensor node is used to collect environmental parameters, environmental parameters include wind speed, humidity, temperature, air pressure; the sensor nodes of the adaptive sensor network unit adopt a self-organizing network protocol based on a biologically inspired algorithm to achieve dynamic topology reconstruction, the self-organizing network protocol automatically adjusts the connection relationship between nodes according to environmental changes and node health status, and is used to optimize the data transmission path and improve the network's anti-interference ability. The adaptive sensor network unit also includes a self-repair module, the self-repair module has a built-in machine learning algorithm, and is used when the sensor node fails, the system automatically reconfigures the network topology;

[0033] Multimodal sensors: used to collect environmental parameters, including temperature (T), humidity (H), wind speed (W), soil moisture (SW), light intensity (LI) and vegetation type (VT).

[0034] Information fusion algorithm: weighted integration formula:

[0035]

[0036] E: Comprehensive index of environmental parameters after fusion, w i : The weight of the ith parameter, reflecting its importance in fire risk assessment, usually determined through expert evaluation or historical data analysis; i : The i-th environmental parameter value collected; the formula is normalized by weight to ensure that the comprehensive index is between 0 and 1, which is convenient for subsequent decision-making;

[0037] The self-organizing network protocol uses dynamic topology reconstruction: using the biologically inspired self-organizing network protocol, the connection relationship transfer probability improvement formula is automatically adjusted based on environmental changes and node health status:

[0038]

[0039] P ij : The transition probability from node i to node j; τ ij : path strength (pheromone), indicating the amount of information transferred in the past; η ij : Heuristic factor (such as the inverse of distance), reflecting the convenience of connection; The health status of node j evaluates the power and operating status of the node. The higher the value, the healthier the node. The health status of node j evaluates the power and operating status of the node. The higher the value, the healthier the node. α, β, γ: adjustment parameters, with values ​​between -1 and 1, reflecting the influence of various factors on the transfer probability, which need to be optimized through experiments.

[0040] The self-repair module uses machine learning algorithms: specifically, ensemble learning (such as random forest) is used to achieve self-repair when a node fails. Node reconfiguration formula:

[0041]

[0042] R j : The target node after reconfiguration, used to replace the failed node. K: The set of candidate nodes, all available nodes. k : The reliability score of node k, output by the machine learning model, based on historical data and real-time performance evaluation.

[0043] Data processing unit: The data processing unit is built into each sensor node. The data processing unit is used to process the data collected by the sensor node and verify the data through the blockchain. The data processing unit has a built-in multi-level integrated learning framework, which combines random forests, support vector machines and deep learning models to extract features and classify the data collected by the sensor nodes, so as to identify fire risks and generate early warning strategies based on dynamic changes in the environment.

[0044] Data processing and verification uses blockchain data verification:

[0045] The data processing unit processes and verifies the collected data locally. Data hash formula:

[0046] Hash d =H(d)=H(T||D||ID)

[0047] Hash d : Hash value of the data record. H: Hash function, ensuring that the data cannot be tampered with. T: Timestamp, recording the time when the data was generated. D: Data collected by the sensor. ID: Unique identifier of the sensor node.

[0048] Feature extraction and classification use an integrated learning framework:

[0049] Combine random forest, support vector machine and deep learning model to extract features and classify data; Random forest feature selection formula

[0050]

[0051] F: total feature importance score; M: number of trees in the forest; N m: The number of samples in the mth tree; G: The loss function (Gini index) of each tree to evaluate the classification performance; f m (x i ): The mth tree is trained on the input feature x i The prediction of i : The output value of the loss function.

[0052] Fire warning unit: The fire warning unit has a built-in generative adversarial network, which is used to predict potential fire scenario data and improve the generalization ability of the fire prediction model. The fire warning unit's generative adversarial network is trained with heterogeneous data, including historical fire records, real-time monitoring data, and meteorological data, to generate multi-dimensional potential fire predictions.

[0053] Generate adversarial network, fire prediction model:

[0054]

[0055] G(z): Generator, which generates potential fire scenario data based on random noise z; Generated forecast data; and D(y): are the discrimination results of generated data and real data, respectively, which are used to optimize the model.

