A real-time monitoring and early warning system for forest fires based on the Internet of Things

Abstract

The present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, which relates to the technical field of the Internet of Things, and includes a data acquisition module: real-time monitoring of forest conditions to obtain forest condition data; a data transmission module: using the Internet of Things technology to transmit the forest condition data to a target monitoring center; an early warning module: the target monitoring center performs fire risk early warning and fire risk level classification on the forest based on the forest condition data; a remote monitoring module: the target user remotely accesses the target monitoring center and intelligently controls the monitoring equipment. By utilizing the Internet of Things technology to transmit the forest condition data obtained by real-time monitoring of the forest to the target monitoring center; the target monitoring center performs fire risk early warning and fire risk level classification on the forest based on the forest condition data received in real time; the target user remotely accesses the target monitoring center and intelligently controls the monitoring equipment, which effectively realizes timely early warning of forest fires and improves the monitoring and early warning capabilities of forest fires.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a real-time monitoring and early warning system for forest fires based on the Internet of Things. Background Art

[0002] In recent years, with global warming, the frequency and destructiveness of forest fires have increased. Forest fire prevention has become an important part of the current national disaster prevention and mitigation work, and is of great significance for protecting forest resources and maintaining ecological balance. However, traditional forest fire monitoring methods have shortcomings such as small monitoring range, high labor intensity, and inability to monitor around the clock, which leads to the inability to timely warn of fires and cause great losses. How to achieve timely warning of forest fires, improve the monitoring and warning capabilities of forest fires, and effectively prevent and control forest fires has become one of the current research centers.

[0003] Therefore, the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things. Summary of the invention

[0004] The present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, which is used to transmit forest status data obtained by real-time monitoring of the forest to a target monitoring center by utilizing the Internet of Things technology; the target monitoring center performs fire risk early warning and fire risk level classification on the forest based on the forest status data received in real time; the target user remotely accesses the target monitoring center and intelligently controls the monitoring equipment, effectively realizing timely early warning of forest fires and improving the monitoring and early warning capabilities of forest fires.

[0005] The present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, comprising:

[0006] Data collection module: used to monitor the status of the target forest in real time using the pre-installed monitoring equipment installed at the set location node to obtain forest status data;

[0007] Data transmission module: used to transmit the forest status data to a target monitoring center using Internet of Things technology;

[0008] Early warning module: used by the target monitoring center to carry out fire risk early warning and fire risk level classification of the target forest based on the received forest condition data;

[0009] Remote monitoring module: used to enable target users to remotely access the target monitoring center and intelligently control monitoring equipment.

[0010] Preferably, the pre-installed monitoring equipment includes a meteorological sensor, a smoke detector and a thermal infrared sensor.

[0011] Preferably, the data transmission module includes:

[0012] Node transmission unit: used to obtain the first core management node to which each set position node belongs in the current transmission period;

[0013] Transmitting the forest status data acquired by the set location node to the corresponding first core management node in real time;

[0014] Data processing unit: used for the first core management node to receive and fuse the forest status data transmitted by all set position nodes within the set clustering range to obtain a fused status data group;

[0015] The first core management node divides the fusion status data group into equal parts to obtain fusion data sub-groups;

[0016] Using the current first core management node as a screening condition, the first network topology structure and node basic information are obtained from the key node information extracted from the preset node database;

[0017] Arranging the next-level node set of the current first core management node determined according to the first network topology structure to form a node relationship graph;

[0018] According to the node relationship diagram, obtaining the transmission path of the current first core management node;

[0019] Based on the next-level node set and node basic information of the current first core management node, a first broadcast message is generated for network-wide broadcast;

[0020] Obtaining the path in-degree of each transmission path of the current first core management node;

[0021] Based on the obtained path in-degree, obtaining the probability of successful transmission of the fused data sub-packet for each transmission path of the current first core management node;

[0022] Link determination unit: used to traverse all first core management nodes, sort the calculated success transmission probability of each transmission path of the first core management node, and use the transmission path with the highest success transmission probability as the selected transmission link of the current first core management node;

[0023] Traversing all first core management nodes, obtaining the transmission delays of all transmission paths of each first core management node except the selected transmission link, and selecting the path with the lowest transmission delay as the backup transmission link corresponding to the first core management node;

[0024] Transmission unit: used to transmit the current fusion data sub-groups to the target monitoring center according to the selected transmission link;

[0025] When the selected transmission link of the first core management node jitters, the corresponding standby transmission link is started to transmit the fused data sub-packets to the target monitoring center.

[0026] Preferably, based on the obtained path in-degree, obtaining the probability of successful transmission of the fused data subpacket for each transmission path of the current first core management node includes:

[0027] Use network monitoring tools to monitor the current network status in real time and obtain key network performance parameters;

[0028] Extracting and analyzing historical transmission records within a preset time period of the current transmission path from the transmission record database to obtain the historical transmission success rate of each historical transmission using the current transmission path;

[0029] The path in-degree of the current transmission path, the historical transmission success rate, and the key network performance parameters are combined to calculate the successful transmission probability of the current transmission path.

