A forest fire monitoring system based on data transmission

Abstract

The present invention provides a forest fire prevention monitoring system based on data transmission, which belongs to the field of data monitoring technology; the system includes: a data acquisition module: configuring sensors to the target forest monitoring area and performing real-time monitoring to obtain original forest parameter data; a data processing module: using edge devices to pre-process the original forest parameter data and then storing it in a first database; a data transmission module: using a heartbeat detection mechanism to detect whether the edge device and the receiver of the data transmission terminal are online connected and regularly transmit data, and if so, standardizing the first parameter data of the first database received by the receiver to obtain standard parameter data; an early warning module: predicting the fire risk of the target forest monitoring area according to historical parameter data and standard parameter data, and configuring it to the real environment to evaluate the monitoring effect. The system improves the efficiency of monitoring, early warning and response, optimizes resource allocation, and efficiently handles disasters.

Description

Technical Field

[0001] The invention relates to the technical field of data monitoring, and in particular to a forest fire monitoring system based on data transmission. Background Art

[0002] At present, forest fire prevention is an important means to protect the ecological environment and ensure the sustainable development of forest resources. With the impact of global climate change and human activities, the frequency and intensity of forest fires are increasing, seriously threatening the ecological balance, public safety and human property. However, traditional forest fire monitoring methods, such as manual inspections, ground monitoring points and remote sensing satellite image analysis, have a certain time delay and are difficult to cover vast forest areas, resulting in low efficiency of fire prevention and weak monitoring efforts.

[0003] Therefore, the present invention proposes a forest fire monitoring system based on data transmission. Summary of the invention

[0004] The present invention provides a forest fire monitoring system based on data transmission, which is used to integrate data transmission and early warning modules, build a data center and back it up regularly, configure real environmental parameters for fire risk prediction, and optimize algorithms and equipment configurations through field feedback evaluation, so as to achieve efficient forest fire monitoring and early warning, improve monitoring, early warning and response efficiency, optimize resource allocation, and efficiently handle disasters.

[0005] In one aspect, the present invention provides a forest fire monitoring system based on data transmission, comprising:

[0006] Data collection module: deploy sensors in the target forest monitoring area and conduct real-time monitoring to obtain original forest parameter data;

[0007] Data processing module: using edge devices to pre-process the original forest parameter data and store it in the first database;

[0008] Data transmission module: using a heartbeat detection mechanism to detect whether the edge device and the receiver of the data transmission terminal are online connected and transmit data regularly. If so, standardizing the first parameter data of the first database received by the receiver to obtain standard parameter data;

[0009] Early warning module: predicts the fire risk in the target forest monitoring area based on historical parameter data and standard parameter data, and configures it to the real environment to evaluate the monitoring effect.

[0010] On the other hand, the data acquisition module includes:

[0011] Area division unit: divide the target forest to be monitored into standard sizes to obtain the target forest monitoring area;

[0012] Scheme Design Unit: Evaluate the environmental characteristics of the target forest monitoring area and design the layout of different types of sensors based on the environmental characteristics.

[0013] On the other hand, the data acquisition module further includes:

[0014] Sensor matching unit: determines the installation type and location of the sensor according to the layout plan;

[0015] Sensor monitoring unit: After the sensor configuration is installed and started, it is connected to the edge device to collect the original forest parameter data of the target forest monitoring area in real time.

[0016] On the other hand, the data processing module includes:

[0017] Edge device configuration unit: based on calculating basic parameters, initializing edge devices of the monitoring station, installing software and processing algorithms in the edge devices, and then starting the edge devices;

[0018] Initialization unit: acquiring original forest parameter data transmitted by the sensor based on the edge device, and formatting the original forest parameter data of any parameter type according to a standard format table to obtain first data;

[0019] Statistical features of the first data are extracted, and the first data are standardized based on the statistical features to obtain second parameter data.