[0056] A visualization display unit, which has a built-in augmented reality module. The augmented reality module displays monitoring data and is used to generate a fire risk assessment interface. The visualization display unit also includes an augmented reality module and a virtual reality module. The augmented reality module overlays real-time monitoring data on the monitoring interface, and the virtual reality module is used to provide a risk simulation environment. The visualization display unit includes risk area distribution, historical fire trend analysis, and future warning models;

[0057] Augmented reality output:

[0058] AR display =Overlay(E,R)

[0059] AR display : Augmented reality display content; E: Environmental parameter fusion results; R: Real-time monitoring data;

[0060] Virtual Reality Simulation:

[0061] VR simulation =Simulate(R,H)

[0062] VR simualtion : Fire risk simulation in virtual reality; R: Real-time data; H: Historical fire data used to simulate the scenario.

[0063] Collaborative decision-making module: The collaborative decision-making module has a built-in swarm intelligence algorithm. The collaborative decision-making module is used to realize information sharing and collaborative decision-making among sensor nodes, and dynamically adjust monitoring strategies and warning thresholds. The collaborative decision-making module has a built-in swarm intelligence algorithm for distributed intelligent decision-making of sensor nodes. Sensor nodes evaluate shared information through adaptive algorithms and dynamically adjust monitoring strategies and warning thresholds; The collaborative decision-making module uses swarm intelligence algorithms:

[0064] Definition: Swarm intelligence algorithms simulate group behavior in nature and are used for distributed intelligent decision-making;

[0065] Information sharing mechanism: Information update formula:

[0066] I ij (t+1)=I ij (t)+β·(S h (t)-I ij (t))

[0067] I ij (t): the value of node i’s trust in node j’s information at time t; S j (t): actual state information of node j (such as environmental parameters); β: learning rate, which controls the speed of information update; This formula is used to dynamically adjust the trust in other node information based on the received information.

[0068] Adaptive algorithms dynamically adjust monitoring strategies and warning thresholds:

[0069] Threshold adjustment formula:

[0070] T new =T old +α·(E current -E target )

[0071] T new : New monitoring threshold; T old : Old monitoring threshold; E current : Current environmental risk assessment value (provided by sensor nodes); E target : Target risk assessment value, usually set by the system; α: Adjustment factor, controlling the change range of the threshold;

[0072] Distributed decision model decision output formula:

[0073]

[0074] D i : The final decision output of node i (such as issuing an early warning or adjusting the monitoring strategy); N i : The set of neighboring nodes of node i; S i: the self-state of node i (such as health status, data validity); f is a comprehensive function that makes decisions based on the information of neighboring nodes and its own state;

[0075] The sensor nodes form a distributed intelligent network through collaborative decision-making modules, which can share information and adjust strategies under different environmental conditions.

[0076] Data flow:

[0077] Each sensor node collects data and generates information.

[0078] Nodes share status and trust through an information update mechanism.

[0079] Dynamically adjust monitoring strategies and warning thresholds based on current environmental parameters.

[0080] The adaptive sensor network unit includes a multimodal sensor node, a microprocessor (MCU), a wireless communication module, a power module and a self-repairing module. The multimodal sensor node integrates temperature sensors, humidity sensors, wind speed sensors, soil moisture sensors, light intensity sensors and vegetation type sensors, which can comprehensively collect environmental parameters. These sensors are connected to the microprocessor, which performs data acquisition and preliminary processing, and connects with other nodes through wireless communication modules (such as ZigBee, LoRa or Wi-Fi). The power module includes a rechargeable battery and a solar power supply device to ensure the long-term stable operation of the node. The self-repairing module has a built-in health monitoring sensor for real-time monitoring of the node status, and automatically triggers the reconfiguration of the network topology when a node failure is detected through a machine learning algorithm to ensure the reliability and integrity of the system.

[0081] Multimodal sensor nodes collect environmental parameters (such as temperature, humidity, wind speed, etc.) and transmit the collected data to the microprocessor for processing. The microprocessor weights and integrates the data of multiple sensors according to the information fusion algorithm to generate a comprehensive environmental risk index. All sensor nodes automatically adjust the connection relationship between nodes through a self-organizing network protocol based on a bio-inspired algorithm to achieve dynamic topology reconstruction. This mechanism ensures the optimization of the data transmission path and improves the anti-interference ability of the network. The self-repair module continuously monitors the health status of the sensor nodes. Once a node failure is detected, the machine learning algorithm is immediately used to reconfigure the network topology to ensure system stability.

