Forestry engineering forest fire prevention monitoring system and method

Abstract

The invention discloses a forest fire prevention and monitoring system and method for forestry engineering, and belongs to the technical field of forest fire monitoring and prevention. The system comprises a monitoring terminal, a data transmission module, a central processing module, an early warning module and a mobile terminal; the monitoring terminal is used for acquiring temperature, humidity, smoke concentration and image information in a forest environment; the data transmission module transmits data acquired by the monitoring terminal to the central processing module; the central processing module analyzes and processes the data, judges the fire risk level, controls the early warning module to give out corresponding early warning, and sends the information to the mobile terminal at the same time. According to the forestry engineering forest fire prevention and monitoring system and method, through multi-dimensional monitoring and intelligent analysis, the accuracy and timeliness of forest fire prevention and monitoring are improved, and the probability of forest fire occurrence can be effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of forest fire monitoring and prevention technology, and in particular to a forestry engineering forest fire prevention and monitoring system and method. Background Technology

[0002] Currently, forest fire prevention and monitoring in forestry projects mainly rely on ground patrols and lookout tower observations. Ground patrols require a large manpower investment; professional forest rangers must walk several kilometers daily, traversing mountains and forests for inspection. Even so, facing treacherous cliffs, deep and complex canyons and dense forests, patrol personnel often find it difficult to reach these areas, resulting in many areas becoming blind spots for monitoring. According to statistics, in forest areas with complex terrain, the effective coverage rate of ground patrols is less than 60%. While lookout tower observations can expand the field of vision due to their height advantage, they are extremely dependent on good weather conditions. On foggy mornings, visibility is less than 100 meters, making it difficult for lookouts to distinguish the outlines of trees 100 meters away. During torrential rain, rainwater washes through the glass, creating a water curtain that obscures the view. In dusty weather, particles floating in the air severely interfere with visibility. Under these adverse weather conditions, the effectiveness of lookout tower observations decreases by more than 70%, and due to the limitations of the manual shift system, information transmission is delayed, making it difficult to detect fire hazards in a timely manner.

[0003] With the development of technology, sensor-based monitoring systems have emerged, bringing new directions to forest fire prevention. However, existing monitoring systems mostly focus on monitoring single indicators. For example, temperature sensors are prone to false alarms when the surface temperature of rocks under direct sunlight can reach over 60°C during the hot summer months. Similarly, in humid environments, water vapor condenses on the surface of smoke sensors, interfering with smoke detection signals and causing missed alarms. Furthermore, the data processing modules of these systems generally have shortcomings. Faced with the massive amounts of data transmitted in real time from sensors, they cannot utilize big data analysis or artificial intelligence algorithms for in-depth analysis. This makes it difficult to establish accurate fire risk assessment models or predict fire development trends. When real fire hazards appear, they struggle to issue accurate warnings within the critical timeframe, failing to meet the actual needs of forest fire prevention and monitoring. Summary of the Invention

[0004] The purpose of this invention is to provide a forest fire prevention and monitoring system and method for forestry engineering, which solves the problems of limited monitoring range, poor real-time performance, single monitoring indicators, easy false alarms and missed alarms, and insufficient data processing and early warning capabilities in existing forest fire prevention and monitoring technologies.

[0005] To achieve the above objectives, the present invention provides a forest fire prevention and monitoring system for forestry engineering, comprising:

[0006] The monitoring terminal includes monitoring nodes set at different locations. Each monitoring node is equipped with a temperature sensor, a humidity sensor, a smoke sensor, an image acquisition device, and a microprocessor. The microprocessor is connected to the temperature sensor, humidity sensor, smoke sensor, and image acquisition device respectively, and is used to perform preliminary processing and storage of the collected data.

[0007] The data transmission module is connected to the microprocessor of the monitoring terminal and is used to transmit the data collected and preliminarily processed by the monitoring terminal to the central processing module.

[0008] The central processing module includes a data receiving unit, a data storage unit, a data analysis unit, and a control unit;

[0009] The early warning module, connected to the control unit of the central processing module, includes an audible and visual alarm and an information push device;

[0010] The mobile terminal is wirelessly connected to the central processing module and the early warning module, and is used to receive monitoring data sent by the central processing module and early warning information sent by the early warning module.

[0011] Preferably, the data transmission module uses wireless communication, including but not limited to 4G, 5G, and LoRa.

[0012] This invention also provides a method for forest fire prevention and monitoring in forestry engineering, comprising the following steps:

[0013] S1. The monitoring terminal uses various sensors to collect and perceive the ring information, and transmits the collected data to the microprocessor for preliminary processing and storage.

[0014] S2. The microprocessor sends the pre-processed data to the data receiving unit of the central processing module through the data transmission module;

[0015] S3. The data receiving unit transmits the received data to the data storage unit for storage, and simultaneously transmits it to the data analysis unit.

[0016] S4. The data analysis unit calls the preset fire risk assessment model to comprehensively analyze temperature, humidity, smoke concentration and image information, and determines the risk level according to the preset threshold.

[0017] S5. The control unit controls the early warning module to work based on the fire risk level determined by the data analysis unit.