[0020] On the other hand, the data processing module further includes:

[0021] A database construction unit: constructs a first database connected to the edge device according to preset database fields and connection information;

[0022] Data distinguishing unit: obtaining second parameter data of any parameter type, cutting the second parameter data according to a preset sliding step length, and obtaining a plurality of data windows including the data;

[0023] Traversing any data window based on the feature engine, determining the data stream features of the data window, wherein the data stream features include: a label difference and a step size;

[0024] Calculate the mark difference and step length according to a statistical algorithm to obtain a data flow value peak value of the data window;

[0025] If there is a situation where the peak value of the data stream reaches the transient data limit, then the transient value is marked to the corresponding data window, otherwise it is marked as no transient value;

[0026] Data windows marked as having no transient value are screened out based on edge devices, and parameters involved in the screened windows are compressed and sent to the first database.

[0027] On the other hand, the data transmission module includes:

[0028] Heartbeat signal unit: predefines the format and content of the heartbeat signal, and sets a timed task on the edge device according to the format and content, wherein the timed task is to send the heartbeat signal to the receiver at a preset time;

[0029] State monitoring unit: obtains the movement coefficient corresponding to the state parameters involved in the execution of any scheduled task;

[0030] ;in, represents the mobility coefficient corresponding to the i-th scheduled task, Indicates the status parameter value of the i-th scheduled task. The value range of i is 1, 2, 3, ..., n-1, where n indicates that there are n scheduled tasks in total. The preset weight coefficient of the i-th scheduled task, Indicates the status parameter value of the i+1th scheduled task. represents the smoothing factor;

[0031] If the mobile coefficient corresponding to any scheduled task is greater than the abnormal threshold and there are consecutive abnormalities in scheduled tasks before and after the current scheduled task, it is determined that the heartbeat signal is abnormal, and then the online connection status of the receiver between the edge device and the data transmission terminal is detected;

[0032] If the movement coefficient corresponding to any scheduled task is greater than the abnormal threshold and only a single scheduled task has an abnormality, the heartbeat signal is determined to be normal;

[0033] If the movement coefficient corresponding to any scheduled task is less than or equal to the abnormal threshold, the heartbeat signal is determined to be normal;

[0034] If the heartbeat signal is normal, the first parameter data of the first database received by the receiver is standardized using a normal algorithm to obtain standard parameter data.

[0035] On the other hand, the early warning module includes:

[0036] Historical data unit: in the historical database, based on the preset parameter type as a screening condition, obtain the historical parameter data of the preset parameter type;

[0037] Model training unit: using historical parameter data as a training set and standard parameter data as a test set, initializing the fire prediction model, training the fire prediction model based on the training set, and obtaining the first model indicator;

[0038] Model verification unit: Use the test set to verify the deviation degree of the first model indicator, and retrain the fire prediction model according to the deviation degree to obtain the final fire prediction model.

[0039] On the other hand, the prediction module further includes:

[0040] System unit: Integrate the data transmission module and early warning module into the monitoring system, build a data center in the monitoring system, and set up regular backup to save data;

[0041] Prediction unit: configure the monitoring system into a real environment and connect it to the real forest parameter data of the designated area. The fire prediction model will predict the fire warning risk of the designated area based on the real forest parameter data and provide a visual interface for display.

[0042] Evaluation Unit: Conduct field investigations on fire warning risks, collect actual feedback data, compare it with fire warning risks, and evaluate and optimize the algorithms and equipment configurations of the monitoring system.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] The present invention provides a forest fire monitoring system based on data transmission, which is used to integrate data transmission and early warning modules, build a data center and back it up regularly, configure real environmental parameters for fire risk prediction, and optimize algorithms and equipment configurations through field feedback evaluation, so as to achieve efficient forest fire monitoring and early warning, improve monitoring, early warning and response efficiency, optimize resource allocation, and efficiently handle disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 It is a structural schematic diagram of a forest fire monitoring system based on data transmission provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0048] Embodiment 1:

[0049] like Figure 1As shown, a forest fire monitoring system based on data transmission provided by an embodiment of the present invention includes:

[0050] Data collection module: deploy sensors in the target forest monitoring area and conduct real-time monitoring to obtain original forest parameter data;

[0051] Data processing module: using edge devices to pre-process the original forest parameter data and store it in the first database;

[0052] Data transmission module: using a heartbeat detection mechanism to detect whether the edge device and the receiver of the data transmission terminal are online connected and transmit data regularly. If so, standardizing the first parameter data of the first database received by the receiver to obtain standard parameter data;

[0053] Early warning module: predicts the fire risk in the target forest monitoring area based on historical parameter data and standard parameter data, and configures it to the real environment to evaluate the monitoring effect.

[0054] In this embodiment, the target forest monitoring area is a specific forest area selected for fire risk monitoring and early warning based on analysis after detection by Beidou navigation satellites.

[0055] In this embodiment, the sensor is a device used to collect various environmental parameters in the target forest monitoring area in real time, including: temperature, humidity, air quality, soil moisture, wind speed and other data.

[0056] In this embodiment, the original forest parameter data refers to the original numerical data collected in real time by sensors and reflecting the state of the forest environment, including: temperature, humidity, air quality, soil moisture, wind speed and other data.

[0057] In this embodiment, the edge device refers to a hardware device located between the data source and the data center.

[0058] In this embodiment, preprocessing refers to the process of cleaning, converting and processing raw data before performing data analysis, modeling or training a model.

[0059] In this embodiment, the first database is a database used to store original forest parameter data.

[0060] In this embodiment, the heartbeat detection mechanism is a technical means for monitoring the connection status between devices, and the connection status is determined by sending a heartbeat signal and monitoring the response status.

[0061] In this embodiment, the data transmission terminal is responsible for receiving data from the edge device and transmitting it to the remote storage cloud platform.

[0062] In this embodiment, the receiver refers to a hardware device or a communication interface for receiving data sent by the data transmission module.

[0063] In this embodiment, online connection means that the network communication between various modules, especially between the edge device and the data transmission terminal and the receiver, remains stable and effective.

[0064] In this embodiment, the first parameter data refers to unprocessed original forest parameter data obtained from the first database.

[0065] In this embodiment, standardization is a processing method for converting data from different sources or formats into a unified scale or range.

[0066] In this embodiment, the standard parameter data is data obtained by processing and normalizing the original first parameter data.

[0067] In this embodiment, historical parameter data refers to data that has been collected and stored in a certain period of time in the past, representing information on environmental conditions, forest health, climate conditions, etc. of the target forest monitoring area at different time points.

[0068] In this embodiment, fire risk refers to a comprehensive assessment of the probability of a forest fire occurring at a specific time and location and its potential impact.

[0069] In this embodiment, the real environment refers to the natural environmental conditions occurring in the actual forest monitoring target area.

[0070] In this embodiment, the monitoring effect refers to the evaluation of the system's effectiveness in predicting fire risks and responding to actual fire incidents, such as when a fire did not actually occur (false positive), or when a fire actually occurred without issuing an early warning (false negative).

[0071] The working principle and beneficial effects of the above technical solution are: real-time monitoring of forest parameters through sensors, pre-processing and storage of data by edge devices, heartbeat detection to ensure stable data transmission, and fire risk prediction after standardized data, thereby providing accurate early warning and effectively improving forest fire prevention and control capabilities and response speed.

[0072] Embodiment 2:

[0073] Based on the above embodiment 1, the data acquisition module includes:

[0074] Area division unit: divide the target forest to be monitored into standard sizes to obtain the target forest monitoring area;

[0075] Scheme Design Unit: Evaluate the environmental characteristics of the target forest monitoring area and design the layout of different types of sensors based on the environmental characteristics.

[0076] In this embodiment, standard size division refers to dividing the target forest monitoring area into areas according to predetermined standard sizes.

[0077] In this embodiment, environmental characteristics refer to a series of factors that affect fire risk and monitoring effect, such as the natural environment, climate conditions, topography, vegetation type, etc. in the target forest area.