[0082] Working steps:

[0083] Initialization: The sensor nodes are powered on, perform self-tests, and establish the initial network topology to ensure that all nodes can communicate normally.

[0084] Data collection: Multimodal sensor nodes continuously collect environmental parameters, detecting indicators such as temperature, humidity, wind speed, soil moisture, light intensity and vegetation type.

[0085] Data fusion: After receiving the sensor data, the microprocessor uses the information fusion algorithm to weight and integrate the data to generate a comprehensive environmental risk index.

[0086] Data transmission: The processed data is transmitted to the data processing unit or other adjacent nodes through the wireless communication module, supporting real-time monitoring and collaborative work.

[0087] Self-organizing network: Adaptive sensor network based on bio-inspired algorithms, realizes dynamic topology reconstruction, automatically adjusts network connections, and ensures efficient and anti-interference data transmission.

[0088] Fault monitoring and repair: The self-repair module monitors the node status in real time. Once a node failure is detected, it triggers network reconfiguration through machine learning algorithms to ensure stable system operation.

[0089] The data processing unit consists of a computing platform, storage devices, network interfaces, and security modules. The computing platform provides computing power and supports a variety of data processing and analysis algorithms. The storage device is used to store sensor data, model parameters, and historical records. The network interface enables high-speed communication with the sensor network, fire warning unit, and visualization unit. The security module has a built-in blockchain technology module to ensure the authenticity and integrity of the data transmission process.

[0090] The data processing unit obtains real-time data from sensor nodes from the adaptive sensor network unit through the network interface and verifies the data through blockchain technology. The verified data is stored in the database and analyzed through a multi-level integrated learning framework (including random forest, support vector machine and deep learning models). These models can extract and classify features of sensor data, identify fire risks and generate dynamic early warning strategies.

[0091] Working steps:

[0092] Data reception: Receive data transmitted by the sensor network through the network interface.

[0093] Data Verification: Use blockchain technology to verify the integrity and authenticity of data to ensure transmission security.

[0094] Data storage: Store verified data in a database as a basis for analysis and prediction.

[0095] Feature extraction and classification: Through an integrated learning framework, features are extracted from the data and classified to identify potential fire risks.

[0096] Early warning strategy generation: Based on the analysis results, the monitoring strategy is dynamically adjusted and an early warning strategy is generated and sent to the collaborative decision-making module and the visualization display unit.

[0097] The fire warning unit includes a computing device, a storage device, and a network interface. The computing device is used to run the generative adversarial network (GAN) model to train and predict data. The storage device is used to store model parameters, training data, and historical records. The network interface realizes communication with the data processing unit and the collaborative decision-making module. The fire warning unit uses a generative adversarial network (GAN) to predict potential fire situations by performing deep learning training on heterogeneous data (including historical fire records, real-time monitoring data, and meteorological data). The generative adversarial network consists of a generator and a discriminator. The generator generates data samples of potential fire situations, and the discriminator evaluates the authenticity of the generated data. By continuously iterating and optimizing the model, the accuracy of fire prediction is improved. Finally, the warning results will be transmitted to the collaborative decision-making module and the visualization display unit.

[0098] Working steps:

[0099] Data preparation: Collect and integrate historical fire records, real-time monitoring data, and meteorological data to form a training data set.

[0100] Model training: Deep learning training is performed through the GAN model. The generator generates potential fire scenario samples, and the discriminator evaluates the generated results and provides feedback to optimize the model.

[0101] Scenario prediction: Use the trained model to predict potential fire scenarios and output risk assessment results.

[0102] Early warning output: The prediction results are transmitted to the collaborative decision-making module and the visualization display unit to generate real-time early warning information.

[0103] Model update: Regularly retrain the model based on new data to ensure the timeliness and accuracy of prediction results.

[0104] The visualization display unit consists of a display, a computer or workstation, AR glasses or VR helmets, and interactive devices. The display and workstation are responsible for running the visualization software and supporting the graphic rendering and display of real-time data. AR glasses or VR helmets are used for augmented and virtual reality display, providing a more intuitive risk simulation environment. Interactive devices (such as a mouse, keyboard, touch screen, or gesture recognition device) support real-time user control and operation.