[0030] Preferably, the calculation formula for the probability of successful transmission is as follows:

[0031] ; In the formula, It is represented as the probability of successful transmission of the fused data sub-packet for the i-th transmission path of the current first core management node; It is expressed as the average value of the historical transmission success rate of the i-th transmission path; It is expressed as the maximum historical transmission success rate of the i-th transmission path; It is represented as the path in-degree of the i-th transmission path; f is represented as the influence weight of the path in-degree on the successful transmission of the transmission path; It is represented as the set performance threshold of the jth key network performance parameter, ; is represented as the jth key network performance parameter, It is expressed as the influence weight of the jth key network performance parameter on the evaluation of network status; It is expressed as the influence weight of the current network status on the successful transmission of the transmission path; ln is expressed as the natural logarithm; e is expressed as the natural base.

[0032] Preferably, the early warning module includes:

[0033] Fire risk analysis unit: used for the target monitoring center to evaluate the fire risk of the current target forest according to the received forest condition data, and obtain a first risk assessment result;

[0034] An early warning unit is used to input the corresponding fire characterization data of the fire occurrence area into a level classification model obtained by a pre-trained neural network according to the first risk assessment result, and output the fire risk level of the current fire occurrence area if it is determined that a fire occurs in the current target forest and there is a fire occurrence area;

[0035] The fire occurrence area is combined with the corresponding fire risk level and fire characterization data to generate a fire alarm report and send it to the fire maintenance personnel;

[0036] The fire maintenance personnel receive the fire alarm report and handle the fire in the fire occurrence area;

[0037] If it is determined that a fire has occurred in the current target forest and there is an area where a fire may occur, the area where a fire may occur in the first risk assessment result is combined with the corresponding possible risk coefficient and possible risk data to generate a fire prevention report;

[0038] Generate a fire warning task according to the fire prevention report, and fill the fire prevention task into a fire prevention task list according to the possible risk factors from large to small;

[0039] The fire prevention personnel shall perform the fire prevention tasks in sequence according to the fire prevention task list.

[0040] Preferably, the fire risk analysis unit comprises:

[0041] Fire judgment unit: used for the target monitoring center to perform data cleaning, data conversion and normalization on the currently acquired forest status data to obtain the first status data;

[0042] Inputting the first condition data into a pre-established fire analysis model to obtain a fire analysis result;

[0043] When there is a fire occurrence area or a fire possible area in the fire analysis result, it is determined that a fire occurs in the current target forest;

[0044] When there is no fire occurrence area and no fire possible area in the fire analysis result, it is determined that no fire occurs in the current target forest;

[0045] Possible risk analysis unit: used to calculate the possible risk coefficient of the fire possible area using the possible risk data when there is a fire possible area in the fire analysis result;

[0046] The calculation formula of possible risk factor is as follows:

[0047] ; In the formula, It is expressed as the possible risk coefficient of the current r-th fire-prone area; It is represented by the number of types of meteorological data contained in the corresponding possible risk data of the current r-th fire possible area, where: ; It is represented by the set data threshold of the t-th type of meteorological data contained in the corresponding possible risk data of the current r-th fire possible area, where t ; It is represented by the t-th type of meteorological data contained in the corresponding possible risk data of the current r-th fire-prone area; It is expressed as the number of combustible materials existing in the current r-th fire-prone area; It is expressed as the weight of the impact of the amount of combustibles on the possibility of fire occurrence; It is represented by the number of historical fires in the current r-th fire-prone area; It is expressed as the weight of the impact of the number of historical fire occurrences on the possibility of fire occurrence;

[0048] Assessment generation unit: used to output the fire occurrence area determined according to the fire analysis results, the fire possible occurrence area, fire characterization data, possible risk data, fire judgment results and the possible risk coefficient obtained by the possible risk analysis unit as the first risk assessment result.

[0049] Preferably, the remote monitoring module includes:

[0050] Remote access unit: used for the target user to establish a connection with the target monitoring center by using the set remote device and pre-set software, and then independently select the user verification method for identity authentication;

[0051] After the target user's identity authentication is successful, the target user automatically logs into the user interface of the target monitoring center and views the forest status data received in real time by the target monitoring center on the user interface;

[0052] Remote control unit: used to combine and analyze the user control requirements of the current target user and the device control authority using the instruction generation unit to generate a user control instruction; and use the instruction execution unit to control the preset monitoring device to execute the user control instruction;

[0053] Instruction generation unit: used by the target user to set remote devices and preset software, and upload user control requirements;

[0054] According to the user control requirements of the current target user, obtain the corresponding first device control authority;

[0055] Compare the first device control permission with the specified device control permission range of the current target user, and if the first device control permission does not exceed the specified device control permission range of the current target user, generate a user control instruction based on the current user control requirement;

[0056] If the first device control permission exceeds the specified device control permission range, the permission in the first device control permission that does not exceed the specified device control permission range of the current target user is regarded as the first selected permission; based on the control requirements of the current target user that can be realized based on the first selected permission, the user control instruction is generated;

[0057] Instruction execution unit: used to transmit the user control instruction to the target monitoring center by using the set remote device and preset software;

[0058] The target monitoring center parses the user control instruction and performs format conversion to obtain the target control instruction;

[0059] The target monitoring center transmits the target control instruction to the corresponding preset monitoring device;

[0060] The preset monitoring device executes the received target control instruction and feeds back the execution result to the target monitoring center;

[0061] The target user views the remote control results in the user interface by utilizing the set remote device and preset software.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] By utilizing Internet of Things technology, the forest condition data obtained from real-time monitoring of the forest is transmitted to the target monitoring center; the target monitoring center issues fire risk warnings and classifies fire risk levels for the forest based on the real-time forest condition data received; the target users remotely access and intelligently control the monitoring equipment of the target monitoring center, effectively realizing timely warnings of forest fires and improving the monitoring and warning capabilities of forest fires.