[0078] In this embodiment, the layout plan refers to a specific plan for rationally configuring and deploying different types of sensors in the target forest monitoring area according to environmental characteristics (such as climate, terrain, vegetation type, etc.).

[0079] The working principle and beneficial effects of the above technical solution are: by standardizing the target forest monitoring area, evaluating the regional environmental characteristics, and designing a reasonable sensor layout plan to achieve accurate monitoring. Through customized layout, the sensor monitoring efficiency is improved, providing a scientific basis for fire warning and forest management.

[0080] Embodiment 3:

[0081] Based on the above embodiment 2, the data acquisition module further includes:

[0082] Sensor matching unit: determines the installation type and location of the sensor according to the layout plan;

[0083] Sensor monitoring unit: After the sensor configuration is installed and started, it is connected to the edge device to collect the original forest parameter data of the target forest monitoring area in real time.

[0084] In this embodiment, the installation type refers to a sensor installation method selected according to the functional requirements of the sensor, environmental conditions, and specific application scenarios.

[0085] In this embodiment, the installation position refers to the specific placement and installation point of the sensor in the target monitoring area.

[0086] The working principle and beneficial effects of the above technical solution are: by matching the appropriate sensor type and location according to the layout plan, the sensor can efficiently monitor the target area. The sensor collects original forest data in real time and connects to edge devices to provide accurate data support, providing a reliable basis for subsequent fire risk assessment and management decisions.

[0087] Embodiment 4:

[0088] Based on the above embodiment 1, the data processing module includes:

[0089] Edge device configuration unit: based on calculating basic parameters, initializing edge devices of the monitoring station, installing software and processing algorithms in the edge devices, and then starting the edge devices;

[0090] Initialization unit: acquiring original forest parameter data transmitted by the sensor based on the edge device, and formatting the original forest parameter data of any parameter type according to a standard format table to obtain first data;

[0091] Statistical features of the first data are extracted, and the first data are standardized based on the statistical features to obtain second parameter data.

[0092] In this embodiment, the calculation basic parameters refer to basic data configuration values ​​used to initialize the edge devices of the monitoring station and the data processing flow.

[0093] In this embodiment, a monitoring station is a location where edge devices are installed to collect, process, and monitor environmental or ecological parameter data.

[0094] In this embodiment, software and processing algorithms refer to programs and calculation methods that run on edge devices and are used for data collection, processing, analysis, and transmission, such as: mean algorithm, standard deviation algorithm, kurtosis algorithm, etc.

[0095] In this embodiment, the parameter type refers to different types of forest environment data collected by the sensor, including parameters such as temperature, humidity, light, and air pressure.

[0096] In this embodiment, the standard format table refers to a predefined data structure, which provides a unified standard for data formatting and processing.

[0097] In this embodiment, data formatting refers to converting and organizing original data according to a predetermined standard so that the data conforms to a certain data structure and format specification.

[0098] In this embodiment, the first data refers to the original forest parameter data after data formatting.

[0099] In this embodiment, statistical features refer to parameters used to describe basic distribution characteristics and trends of data, including mean, variance, maximum value, etc.

[0100] In this embodiment, the second parameter data is data obtained by performing statistical feature extraction and standardization processing on the first data.

[0101] The working principle and beneficial effects of the above technical solution are: by initializing the edge device and installing the processing algorithm, formatting and statistical feature extraction are performed after receiving the sensor data. After data standardization, the second parameter data is obtained, which improves the data consistency and accuracy, provides a reliable basis for subsequent analysis and forest risk assessment, and enhances monitoring accuracy.