[0105] The visualization unit uses augmented reality (AR) and virtual reality (VR) technologies to present monitoring data and analysis results to users in an intuitive way. The augmented reality module can overlay real-time monitoring data on the real environment, allowing users to directly see fire risk indicators on the operation interface. The virtual reality module provides a risk simulation environment, where users can experience different fire scenarios through interactive devices to help make decisions.

[0106] Working steps:

[0107] Data acquisition: Receive real-time monitoring data and analysis results from the data processing unit and fire warning unit.

[0108] Graphics rendering: Graphics rendering of data using augmented reality and virtual reality technologies.

[0109] Interface display: Display the fire risk assessment interface on a high-resolution display or AR / VR device, including real-time monitoring data, historical trends, and future warning models.

[0110] User interaction: Users can adjust monitoring parameters in real time through interactive devices, or select different data views to further analyze risk situations.

[0111] Feedback mechanism: User operations are fed back to the data processing unit, and the system optimizes the monitoring strategy based on the feedback to improve subsequent monitoring and early warning processes.

[0112] The collaborative decision-making module consists of distributed computing nodes, communication modules, and storage modules. Distributed computing nodes usually share hardware with sensor nodes and have computing and communication capabilities. The communication module supports information sharing and synchronization between nodes. The storage module is used to store shared information, decision strategies, and historical data.

[0113] The collaborative decision-making module uses a swarm intelligence algorithm, particle swarm optimization (PSO) or ant colony algorithm to achieve collaborative decision-making between nodes. Through the information sharing mechanism, each sensor node exchanges environmental data and status information with each other to form a global cognition. Based on this shared information, the collaborative decision-making module can dynamically adjust the monitoring strategy and warning threshold, so that the system can adapt to environmental changes and optimize monitoring efficiency. After receiving the prediction results of the fire warning unit, the system adjusts the strategy according to the node information and model analysis results, and feeds back to the sensor network to form a closed loop.

[0114] Working steps:

[0115] Information collection: Each sensor node shares the collected data and status information to the collaborative decision-making module.

[0116] Swarm intelligence computing: Use swarm intelligence algorithms to analyze shared information, perform collaborative computing, and generate optimal monitoring strategies and warning thresholds.

[0117] Strategy update: Update the calculation results to each node and adjust its monitoring behavior and early warning mechanism.

[0118] Real-time feedback: After the node executes the new strategy, the execution results will be fed back to the collaborative decision-making module to optimize the overall monitoring effect.

[0119] Continuous optimization: Through continuous information sharing and decision-making feedback, monitoring strategies and early warning systems are continuously adjusted to improve the adaptability and stability of the system.

[0120] The overall workflow of the system:

[0121] Deployment phase: Adaptive sensor network units are placed in key areas along the transmission channel to initially establish network connectivity and topology.

[0122] Data collection and transmission: The adaptive sensor network unit collects environmental data in real time and transmits it to the data processing unit through the wireless communication module.

[0123] Data processing and analysis: The data processing unit receives, verifies and analyzes data, identifies potential fire risks, and generates early warning strategies.

[0124] Fire prediction and warning: The fire warning unit uses the GAN model to train heterogeneous data to generate potential fire scenarios and provide risk assessment.

[0125] Collaborative decision-making and adjustment: The collaborative decision-making module adjusts monitoring strategies and warning thresholds in real time through information sharing and intelligent algorithms to optimize overall system performance.

[0126] Visual display and user interaction: The visual display unit displays environmental monitoring data and fire prediction results in real time for operators to make decisions and control.

[0127] Feedback and optimization: The system continuously optimizes itself through user feedback, node feedback and data updates to improve monitoring and early warning effects and form a complete closed loop. Specific embodiment 2

[0129] As shown in the figure, the cross-platform remote power transmission channel wildfire monitoring and early warning method, the working steps of the method are as follows:

[0130] Sp1: Deploy an adaptive sensor network unit in the key area of ​​the transmission channel. The adaptive sensor network unit consists of multiple sensor nodes, each of which is used to collect environmental parameters, including wind speed, humidity, temperature and air pressure.