[0064] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0065] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0067] Figure 1The present invention is a structural diagram of a forest fire real-time monitoring and early warning system based on the Internet of Things in an embodiment of the present invention. DETAILED DESCRIPTION

[0068] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0069] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, such as Figure 1 As shown, including:

[0070] Data collection module: used to monitor the status of the target forest in real time using the pre-installed monitoring equipment installed at the set location node to obtain forest status data;

[0071] Data transmission module: used to transmit the forest status data to a target monitoring center using Internet of Things technology;

[0072] Early warning module: used by the target monitoring center to carry out fire risk early warning and fire risk level classification of the target forest based on the received forest condition data;

[0073] Remote monitoring module: used to enable target users to remotely access the target monitoring center and intelligently control monitoring equipment.

[0074] In this embodiment, the target forest refers to the forest that currently needs to be warned of a fire; the preset monitoring equipment includes a meteorological sensor, a smoke detector and a thermal infrared sensor, wherein the meteorological sensor includes a temperature sensor, a humidity sensor and an anemometer; the set position node is a predetermined set position for installing the preset monitoring equipment; the set position for installing the meteorological sensor is a position that can monitor regional climate characteristics; the set position for installing the smoke detector is an area prone to fire; the set position for installing the thermal infrared sensor is a commanding height in the target forest; the forest status data refers to the first meteorological data, the first smoke data and the first thermal infrared data, wherein the data type of the first meteorological data includes three types: temperature data, humidity data and wind speed data.

[0075] In this embodiment, the smoke detector is used to capture smoke generated by a fire source, and when smoke is detected, it sends out a smoke alarm signal at a set frequency, wherein the set frequency is predetermined; the thermal infrared sensor is used to identify heat sources at night or in foggy days, and when a large amount of thermal radiation is detected, it sends out a thermal infrared alarm signal at a set frequency, wherein the set frequency is predetermined.

[0076] In this embodiment, the Internet of Things technology is a technology that connects any object to the network through information sensing devices according to an agreed protocol, so that the object can exchange and communicate information through information transmission media to achieve intelligent identification, positioning, tracking, supervision and other functions. Its principle is mainly to use perception, communication and control technologies to connect the physical world and the digital world to each other, and realize information interaction and intelligent management between devices; the target monitoring center refers to a cloud computing platform that can receive and analyze and process the first forest data, as well as fire warning; the target user refers to a user who is not in the target forest area and is far away from the monitoring equipment and the target monitoring center; the fire risk level includes four levels: minor, serious, very serious and extremely serious; remote access to the target monitoring center refers to remote query of the forest status data received by the target monitoring center in real time; intelligent control of the monitoring equipment refers to equipment adjustment of the preset monitoring equipment, such as adjusting the equipment sampling frequency, modifying the equipment configuration parameters, etc.

[0077] The beneficial effects of the above technical solution are: by utilizing the Internet of Things technology, the forest condition data obtained from real-time monitoring of the forest is transmitted to the target monitoring center; the target monitoring center conducts fire risk warning and fire risk level classification for the forest based on the forest condition data received in real time; the target user remotely accesses and intelligently controls the monitoring equipment of the target monitoring center, effectively realizing timely warning of forest fires and improving the monitoring and warning capabilities of forest fires.

[0078] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, wherein the data transmission module comprises:

[0079] Node transmission unit: used to obtain the first core management node to which each set position node belongs in the current transmission period;

[0080] Transmitting the forest status data acquired by the set location node to the corresponding first core management node in real time;

[0081] Data processing unit: used for the first core management node to receive and fuse the forest status data transmitted by all set position nodes within the set clustering range to obtain a fused status data group;

[0082] The first core management node divides the fusion status data group into equal parts to obtain fusion data sub-groups;

[0083] Using the current first core management node as a screening condition, the first network topology structure and node basic information are obtained from the key node information extracted from the preset node database;

[0084] Arranging the next-level node set of the current first core management node determined according to the first network topology structure to form a node relationship graph;

[0085] According to the node relationship diagram, obtaining the transmission path of the current first core management node;

[0086] Based on the next-level node set and node basic information of the current first core management node, a first broadcast message is generated for network-wide broadcast;

[0087] Obtaining the path in-degree of each transmission path of the current first core management node;

[0088] Based on the obtained path in-degree, obtaining the probability of successful transmission of the fused data sub-packet for each transmission path of the current first core management node;

[0089] Link determination unit: used to traverse all first core management nodes, sort the calculated success transmission probability of each transmission path of the first core management node, and use the transmission path with the highest success transmission probability as the selected transmission link of the current first core management node;

[0090] Traversing all first core management nodes, obtaining the transmission delays of all transmission paths of each first core management node except the selected transmission link, and selecting the path with the lowest transmission delay as the backup transmission link corresponding to the first core management node;

[0091] Transmission unit: used to transmit the current fusion data sub-groups to the target monitoring center according to the selected transmission link;

[0092] When the selected transmission link of the first core management node jitters, the corresponding standby transmission link is started to transmit the fused data sub-packets to the target monitoring center.