[0102] Embodiment 5:

[0103] Based on the above embodiment 4, the data processing module further includes:

[0104] A database construction unit: constructs a first database connected to the edge device according to preset database fields and connection information;

[0105] Data distinguishing unit: obtaining second parameter data of any parameter type, cutting the second parameter data according to a preset sliding step length, and obtaining a plurality of data windows including the data;

[0106] Traversing any data window based on the feature engine, determining the data stream features of the data window, wherein the data stream features include: a label difference and a step size;

[0107] Calculate the mark difference and step length according to a statistical algorithm to obtain a data flow value peak value of the data window;

[0108] If there is a situation where the peak value of the data stream reaches the transient data limit, then the transient value is marked to the corresponding data window, otherwise it is marked as no transient value;

[0109] Data windows marked as having no transient value are screened out based on edge devices, and parameters involved in the screened windows are compressed and sent to the first database.

[0110] In this embodiment, the preset database field refers to a field that is predefined in the database design phase according to the requirements of data storage, processing and query, such as a time field, an ID field, a data storage field, etc.

[0111] In this embodiment, the connection information refers to all necessary configuration and protocol parameters for connecting the edge device and the database, such as port number, IP address, host name, etc.

[0112] In this embodiment, the preset sliding step size refers to the step size of the sliding window when processing the data window. The size of the sliding window determines how many data points each data window contains. For example, a fixed window size is set to 10 data points.

[0113] In this embodiment, cutting refers to dividing the continuous data stream into multiple independent data windows according to a preset sliding step size.

[0114] In this embodiment, the data window refers to a data subset extracted from the entire data stream according to a preset size and sliding step when processing a continuous data stream.

[0115] In this embodiment, the feature engine refers to a module used to extract, process and convert data features during the data analysis process.

[0116] In this embodiment, the data stream characteristics refer to a set of indicators that can describe characteristics such as data change patterns, trends, fluctuations, and periodicity in a continuous data stream.

[0117] In this embodiment, the label difference refers to the difference between consecutive data points.

[0118] In this embodiment, the step size refers to the step size of the window movement or the increment per unit time when the sliding window is cut on the data.

[0119] In this embodiment, the statistical algorithm is a mathematical method for calculating and analyzing the peak value of the data stream in the data window, extracting m data according to the step size, and determining the difference between two marking points based on the marking difference.

[0120] In this embodiment, the data stream value peak is a numerical indicator reflecting the degree of fluctuation in the data window, wherein the specific calculation method for the data stream value peak is as follows:

[0121] ;in, represents the label difference of the i-th data window, represents the step size of the i-th data window, Indicates the peak value of the data stream, N indicates that there are N data windows in total, represents the external conversion rate, represents the loss coefficient, Indicates the peak value setting. represents the variance of the remaining label differences except the label differences of the i-th data window, N1 represents the number of label differences among all label differences that are greater than the i-th data window; ln represents the sign of the logarithmic function.

[0122] In this embodiment, the transient data limit is a numerical limit. When the value peak of the data stream exceeds this limit, it means that the change within the data window is significant and rapid, and is therefore marked as a transient value.

[0123] In this embodiment, transient value refers to short-term, drastic fluctuations or changes that occur in the data stream, which represent momentary anomalies or important events in the data and have high analytical value.

[0124] In this embodiment, the screening window refers to a data window that is screened out and marked as having no transient value after being processed by the data distinguishing unit and the feature engine.

[0125] In this embodiment, compression refers to performing a data compression process on a data window marked as having no transient value, thereby reducing the space occupied by data storage and transmission.

[0126] The working principle and beneficial effects of the above technical solution are: by building a database connected to the edge device, cutting and analyzing the second parameter data, extracting data stream features and calculating the data stream value peak. By marking transient or non-transient data, filtering data windows without transient value, compressing and storing them in the database, data storage efficiency and analysis accuracy are improved.