[0131] Adaptive sensor network units are deployed in key areas along the transmission corridor, with the goal of fully covering environmental monitoring in these areas. Each sensor node has built-in multimodal sensors, including thermistors for measuring temperature, capacitive humidity sensors for measuring humidity, ultrasonic anemometers for measuring wind speed, and piezoresistive sensors for measuring air pressure. These sensor nodes are equipped with wireless communication modules (such as LoRa, ZigBee or Wi-Fi), which can form an adaptive network with other nodes to achieve dynamic data transmission. The sensor nodes are controlled by a microprocessor (MCU). After collecting environmental parameters, they use information fusion algorithms to weightedly integrate multiple sensor data to generate a comprehensive environmental risk index. The self-organizing characteristics of the network are based on bio-inspired algorithms, which can dynamically adjust the connection relationship between nodes according to environmental changes and node health status to ensure the stability of the network and the efficiency of data transmission. Environmental parameters are collected using multimodal sensors, which use information fusion algorithms to weightedly integrate various parameters.

[0132] Weighted integration formula:

[0133]

[0134] E: Comprehensive index of environmental parameters after fusion, w i : The weight of the ith parameter, reflecting its importance in fire risk assessment, usually determined through expert evaluation or historical data analysis; i : The i-th environmental parameter value collected; the formula is normalized by weight to ensure that the comprehensive index is between 0 and 1, which is convenient for subsequent decision-making;

[0135] The sensor nodes use a self-organizing network protocol based on a bio-inspired algorithm to achieve dynamic topology reconstruction and automatically adjust the connection relationship transfer probability based on environmental changes and node health status. Improved formula:

[0136]

[0137] P ij : the transition probability from node i to node j; τ ij : path strength, indicating the amount of information transferred in the past; η ij : Heuristic factor, reflecting the convenience of connection; The health status of node j evaluates the power and operating status of the node. The higher the value, the healthier the node. The health status of node j evaluates the power and operation status of the node. The higher the value, the healthier the node. α, β, γ: adjustment parameters, with values ​​between -1 and 1, reflecting the influence of various factors on the transfer probability, which need to be optimized through experiments;

[0138] The adaptive sensor network unit uses ensemble learning to achieve self-repair when a node fails. The node reconfiguration formula is:

[0139]

[0140] R j : The target node after reconfiguration, used to replace the failed node. K: The set of candidate nodes, all available nodes. k : The reliability score of node k, output by the machine learning model, based on historical data and real-time performance evaluation.

[0141] Sp2: The sensor node collects environmental parameter data in real time and transmits the data to the built-in data processing unit for local processing.

[0142] Sensor nodes acquire environmental parameters in real time through periodic or event-driven acquisition modes. When rapid changes are detected (such as a sudden increase in wind speed or a sharp drop in humidity), the system can increase the sampling frequency to ensure that environmental changes are captured. The collected data is first processed in the node to reduce noise and errors. The processed data is sent to the node's built-in data processing unit through the wireless communication module, which relies on a microprocessor to quickly process large amounts of data and perform preliminary data analysis. The data processing unit can automatically select the optimal data transmission path through the protocol to ensure that data flow can be maintained even when the network is under high pressure.

[0143] Sp3: The data processing unit verifies the collected data through blockchain technology to ensure the authenticity and integrity of the data

[0144] In order to ensure the authenticity and non-tamperability of sensor data, the data processing unit introduces blockchain technology. Each piece of collected data will generate a unique hash value through a hash function and be stored on the blockchain together with the timestamp and node ID to form a chain of data records. The distributed ledger technology of the blockchain allows different nodes to verify the data, ensuring that the data of all sensor nodes can be traced and cannot be forged. This data verification mechanism improves the security and credibility of the entire monitoring system and prevents data anomalies caused by external data tampering or sensor node failure.

[0145] The data processing unit processes and verifies the collected data locally. The data hash formula is:

[0146] Hash d =H(d)=H(T||D||ID)

[0147] Hash d: Hash value of data record; H: Hash function, ensuring that data cannot be tampered with; T: Timestamp, recording the time when data was generated; D: Data collected by the sensor; ID: Unique identifier of the sensor node;

[0148] Combine random forest, support vector machine and deep learning model to extract features and classify data; Random forest feature selection formula

[0149]

[0150] F: total feature importance score; M: number of trees in the forest; N m : The number of samples in the mth tree; G: The loss function (Gini index) of each tree to evaluate the classification performance; f m (x i ): The mth tree is trained on the input feature x i The prediction of i : The output value of the loss function.