[0093] In this embodiment, the transmission cycle refers to a preset time period for transmitting specific forest status data to the target monitoring center. In different transmission cycles, the first core management node to which the set position node belongs changes; the set position node refers to the position node where the preset monitoring equipment is placed; the first core management node refers to the node responsible for receiving, fusing and transmitting the data of all set position nodes within the set clustering range; the set clustering range is a predetermined range; the fused status data group is obtained by fusing the forest status data transmitted by all set position nodes received by the first core management node within the set clustering range using a data fusion algorithm; the preset node database is composed of the first core management core node and the corresponding key node information, wherein the key node information includes the network topology structure and the node basic information, and the node basic information includes an identifier (such as IP address, MAC address, etc.), location, management range, etc.; the first network topology structure refers to the network topology structure extracted from the preset node database with the current first core management node as the screening condition; the fused data sub-group is the data group obtained after the fused status data group is equally divided.

[0094] In this embodiment, the next-level node set is obtained by collecting the next-level nodes obtained according to the first network topology structure and the relationship between the nodes; the node relationship graph is a relationship graph formed by organizing the next-level node set of the core management node; the transmission path refers to the path obtained by analyzing the node relationship graph and capable of transmitting forest status data from the set location node to the target monitoring center; the first broadcast message is composed of the next-level node set of the first core management node and the node basic information; the purpose of the whole network broadcast is to enable all nodes in the network to obtain the necessary information for subsequent data transmission or processing.

[0095] In this embodiment, the path in-degree refers to the number of edges reaching a certain node; the successful transmission probability is used to express the possibility of successful transmission of the current fused data subpacket through the transmission path of the current first core management node; the selected transmission link refers to the transmission path with the highest probability of successful transmission in the current first core management node; the backup transmission link refers to the path with the lowest transmission delay among the transmission paths of the current first core management node other than the selected transmission link; jitter refers to the short-term, rapid, and unexpected changes in parameters such as amplitude, frequency, phase or arrival time during signal transmission, which indicates that data transmission is unstable.

[0096] In this embodiment, for example, there are transmission paths a1, a2, and a3 of the first core management node A1, and transmission paths b1, b2, b3, and b4 of the first core management node B1, wherein the probability of successful transmission of the transmission path a1 of the first core management node A1 is greater than the probability of successful transmission of the transmission paths a2 and a3; the probability of successful transmission of the transmission path b3 of the first core management node B1 is greater than the probability of successful transmission of the transmission paths b1, b2, and b4;

[0097] At this time, the transmission path a1 is used as the selected transmission link of the current first core management node A1, and the transmission path b3 is used as the selected transmission link of the current first core management node B1.

[0098] The beneficial effects of the above technical solution are: by grouping forest status data and allocating selected transmission links based on the Internet of Things technology to transmit the data to the target monitoring center, and when the selected transmission link jitters, the corresponding backup transmission link is started, which effectively improves the reliability of data transmission and the utilization of network resources, and is conducive to improving the timeliness of forest monitoring.

[0099] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, which obtains the success transmission probability of the fused data sub-packet for each transmission path of the current first core management node based on the obtained path in-degree, including:

[0100] Use network monitoring tools to monitor the current network status in real time and obtain key network performance parameters;

[0101] Extracting and analyzing historical transmission records within a preset time period of the current transmission path from the transmission record database to obtain the historical transmission success rate of each historical transmission using the current transmission path;

[0102] The path in-degree of the current transmission path, the historical transmission success rate, and the key network performance parameters are combined to calculate the successful transmission probability of the current transmission path.

[0103] In this embodiment, the network monitoring tool refers to a software system used to monitor and manage network traffic, user activities, and network resource usage. It is lightweight, low-overhead, and supports multiple communication protocols, such as Wireshark and Nagios. Key network performance parameters include network bandwidth utilization, latency, and packet loss rate. The transmission record database is used to store historical transmission records of the transmission path, including the number of successfully transmitted data packets, historical delays, etc. The path in-degree refers to the number of edges reaching a certain node. The successful transmission probability is used to express the possibility of successful transmission of the current fused data subpacket through the transmission path of the current first core management node.

[0104] The beneficial effect of the above technical solution is: by using network monitoring tools to monitor the current network status in real time, and combining historical data to calculate the successful transmission probability of the current transmission path, it provides data basis for subsequent screening of the transmission link with the highest successful transmission rate, thereby helping to improve the reliability of data transmission.

[0105] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things. The calculation formula of the successful transmission probability is as follows:

[0106] ; In the formula, It is represented as the probability of successful transmission of the fused data sub-packet for the i-th transmission path of the current first core management node; It is expressed as the average value of the historical transmission success rate of the i-th transmission path; It is expressed as the maximum historical transmission success rate of the i-th transmission path; It is represented as the path in-degree of the i-th transmission path; f is represented as the influence weight of the path in-degree on the successful transmission of the transmission path; It is represented as the set performance threshold of the jth key network performance parameter, ; is represented as the jth key network performance parameter, It is expressed as the influence weight of the jth key network performance parameter on the evaluation of network status; It is expressed as the influence weight of the current network status on the successful transmission of the transmission path; ln is expressed as the natural logarithm; e is expressed as the natural base.