[0127] Embodiment 6:

[0128] Based on the above embodiment 1, the data transmission module includes:

[0129] Heartbeat signal unit: predefines the format and content of the heartbeat signal, and sets a timed task on the edge device according to the format and content, wherein the timed task is to send the heartbeat signal to the receiver at a preset time;

[0130] State monitoring unit: obtains the movement coefficient corresponding to the state parameters involved in the execution of any scheduled task;

[0131] ;in, represents the mobility coefficient corresponding to the i-th scheduled task, Indicates the status parameter value of the i-th scheduled task. The value range of i is 1, 2, 3, ..., n-1, where n indicates that there are n scheduled tasks in total. The preset weight coefficient of the i-th scheduled task, Indicates the status parameter value of the i+1th scheduled task. represents the smoothing factor;

[0132] If the mobile coefficient corresponding to any scheduled task is greater than the abnormal threshold and there are consecutive abnormalities in scheduled tasks before and after the current scheduled task, it is determined that the heartbeat signal is abnormal, and then the online connection status of the receiver between the edge device and the data transmission terminal is detected;

[0133] If the movement coefficient corresponding to any scheduled task is greater than the abnormal threshold and only a single scheduled task has an abnormality, the heartbeat signal is determined to be normal;

[0134] If the movement coefficient corresponding to any scheduled task is less than or equal to the abnormal threshold, the heartbeat signal is determined to be normal;

[0135] If the heartbeat signal is normal, the first parameter data of the first database received by the receiver is standardized using a normal algorithm to obtain standard parameter data.

[0136] In this embodiment, the heartbeat signal is a signal sent periodically to confirm the online status and normal operation of a device or system.

[0137] In this embodiment, the format and content include: a signal header, a timestamp, a task identifier, a task execution status, etc.

[0138] In this embodiment, the scheduled task refers to a task that executes a certain operation function at a preset time interval in the system.

[0139] In this embodiment, the task execution process refers to a flow from signal sending-receiving signal-returning signal.

[0140] In this embodiment, the status parameter refers to an indicator or parameter related to the device operation status monitored during the execution of the scheduled task, including: CPU usage, memory usage, network bandwidth, etc.

[0141] In this embodiment, the movement coefficient is an indicator used to describe the rate of change of the task state, reflecting the change of the device state parameters over time during the execution of the scheduled task.

[0142] In this embodiment, the smoothing factor is a coefficient used to smooth the state parameter value in heartbeat signal monitoring and anomaly detection.

[0143] In this embodiment, the preset weight coefficient is a parameter used to control the relative importance of different tasks in the calculation process.

[0144] In this embodiment, the abnormal threshold sets a limit value for judging the normal standard of the movement coefficient corresponding to the scheduled task.

[0145] In this embodiment, continuous abnormality refers to the occurrence of abnormalities in multiple scheduled tasks continuously during the heartbeat signal monitoring process.

[0146] In this embodiment, the normal algorithm refers to an algorithm that uses normal distribution to perform normal processing on data.

[0147] The working principle and beneficial effects of the above technical solution are: the connection status between the edge device and the receiver is monitored through the heartbeat signal timing task, and whether the heartbeat signal is abnormal is determined based on the mobility coefficient and the abnormal threshold. If the signal is normal, the data is standardized to improve the connection monitoring accuracy and the reliability of data analysis.

[0148] Embodiment 7:

[0149] Based on the above embodiment 1, the early warning module includes:

[0150] Historical data unit: in the historical database, based on the preset parameter type as a screening condition, obtain the historical parameter data of the preset parameter type;

[0151] Model training unit: using historical parameter data as a training set and standard parameter data as a test set, initializing the fire prediction model, training the fire prediction model based on the training set, and obtaining the first model indicator;

[0152] Model verification unit: Use the test set to verify the deviation degree of the first model indicator, and retrain the fire prediction model according to the deviation degree to obtain the final fire prediction model.

[0153] In this embodiment, the history library refers to a database system that stores historical data and saves past observation data.

[0154] In this embodiment, the screening condition refers to a rule used to extract relevant data from the history library.

[0155] In this embodiment, the training set is a set of data used to train the model.

[0156] In this embodiment, the test set is a set of data used to evaluate and verify the performance of the model.

[0157] In this embodiment, the fire prediction model is a mathematical model constructed based on historical data and a machine learning algorithm.