[0151] Sp4: The fire warning unit uses a generative adversarial network to analyze historical data and real-time data, predict potential fire situation data, and generate warning signals

[0152] The fire warning unit has a built-in generative adversarial network (GAN) for in-depth analysis of historical and real-time data collected by sensor nodes. The generator in the GAN model is responsible for generating data samples of potential fire scenarios, while the discriminator is used to evaluate whether the generated data is credible. Through repeated training of generation and discrimination, the model can learn from changes in environmental characteristics before a fire occurs and predict potential fire scenarios. The model can combine real-time data and meteorological data to generate early warning signals for future fire risks, and send them to the monitoring center and collaborative decision-making module in real time to ensure timely response.

[0153] Generate adversarial network, fire prediction model:

[0154]

[0155] G(z): Generator, which generates potential fire scenario data based on random noise z; Generated forecast data; and D(y): are the discrimination results of generated data and real data, respectively, which are used to optimize the model.

[0156] Sp5: The data processed by the data processing unit and the predicted data of the fire warning unit are transmitted to the visualization display unit. The augmented reality module displays the monitoring data in real time and generates a fire risk assessment interface.

[0157] After blockchain verification and local processing, the data will be transmitted to the visualization display unit. The unit displays real-time monitoring data, including current environmental parameters and fire risk index, through high-resolution displays or AR glasses. The augmented reality module can overlay and display these data in the real environment, allowing operators to directly see changes in environmental conditions on the monitoring interface. The system can also generate a comprehensive fire risk assessment interface, including visual elements such as charts and heat maps, to help operators quickly understand the risks behind the data. In addition, the module supports interactive operations with users, who can adjust monitoring parameters, view different historical data trends, and analyze environmental conditions from multiple angles.

[0158] Augmented reality output:

[0159] AR display =Overlay(E,R)

[0160] AR display : Augmented reality display content; E: Environmental parameter fusion results; R: Real-time monitoring data;

[0161] Virtual Reality Simulation:

[0162] VR simulation =Simulate(R,H)

[0163] VR simulation : Fire risk simulation in virtual reality; R: Real-time data; H: Historical fire data used to simulate the scenario.

[0164] Sp6: The collaborative decision-making module analyzes the data of each sensor node through a swarm intelligence algorithm, shares information, and dynamically adjusts monitoring strategies and warning thresholds to improve response efficiency.

[0165] The collaborative decision-making module uses group intelligence technologies such as particle swarm optimization (PSO) and ant colony algorithm (ACO) to achieve information sharing and collaborative analysis among multiple nodes. Each node can adjust its own monitoring strategy based on the data transmitted by other nodes, thus forming a dynamic adaptive network. The system analyzes the health status and real-time environmental data of sensor nodes, adjusts the communication frequency, sampling rate, and sensitivity of monitoring parameters between nodes to ensure the timeliness and accuracy of fire risk monitoring. In addition, the collaborative decision-making module will adjust the system's early warning threshold based on real-time sensor data and historical data to ensure that an alarm can be quickly issued when environmental changes exceed the set threshold.

[0166] Information sharing mechanism, information update formula:

[0167] I ij (t+1)=I ij (t)+β·(S j(t)-I ij (t))

[0168] I ij (t): the value of node i’s trust in node j’s information at time t; S j (t): the actual state information of node j (such as environmental parameters); β: learning rate, which controls the speed of information update; this formula is used to dynamically adjust the trust in other node information based on the received information;

[0169] Dynamically adjust monitoring strategies and warning thresholds. Threshold adjustment formula:

[0170] T new =T old +α·(E current -E target )

[0171] T new : New monitoring threshold; T old : Old monitoring threshold; E current : Current environmental risk assessment value (provided by sensor nodes); E target : Target risk assessment value, usually set by the system; α: Adjustment factor, controlling the change range of the threshold;

[0172] Distributed decision model decision output formula:

[0173]

[0174] D I : The final decision output of node i (such as issuing an early warning or adjusting the monitoring strategy); N i : The set of neighboring nodes of node i; S i : The self-state of node i (such as health status, data validity); f is a comprehensive function that makes decisions based on the information of neighboring nodes and its own state.

[0175] Sp7: The monitoring center operator makes emergency response decisions and implements corresponding measures based on the real-time data and warning information provided by the visualization display unit.