[0107] In this embodiment, the weights assigned to key network performance parameters are obtained by solving a matrix constructed by using a hierarchical analysis method to compare key network performance parameters pairwise and score their relative importance; the key network performance parameters include network bandwidth utilization, delay, and packet loss rate.

[0108] In this embodiment, the weights assigned to the path in-degree and the network status are obtained by solving a matrix constructed by performing pairwise comparison and relative importance scoring using the hierarchical analysis method.

[0109] The beneficial effect of the above technical solution is: by combining the path in-degree of the transmission path with the historical transmission records to analyze and calculate the probability of successful transmission, it can provide data basis for subsequent screening of the transmission link with the highest successful transmission rate, thereby helping to improve the reliability of data transmission.

[0110] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, wherein the early warning module comprises:

[0111] Fire risk analysis unit: used for the target monitoring center to evaluate the fire risk of the current target forest according to the received forest condition data, and obtain a first risk assessment result;

[0112] An early warning unit is used to input the corresponding fire characterization data of the fire occurrence area into a level classification model obtained by a pre-trained neural network according to the first risk assessment result, and output the fire risk level of the current fire occurrence area if it is determined that a fire occurs in the current target forest and there is a fire occurrence area;

[0113] The fire occurrence area is combined with the corresponding fire risk level and fire characterization data to generate a fire alarm report and send it to the fire maintenance personnel;

[0114] The fire maintenance personnel receive the fire alarm report and handle the fire in the fire occurrence area;

[0115] If it is determined that a fire has occurred in the current target forest and there is an area where a fire may occur, the area where a fire may occur in the first risk assessment result is combined with the corresponding possible risk coefficient and possible risk data to generate a fire prevention report;

[0116] Generate a fire warning task according to the fire prevention report, and fill the fire prevention task into a fire prevention task list according to the possible risk factors from large to small;

[0117] The fire prevention personnel shall perform the fire prevention tasks in sequence according to the fire prevention task list.

[0118] In this embodiment, the forest condition data refers to the data obtained by real-time monitoring of the target forest condition by a preset monitoring device installed at a set position node, including first meteorological data, first smoke data and first thermal infrared data, wherein the data type of the first meteorological data includes three types: temperature data, humidity data and wind speed; the first risk assessment result is the result obtained by the target monitoring center evaluating the fire risk of the current forest based on the forest condition data received in real time, such as fire judgment results, fire occurrence areas, fire possible occurrence areas, fire characterization data and possible risk coefficients, etc., wherein the fire judgment results include two judgment results: a fire occurs in the current target forest, and a fire does not occur in the current target forest, which is based on the fire Whether there is a fire occurrence area or a fire possible area in the analysis results is determined; the fire occurrence area is the area where the fire has actually occurred in the current target forest obtained by the fire analysis model; the fire possible area is the area where the fire may occur in the current target forest obtained by the fire analysis model, but the fire has not actually occurred; the fire characterization data is the fire situation data obtained by the fire analysis model, such as the size of the fire and the speed of spread; the possible risk data is the meteorological data in the current forest condition data obtained by the fire analysis model that can be used to characterize the possible occurrence of fire in the current forest in the future, such as temperature data and wind speed; the possible risk coefficient is used to express the probability and degree of danger of fire in the current fire possible area.

[0119] In this embodiment, the level classification model is a model for classifying fire risk levels by training a neural network using data obtained after preprocessing and feature extraction of collected historical forest data as training data, wherein the historical forest data is composed of historical forest condition data and corresponding fire occurrence data, and the fire occurrence data refers to whether a fire has occurred and the severity of the fire; the fire risk levels include four levels: minor, severe, very severe and extremely severe.

[0120] In this embodiment, the fire alarm report consists of the report generation time, the fire occurrence area and the corresponding fire risk level and fire characterization data, which is used to notify fire maintenance personnel to deal with the fire; the fire prevention report consists of the possible fire occurrence area and the corresponding possible risk coefficient and possible risk data; the fire warning task is a task generated according to the fire prevention report, such as investigating the possible fire occurrence area; the fire prevention task list is a task list sorted from large to small according to the possible risk coefficient, which is obtained by sorting the fire warning tasks generated according to the warning unit. The purpose is to give priority to tasks with higher risks and ensure that the risk of fire can be minimized to the greatest extent possible under limited resources, thereby more effectively preventing the occurrence of fire; fire prevention personnel refer to staff who perform fire prevention tasks.

[0121] The beneficial effect of the above technical solution is that by conducting fire risk analysis, fire risk level identification and fire warning on the target forest, the accuracy and timeliness of forest fire warning can be effectively improved, and the intelligent level of forest fire prevention and control can be enhanced.