[0158] In this embodiment, the first model index refers to the performance index of the fire prediction model obtained through preliminary training, including accuracy, precision, recall rate, error rate, etc.

[0159] In this embodiment, the degree of deviation refers to the degree of difference between the predicted results of the model on the test set and the actual results.

[0160] In this embodiment, the final fire prediction model is a model that has been optimized through multiple rounds of training and verification.

[0161] The working principle and beneficial effects of the above technical solution are: training the fire prediction model through historical parameter data and verifying the model accuracy with standardized data. By continuously adjusting the model, optimizing the prediction effect, improving the accuracy and reliability of fire warning, and effectively assisting fire risk prevention and emergency response.

[0162] Embodiment 8:

[0163] Based on the above embodiment 7, the prediction module further includes:

[0164] System unit: Integrate the data transmission module and early warning module into the monitoring system, build a data center in the monitoring system, and set up regular backup to save data;

[0165] Prediction unit: configure the monitoring system into a real environment and connect it to the real forest parameter data of the designated area. The fire prediction model will predict the fire warning risk of the designated area based on the real forest parameter data and provide a visual interface for display.

[0166] Evaluation Unit: Conduct field investigations on fire warning risks, collect actual feedback data, compare it with fire warning risks, and evaluate and optimize the algorithms and equipment configurations of the monitoring system.

[0167] In this embodiment, a data center refers to a centralized, specialized facility used to store, manage, and process large amounts of data and provide support for various computing needs.

[0168] In this embodiment, the fire warning risk refers to the possibility of a fire occurring in a specific area based on the forest environment and the fire prediction model.

[0169] In this embodiment, the visualization interface is an interface that displays fire warning risks, real-time monitoring data and prediction results to users in the form of graphics, charts, maps, etc.

[0170] In this embodiment, the field investigation refers to the process in which the assessment unit verifies and investigates the actual situation of the fire warning risk through on-site visits, field inspections or data collection.

[0171] In this embodiment, the actual feedback data is data obtained by monitoring the fire risk of the real environment based on the Tiantong satellite link;

[0172] In this embodiment, evaluation and optimization, evaluation refers to the process of comprehensive analysis of the performance, accuracy and reliability of the fire warning system, including: system performance, prediction accuracy, environmental adaptability, etc.; optimization refers to improving the various components of the fire warning system based on the evaluation results so that it can operate more accurately and efficiently in the future, including: algorithm optimization, equipment optimization, data processing optimization, etc.

[0173] The working principle and beneficial effects of the above technical solution are: by integrating data transmission and early warning modules, building a monitoring system and performing regular data backup. Using the fire prediction model combined with actual forest data to predict risks, and optimizing the algorithm and equipment configuration through field evaluation, the accuracy and reliability of the fire early warning system are improved.