[0176] When the fire warning unit or collaborative decision-making module detects a potential fire risk, the warning signal and related data will be transmitted to the monitoring center. The operator can view the real-time environmental parameters, fire risk assessment interface and predicted fire situation data through the visual display unit. The operator will make emergency decisions based on this information, such as whether to send on-site inspection personnel or directly start firefighting equipment for early firefighting. The operator can also adjust the system's monitoring strategy through the interactive interface, increase the monitoring frequency of high-risk areas, or temporarily set new warning thresholds to cope with sudden environmental changes. The system will collect the operator's instructions in real time and feed them back to each module, so that the entire system forms a closed-loop monitoring and early warning mechanism to ensure seamless collaboration between monitoring and emergency response.

[0177] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprising a reference structure" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0178] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cross-platform remote power transmission channel mountain fire monitoring and early warning system, characterized in that: include: An adaptive sensor network unit is used to collect environmental parameters, and weightedly integrate the collected environmental parameters to obtain integrated data; A data processing unit, used for verifying, storing and classifying the received integrated data; A fire warning unit is used to integrate and train the stored historical fire data and the received integrated data to form a training data set and output the generated potential fire prediction data; A visual display unit, used to display the integrated data and potential fire prediction data, and generate a fire risk assessment interface; The collaborative decision-making unit is used to collaboratively calculate the integrated data, generate a dynamically adjusted monitoring strategy and an early warning threshold, and feed back the calculation results to the adaptive sensor network unit.

2. The cross-platform remote power transmission channel mountain fire monitoring and early warning system according to claim 1 is characterized by: The adaptive sensor network unit includes sensors, each sensor constitutes a sensor node, and the sensor node adopts a self-organizing network protocol based on a bio-inspired algorithm for dynamic topology reconstruction. The self-organizing network protocol automatically adjusts the connection relationship between nodes according to environmental changes and node health status to optimize the data transmission path.

3. The cross-platform remote power transmission channel mountain fire monitoring and early warning system according to claim 2 is characterized by: The sensor node also includes a multimodal sensor, which collects environmental parameters. The multimodal sensor includes temperature, humidity, wind speed, soil moisture, light intensity, and vegetation type sensors. The multimodal sensor weightedly integrates various environmental parameters through an information fusion algorithm.

4. The cross-platform remote power transmission channel mountain fire monitoring and early warning system according to claim 1 is characterized by: The data processing unit includes a computing platform, a storage device, a network interface and a security module. The computing platform is used for data processing and calculation; the storage device is used to store sensor data, model parameters and historical records; the network interface is used to communicate with the adaptive sensor network unit, the fire warning unit, the visualization display unit and the collaborative decision-making unit.

5. The cross-platform remote power transmission channel wildfire monitoring and early warning system according to claim 1 is characterized by: The visualization display unit includes an augmented reality module and a virtual reality module. The augmented reality module overlays real-time monitoring data on the monitoring interface; the virtual reality module is used to provide a risk simulation environment.

6. The cross-platform remote power transmission channel wildfire monitoring and early warning system according to claim 1 is characterized by: The fire warning unit has a built-in generative adversarial network, which is trained using heterogeneous data. The heterogeneous data includes historical fire records, real-time monitoring data, and meteorological data to generate multi-dimensional potential fire predictions.

7. The cross-platform remote power transmission channel wildfire monitoring and early warning system according to claim 1 is characterized by: The collaborative decision-making module includes a distributed computing node, a communication module and a storage module. The distributed computing node is used for collaborative computing; the communication module is used to share synchronization information with the sensor node; and the storage module is used to store shared information, decision strategies and historical data.

8. The cross-platform remote power transmission channel wildfire monitoring and early warning system according to claim 1 is characterized by: The adaptive sensor network unit also includes a self-repair module, which has a built-in machine learning algorithm for automatically reconfiguring the network topology when a sensor node fails.

9. The cross-platform remote power transmission channel wildfire monitoring and early warning system according to claim 1 is characterized by: The visualization display unit also includes risk area distribution, historical fire trend analysis and future warning models.

10. A monitoring and early warning method for a cross-platform remote power transmission channel mountain fire monitoring and early warning system, characterized in that: include: Collect environmental parameters, perform weighted integration on the collected environmental parameters, and obtain integrated data; The integrated data is verified, stored and classified; Performing integrated training on the stored historical fire data and the received integrated data to form a training data set and outputting the generated potential fire prediction data; Displaying the integrated data and potential fire prediction data to generate a fire risk assessment interface; The integrated data is collaboratively calculated to generate dynamically adjusted monitoring strategies and early warning thresholds, and the calculation results are fed back for information sharing.