[0122] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, wherein the fire risk analysis unit comprises:

[0123] Fire judgment unit: used for the target monitoring center to perform data cleaning, data conversion and normalization on the currently acquired forest status data to obtain the first status data;

[0124] Inputting the first condition data into a pre-established fire analysis model to obtain a fire analysis result;

[0125] When there is a fire occurrence area or a fire possible area in the fire analysis result, it is determined that a fire occurs in the current target forest;

[0126] When there is no fire occurrence area and no fire possible area in the fire analysis result, it is determined that no fire occurs in the current target forest;

[0127] Possible risk analysis unit: used to calculate the possible risk coefficient of the fire possible area using the possible risk data when there is a fire possible area in the fire analysis result;

[0128] The calculation formula of possible risk factor is as follows:

[0129] ; In the formula, It is expressed as the possible risk coefficient of the current r-th fire-prone area; It is represented by the number of types of meteorological data contained in the corresponding possible risk data of the current r-th fire possible area, where: ; It is represented by the set data threshold of the t-th type of meteorological data contained in the corresponding possible risk data of the current r-th fire possible area, where t ; It is represented by the t-th type of meteorological data contained in the corresponding possible risk data of the current r-th fire-prone area; It is expressed as the number of combustible materials existing in the current r-th fire-prone area; It is expressed as the weight of the impact of the amount of combustibles on the possibility of fire occurrence; It is represented by the number of historical fires in the current r-th fire-prone area; It is expressed as the weight of the impact of the number of historical fire occurrences on the possibility of fire occurrence;

[0130] Assessment generation unit: used to output the fire occurrence area determined according to the fire analysis results, the fire possible occurrence area, fire characterization data, possible risk data, fire judgment results and the possible risk coefficient obtained by the possible risk analysis unit as the first risk assessment result.

[0131] In this embodiment, the forest condition data refers to first meteorological data, first smoke data and first thermal infrared data, wherein the data type of the first meteorological data includes three types: temperature data, humidity data and wind speed data; the first condition data is the data obtained after data cleaning, data conversion and normalization processing of the forest condition data.

[0132] In this embodiment, the steps of obtaining the fire analysis model are as follows:

[0133] 1. Extract a preset amount of historical fire record data from the forest fire record database;

[0134] 2. After data preprocessing of the extracted fire history record data, features associated with fire identification are extracted, such as temperature, humidity, smoke alarm signals, and thermal infrared alarm signals, to obtain a first feature set;

[0135] 3. Using the preprocessed fire history record data and the first feature set as training data, a neural network is trained to obtain a fire analysis model;

[0136] Among them, the forest fire record database is used to store historical fire record data of the forest; the preset quantity is pre-set; the historical fire record data includes the time of historical fire occurrence, the historical fire occurrence area, the historical fire duration, the historical forest condition data received by the target monitoring center during the historical fire duration, the cause of the fire, the size of the fire, the spread speed and the fire loss, etc.; data preprocessing refers to data cleaning, data conversion and data standardization processing.

[0137] In this embodiment, the fire analysis result refers to the fire occurrence area, fire characterization data, fire possible area and possible risk data, wherein the fire occurrence area is the area where the fire has actually occurred in the current target forest obtained by the fire analysis model; the fire possible area is the area where the fire may occur in the current target forest obtained by the fire analysis model, but the fire has not actually occurred yet; the fire characterization data is the fire situation data obtained by the fire analysis model, such as the size of the fire and the spread speed; the possible risk data is the meteorological data in the current forest condition data obtained by the fire analysis model that can be used to characterize the possible future fire in the current forest, such as temperature data and wind speed; the possible risk coefficient is used to express the probability and danger level of fire in the current fire possible area; the fire judgment result includes two judgment results: the fire occurred in the current target forest, and the fire did not occur in the current target forest, which is determined based on whether there is a fire occurrence area or a fire possible area in the fire analysis result; the weights assigned to the number of combustibles and the number of historical fires are obtained by solving the matrix constructed after pairwise comparison and relative importance scoring using the hierarchical analysis method.

[0138] The beneficial effects of the above technical solution are: by analyzing forest status data in real time, quickly identifying fire areas or areas where fire may occur, and calculating the possible risk coefficient of fire areas, it can provide priority sorting of fire areas, help to timely discover fire hazards, reasonably allocate resources, and provide valuable time for subsequent emergency response and fire fighting operations. Improve the efficiency and accuracy of fire emergency response.

[0139] The embodiment of the present invention provides a forest fire real-time monitoring and early warning system based on the Internet of Things, wherein the remote monitoring module comprises:

[0140] Remote access unit: used for the target user to establish a connection with the target monitoring center by using the set remote device and pre-set software, and then independently select the user verification method for identity authentication;

[0141] After the target user's identity authentication is successful, the target user automatically logs into the user interface of the target monitoring center and views the forest status data received in real time by the target monitoring center on the user interface;

[0142] Remote control unit: used to combine and analyze the user control requirements of the current target user and the device control authority using the instruction generation unit to generate a user control instruction; and use the instruction execution unit to control the preset monitoring device to execute the user control instruction;

[0143] Instruction generation unit: used by the target user to set remote devices and preset software, and upload user control requirements;

[0144] According to the user control requirements of the current target user, obtain the corresponding first device control authority;

[0145] Compare the first device control permission with the specified device control permission range of the current target user, and if the first device control permission does not exceed the specified device control permission range of the current target user, generate a user control instruction based on the current user control requirement;

[0146] If the first device control permission exceeds the specified device control permission range, the permission in the first device control permission that does not exceed the specified device control permission range of the current target user is regarded as the first selected permission; based on the control requirements of the current target user that can be realized based on the first selected permission, the user control instruction is generated;

[0147] Instruction execution unit: used to transmit the user control instruction to the target monitoring center by using the set remote device and preset software;

[0148] The target monitoring center parses the user control instruction and performs format conversion to obtain the target control instruction;

[0149] The target monitoring center transmits the target control instruction to the corresponding preset monitoring device;

[0150] The preset monitoring device executes the received target control instruction and feeds back the execution result to the target monitoring center;

[0151] The target user views the remote control results in the user interface by utilizing the set remote device and preset software.