[0174] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A forest fire monitoring system based on data transmission, characterized in that: include: Data collection module: deploy sensors in the target forest monitoring area and conduct real-time monitoring to obtain original forest parameter data; Data processing module: using edge devices to pre-process the original forest parameter data and store it in the first database; Data transmission module: uses a heartbeat detection mechanism to detect whether the edge device and the receiver of the data transmission terminal are online connected and transmit data regularly. If so, the first parameter data of the first database received by the receiver is standardized to obtain standard parameter data, including: Heartbeat signal unit: predefines the format and content of the heartbeat signal, and sets a timed task on the edge device according to the format and content, wherein the timed task is to send the heartbeat signal to the receiver at a preset time; State monitoring unit: obtains the movement coefficient corresponding to the state parameters involved in the execution of any scheduled task; ;in, represents the mobile coefficient corresponding to the i-th scheduled task, Indicates the status parameter value of the i-th scheduled task. The value range of i is 1, 2, 3, ..., n-1, where n indicates that there are n scheduled tasks in total. The preset weight coefficient of the i-th scheduled task, Indicates the status parameter value of the i+1th scheduled task. represents the smoothing factor; If the mobile coefficient corresponding to any scheduled task is greater than the abnormal threshold and there are consecutive abnormalities in scheduled tasks before and after the current scheduled task, it is determined that the heartbeat signal is abnormal, and then the online connection status of the receiver between the edge device and the data transmission terminal is detected; If the movement coefficient corresponding to any scheduled task is greater than the abnormal threshold and only a single scheduled task has an abnormality, the heartbeat signal is determined to be normal; If the movement coefficient corresponding to any scheduled task is less than or equal to the abnormal threshold, the heartbeat signal is determined to be normal; If the heartbeat signal is normal, the first parameter data of the first database received by the receiver is standardized using a normal algorithm to obtain standard parameter data; Early warning module: predicts the fire risk of the target forest monitoring area based on historical parameter data and standard parameter data, and configures it to evaluate the monitoring effect in the real environment, including: Historical data unit: obtains historical parameter data of the preset parameter type in the historical library according to the preset parameter type as the screening condition; Model training unit: using historical parameter data as a training set and standard parameter data as a test set, initializing the fire prediction model, training the fire prediction model based on the training set, and obtaining the first model indicator; Model verification unit: Use the test set to verify the degree of deviation of the first model indicator, and retrain the fire prediction model according to the degree of deviation to obtain the final fire prediction model.

2. A forest fire monitoring system based on data transmission according to claim 1, characterized in that: The data acquisition module comprises: Area division unit: divide the target forest to be monitored into standard sizes to obtain the target forest monitoring area; Scheme Design Unit: Evaluate the environmental characteristics of the target forest monitoring area and design the layout of different types of sensors based on the environmental characteristics.

3. A forest fire monitoring system based on data transmission according to claim 2, characterized in that: The data acquisition module further includes: Sensor matching unit: determines the installation type and location of the sensor according to the layout plan; Sensor monitoring unit: After the sensor configuration is installed and started, it is connected to the edge device to collect the original forest parameter data of the target forest monitoring area in real time.

4. A forest fire monitoring system based on data transmission according to claim 1, characterized in that: The data processing module comprises: Edge device configuration unit: based on calculating basic parameters, initializing edge devices of the monitoring station, installing software and processing algorithms in the edge devices, and then starting the edge devices; Initialization unit: acquiring original forest parameter data transmitted by the sensor based on the edge device, and formatting the original forest parameter data of any parameter type according to a standard format table to obtain first data; Statistical features of the first data are extracted, and the first data are standardized based on the statistical features to obtain second parameter data.

5. A forest fire monitoring system based on data transmission according to claim 4, characterized in that: The data processing module further includes: A database construction unit: constructs a first database connected to the edge device according to preset database fields and connection information; Data distinguishing unit: obtaining second parameter data of any parameter type, cutting the second parameter data according to a preset sliding step length, and obtaining a plurality of data windows including the data; Traversing any data window based on the feature engine, determining the data stream features of the data window, wherein the data stream features include: a label difference and a step size; Calculate the mark difference and step length according to a statistical algorithm to obtain a data flow value peak value of the data window; If there is a situation where the peak value of the data stream reaches the transient data limit, then the transient value is marked to the corresponding data window, otherwise it is marked as no transient value; Data windows marked as having no transient value are screened out based on edge devices, and parameters involved in the screened windows are compressed and sent to the first database.

6. A forest fire monitoring system based on data transmission according to claim 1, characterized in that: The early warning module further includes: System unit: Integrate the data transmission module and early warning module into the monitoring system, build a data center in the monitoring system, and set up regular backup to save data; Prediction unit: configure the monitoring system into a real environment and connect it to the real forest parameter data of the designated area. The fire prediction model will predict the fire warning risk of the designated area based on the real forest parameter data and provide a visual interface for display. Evaluation Unit: Conduct field investigations on fire warning risks, collect actual feedback data, compare it with fire warning risks, and evaluate and optimize the algorithms and equipment configurations of the monitoring system.

Images