11. The cross-platform remote power transmission channel wildfire monitoring and early warning method according to claim 10 is characterized in that: The environmental parameters are collected using multimodal sensors, which perform weighted integration of various parameters through information fusion algorithms. Weighted integration formula: E: Comprehensive index of environmental parameters after fusion, w i : The weight of the ith parameter, reflecting its importance in fire risk assessment, usually determined through expert evaluation or historical data analysis; i : The i-th environmental parameter value collected; the formula is normalized by weight to ensure that the comprehensive index is between 0 and 1, which is convenient for subsequent decision-making; The sensor nodes use a self-organizing network protocol based on a bio-inspired algorithm to achieve dynamic topology reconstruction and automatically adjust the connection relationship transfer probability based on environmental changes and node health status. Improved formula: P ij : the transition probability from node i to node j; τ ij : Path strength, indicating the amount of information transfer in the past; η ij : Heuristic factor, reflecting the convenience of connection; The health status of node j evaluates the power and operating status of the node. The higher the value, the healthier the node. The health status of node j evaluates the power and operation status of the node. The higher the value, the healthier the node. α, β, γ: adjustment parameters, with values ​​between -1 and 1, reflecting the influence of various factors on the transfer probability, which need to be optimized through experiments; The adaptive sensor network unit uses ensemble learning to achieve self-repair when a node fails. The node reconfiguration formula is: R j : The target node after reconfiguration, used to replace the failed node. K: The set of candidate nodes, all available nodes. k : The reliability score of node k, output by the machine learning model, based on historical data and real-time performance evaluation.

12. The cross-platform remote power transmission channel wildfire monitoring and early warning method according to claim 10 is characterized in that: The collected data is processed and verified locally, and the data hash formula is: Hash d =H(d)=H(T||D||ID) Hash d : Hash value of data record; H: Hash function, ensuring that data cannot be tampered with; T: Timestamp, recording the time when data was generated; D: Data collected by the sensor; ID: Unique identifier of the sensor node; Combine random forest, support vector machine and deep learning model to extract features and classify data; Random forest feature selection formula F: total feature importance score; M: number of trees in the forest; N m : The number of samples of the mth tree; G: loss function (Gini index) of each tree, evaluating classification performance; f m (x i ): The mth tree is trained on the input feature x i The prediction of i : The output value of the loss function.

13. The cross-platform remote power transmission channel wildfire monitoring and early warning method according to claim 10 is characterized in that: In the step of displaying the integrated data and potential fire prediction data, Augmented reality output: AR display =Overlay(E,R) AR display : Augmented reality display content; E: Environmental parameter fusion results; R: Real-time monitoring data; Virtual Reality Simulation: VR simulation =Simulate(R,H) VR simulation : Fire risk simulation in virtual reality; R: Real-time data; H: Historical fire data used to simulate the scenario.

14. The cross-platform remote power transmission channel wildfire monitoring and early warning method according to claim 10 is characterized in that: In the step of integrating the stored historical fire data with the received integrated data, a confrontation network and a fire prediction model are generated: G(z): Generator, which generates potential fire scenario data based on random noise z; Generated forecast data; and D(y): are the discrimination results of generated data and real data, respectively, which are used to optimize the model.

15. The cross-platform remote power transmission channel wildfire monitoring and early warning method according to claim 10 is characterized in that: In the information sharing step, Information sharing mechanism, information update formula: I ij (t+1)=I ij (t)+β·(S j (t)-I ij (t)) I ij (t): the value of node i’s trust in node j’s information at time t; S j (t): the actual state information of node j (such as environmental parameters); β: learning rate, which controls the speed of information update; this formula is used to dynamically adjust the trust in other node information based on the received information; Dynamically adjust monitoring strategies and warning thresholds. Threshold adjustment formula: T new =T old +α·(E current -E target ) T new : New monitoring threshold; T old : Old monitoring threshold; E current : The current environmental risk assessment value provided by the sensor node; E target : Target risk assessment value, usually set by the system; α: Adjustment factor, controlling the change range of the threshold; Distributed decision model decision output formula: D i : The final decision output of node i; N i : The set of neighboring nodes of node i; S i : The self-state of node i; f is a comprehensive function that makes decisions based on the information of neighboring nodes and its own status.

Images