[0152] In this embodiment, the target user refers to a user who is not in the target forest area and is far away from the monitoring equipment and the target monitoring center; the set remote device refers to a smart mobile device, such as a mobile phone, tablet, or computer; the preset software refers to a software application running on the set remote device; the user authentication methods include user name and password authentication, fingerprint recognition authentication, and facial recognition authentication; the user interface is used to view the forest status data received in real time by the target monitoring center, upload user control requirements, and view remote control results, etc.

[0153] In this embodiment, user control requirements refer to the control requirements of the current target user for the preset monitoring equipment, such as adjusting the equipment sampling frequency, modifying the equipment configuration parameters, starting or stopping equipment data collection; the first equipment control authority refers to the control authority required for the current target user to realize the user control requirements; the specified equipment control authority range refers to all control authorities granted to the current target user.

[0154] In this embodiment, the user control instruction refers to the specific operation that the target user wants the preset monitoring device to perform; the first selected authority refers to the control authority in the first device control authority that belongs to the scope of the specified device control authority; the user control instruction is a control instruction generated based on the user control demand; the target control instruction is a control instruction obtained after the format of the user control instruction is converted into a format that can be understood by the preset monitoring device; the execution result refers to the execution result and corresponding device status change generated by the preset monitoring device executing the instruction after receiving the target control instruction, wherein the execution result includes two results: execution success and execution failure; the device status change refers to the result after the preset monitoring device executes the target control instruction, such as the device sampling frequency adjustment result, the device configuration parameter modification result, etc.

[0155] The beneficial effect of the above technical solution is that through the user's remote access to the monitoring center and remote control of the monitoring equipment, the user can timely understand the monitoring site, reduce labor costs and maintenance costs, and improve the operating efficiency of the overall system.

[0156] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A real-time forest fire monitoring and early warning system based on the Internet of Things, characterized in that: include: Data collection module: used to monitor the status of the target forest in real time using the pre-installed monitoring equipment installed at the set location node to obtain forest status data; Data transmission module: used to transmit the forest status data to a target monitoring center using Internet of Things technology; Early warning module: used by the target monitoring center to carry out fire risk early warning and fire risk level classification of the target forest based on the received forest condition data; Remote monitoring module: used to enable target users to remotely access the target monitoring center and intelligently control monitoring equipment; Wherein, the early warning module includes: Fire risk analysis unit: used for the target monitoring center to evaluate the fire risk of the current target forest according to the received forest condition data, and obtain a first risk assessment result; An early warning unit is used to input the corresponding fire characterization data of the fire occurrence area into a level classification model obtained by a pre-trained neural network according to the first risk assessment result, and output the fire risk level of the current fire occurrence area if it is determined that a fire occurs in the current target forest and there is a fire occurrence area; The fire occurrence area is combined with the corresponding fire risk level and fire characterization data to generate a fire alarm report and send it to the fire maintenance personnel; The fire maintenance personnel receive the fire alarm report and handle the fire in the fire occurrence area; If it is determined that a fire has occurred in the current target forest and there is an area where a fire may occur, the area where a fire may occur in the first risk assessment result is combined with the corresponding possible risk coefficient and possible risk data to generate a fire prevention report; generating fire prevention tasks according to the fire prevention report, and filling the fire prevention tasks into a fire prevention task list according to possible risk factors from large to small; The fire prevention personnel perform the fire prevention tasks in order according to the fire prevention task list; Wherein, the fire risk analysis unit comprises: Fire judgment unit: used for the target monitoring center to perform data cleaning, data conversion and normalization on the currently acquired forest status data to obtain the first status data; Inputting the first condition data into a pre-established fire analysis model to obtain a fire analysis result; When there is a fire occurrence area or a fire possible area in the fire analysis result, it is determined that a fire occurs in the current target forest; When there is no fire occurrence area and no fire possible area in the fire analysis result, it is determined that no fire occurs in the current target forest; Possible risk analysis unit: used to calculate the possible risk coefficient of the fire possible area using the possible risk data when there is a fire possible area in the fire analysis result; The calculation formula of possible risk factor is as follows: ; In the formula, It is expressed as the possible risk coefficient of the current r-th fire-prone area; It is represented by the number of types of meteorological data contained in the corresponding possible risk data of the current r-th fire possible area, where: ; It is represented by the set data threshold of the t-th type of meteorological data contained in the corresponding possible risk data of the current r-th fire possible area, where t ; It is represented by the t-th type of meteorological data contained in the corresponding possible risk data of the current r-th fire-prone area; It is expressed as the number of combustible materials existing in the current r-th fire-prone area; It is expressed as the weight of the impact of the amount of combustibles on the possibility of fire occurrence; It is represented by the number of historical fires in the current r-th fire-prone area; It is expressed as the weight of the impact of the number of historical fire occurrences on the possibility of fire occurrence; Assessment generation unit: used to output the fire occurrence area determined according to the fire analysis results, the fire possible occurrence area, fire characterization data, possible risk data, fire judgment results and the possible risk coefficient obtained by the possible risk analysis unit as the first risk assessment result.

2. According to the Internet of Things-based forest fire real-time monitoring and early warning system according to claim 1, it is characterized in that: Pre-installed monitoring equipment includes meteorological sensors, smoke detectors and thermal infrared sensors.

3. The real-time forest fire monitoring and early warning system based on the Internet of Things according to claim 1 is characterized in that: The data transmission module comprises: Node transmission unit: used to obtain the first core management node to which each set position node belongs in the current transmission period; Transmitting the forest status data acquired by the set location node to the corresponding first core management node in real time; Data processing unit: used for the first core management node to receive and fuse the forest status data transmitted by all set position nodes within the set clustering range to obtain a fused status data group; The first core management node divides the fusion status data group into equal parts to obtain fusion data sub-groups; Using the current first core management node as a screening condition, the first network topology structure and node basic information are obtained from the key node information extracted from the preset node database; Arranging the next-level node set of the current first core management node determined according to the first network topology structure to form a node relationship graph; According to the node relationship diagram, obtaining the transmission path of the current first core management node; Based on the next-level node set and node basic information of the current first core management node, a first broadcast message is generated for network-wide broadcast; Obtaining the path in-degree of each transmission path of the current first core management node; Based on the obtained path in-degree, obtaining the probability of successful transmission of the fused data sub-packet for each transmission path of the current first core management node; Link determination unit: used to traverse all first core management nodes, sort the calculated success transmission probability of each transmission path of the first core management node, and use the transmission path with the highest success transmission probability as the selected transmission link of the current first core management node; Traversing all first core management nodes, obtaining the transmission delays of all transmission paths of each first core management node except the selected transmission link, and selecting the path with the lowest transmission delay as the backup transmission link corresponding to the first core management node; Transmission unit: used to transmit the current fusion data sub-groups to the target monitoring center according to the selected transmission link; When the selected transmission link of the first core management node jitters, the corresponding standby transmission link is started to transmit the fused data sub-packets to the target monitoring center.

4. The real-time forest fire monitoring and early warning system based on the Internet of Things according to claim 3 is characterized in that: Based on the obtained path in-degree, obtaining the probability of successful transmission of the fused data sub-packet for each transmission path of the current first core management node includes: Use network monitoring tools to monitor the current network status in real time and obtain key network performance parameters; Extracting and analyzing historical transmission records within a preset time period of the current transmission path from the transmission record database to obtain the historical transmission success rate of each historical transmission using the current transmission path; The path in-degree of the current transmission path, the historical transmission success rate, and the key network performance parameters are combined to calculate the successful transmission probability of the current transmission path.

5. The real-time forest fire monitoring and early warning system based on the Internet of Things according to claim 4 is characterized in that: The formula for calculating the probability of successful transmission is as follows: ; In the formula, It is represented as the probability of successful transmission of the fused data sub-packet for the i-th transmission path of the current first core management node; It is expressed as the average value of the historical transmission success rate of the i-th transmission path; It is expressed as the maximum historical transmission success rate of the i-th transmission path; It is represented as the path in-degree of the i-th transmission path; f is represented as the influence weight of the path in-degree on the successful transmission of the transmission path; It is represented as the set performance threshold of the jth key network performance parameter, ; is represented as the jth key network performance parameter, It is expressed as the influence weight of the jth key network performance parameter on the evaluation of network status; It is expressed as the influence weight of the current network status on the successful transmission of the transmission path; ln is expressed as the natural logarithm; e is expressed as the natural base.

6. The real-time forest fire monitoring and early warning system based on the Internet of Things according to claim 1 is characterized in that: The remote monitoring module comprises: Remote access unit: used for the target user to establish a connection with the target monitoring center by using the set remote device and pre-set software, and then independently select the user verification method for identity authentication; After the target user's identity authentication is successful, the target user automatically logs into the user interface of the target monitoring center and views the forest status data received in real time by the target monitoring center on the user interface; Remote control unit: used to combine and analyze the user control requirements of the current target user and the device control authority using the instruction generation unit to generate a user control instruction; and use the instruction execution unit to control the preset monitoring device to execute the user control instruction; Instruction generation unit: used by the target user to set remote devices and preset software, and upload user control requirements; According to the user control requirements of the current target user, obtain the corresponding first device control authority; Compare the first device control permission with the specified device control permission range of the current target user, and if the first device control permission does not exceed the specified device control permission range of the current target user, generate a user control instruction based on the current user control requirement; If the first device control permission exceeds the specified device control permission range, the permission in the first device control permission that does not exceed the specified device control permission range of the current target user is regarded as the first selected permission; based on the control requirements of the current target user that can be realized based on the first selected permission, the user control instruction is generated; Instruction execution unit: used to transmit the user control instruction to the target monitoring center by using the set remote device and preset software; The target monitoring center parses the user control instruction and performs format conversion to obtain the target control instruction; The target monitoring center transmits the target control instruction to the corresponding preset monitoring device; The preset monitoring device executes the received target control instruction and feeds back the execution result to the target monitoring center; The target user views the remote control results in the user interface by utilizing the set remote device and preset software.

Images