[0018] Preferably, in S1, the monitoring nodes of the monitoring terminal are distributed in different areas of the forest. Temperature sensors, humidity sensors, smoke sensors and image acquisition devices collect temperature, humidity, smoke concentration and image information of their respective areas, and transmit the collected data to the microprocessor for preliminary processing and storage.

[0019] Preferably, S2 specifically includes the following steps:

[0020] S21. First, prioritize the data, dividing it into three priority levels: abnormal data (P1 level), routine monitoring data (P2 level), and node status information (P3 level). The priority weights satisfy P1:P2:P3 = 5:3:2. The transmission priority index is calculated using the formula:

[0021]

[0022] Among them, P i ω represents the transmission priority index of the i-th level of data; i To ensure that P1 level data has priority in occupying the transmission channel, the corresponding level weights are assigned.

[0023] S22. A transmission strategy combining time-slotted ALOHA protocol and dynamic backoff mechanism is adopted. P1 level data directly occupies the current time slot for transmission. If a conflict occurs, the backoff time T is used to resolve the conflict. b =2 n ×Δt, where n is the number of collisions and Δt is the base time interval. If Δt = 10ms, retry. P2 / P3 level data needs to wait for an idle time slot, with initial backoff times of 50ms and 100ms respectively.

[0024] S23. The microprocessor collects the received signal strength indicator (RSSI) in real time. When RSSI ≤ -100dBm, it automatically increases the transmit power to 20dBm; when RSSI ≥ -70dBm, it decreases it to 10dBm, achieving a dynamic balance between power consumption and transmission distance. The power adjustment formula is as follows:

[0025]

[0026] In the formula, P t This indicates the adjusted transmit power;

[0027] S24. Large data packets are fragmented into 1024-byte segments, and the AES-128-GCM encryption algorithm is used. Each segment is appended with a 16-byte checksum and a 3-byte segment index, and transmitted through the FRMPayload field of the LoRaWAN protocol to ensure data integrity and security.

[0028] Preferably, step S4 specifically includes the following steps:

[0029] S41. Extract feature parameters;

[0030] In addition to temperature T, humidity H, smoke concentration S, and image confidence I, forest type parameter λ and seasonal coefficient β are added.

[0031] Among them, the forest type parameter λ: coniferous forest = 1.2, broad-leaved forest = 0.8, mixed forest = 1.0; the seasonal coefficient β: dry season = 1.3, wet season = 0.7, transitional season = 1.0;

[0032] S42. Adjust the weights of each indicator dynamically based on forest type and season, using the following formula:

[0033] ω T =0.3×λ×β,ω H =0.2×(2-λ×β);

[0034] ω S =0.3×λ×β,ω I =0.2×(2-λ×β);

[0035] In the formula, ω T ω H ω S ω I The weights are respectively for temperature, humidity, smoke concentration, and image information; and satisfy: ω T +ω H +ω S +ω I =1;

[0036] S43. Standardization processing, the calculation formula is as follows:

[0037]

[0038] The temperature threshold is set to T0 = 35℃, and the critical temperature is T. c =80℃; humidity threshold H0 = 40%, critical humidity H c =20%; smoke threshold S0 = 0.5 mg / m³ 3 ;T s H s S s I s These are the standardized scores for temperature, humidity, smoke concentration, and image information, respectively; T represents the measured temperature; H represents the measured humidity; S represents the measured smoke concentration; and I represents the confidence level of image recognition for suspected fire, ranging from 0 to 1.

[0039] S44. Risk Index Calculation:

[0040] FRI = ω T +ω H ×H s +ω s ×S s +ω I ×I s ;

[0041] S45. When at least one of the following conditions exists, namely, the temperature exceeds the preset temperature threshold, the humidity is lower than the preset humidity threshold, or the smoke concentration exceeds the preset smoke concentration threshold, and suspected fire features appear in the image, it is determined to be a high fire risk level.

[0042] When at least one of the temperature, humidity, and smoke concentration exceeds a preset threshold, but no suspected fire features appear in the image, it is judged to be at a medium fire risk level.

[0043] When the temperature, humidity, and smoke concentration are all within the normal range, and there are no abnormalities in the image, it is judged to be a low fire risk level.

[0044] Preferably, in S45, FRI ≥ 0.7 is considered high risk, 0.3 ≤ FRI < 0.7 is considered medium risk, and FRI < 0.3 is considered low risk.

[0045] Preferably, in S5, if the fire risk level is high, the sound and light alarm is controlled to issue a set maximum power sound and light warning, and at the same time the information push device pushes emergency warning information to the mobile terminal, including the fire risk location, risk level and related monitoring data.

[0046] If the fire risk level is medium, the sound and light alarm will issue a medium-power sound and light warning, and the information push device will push the warning information to the mobile terminal.

[0047] If the fire risk level is low, the early warning module will not work, and the central processing module will only periodically send the monitoring data to the mobile terminal.

[0048] Therefore, the beneficial effects of the forest fire prevention and monitoring system and method for forestry engineering described above are as follows:

[0049] (1) The monitoring terminal of the present invention adopts multi-sensor fusion technology to collect temperature, humidity, smoke concentration and image information at the same time, realizing multi-dimensional monitoring, avoiding the false alarm and missed alarm problems that are easy to occur in single indicator monitoring, and improving the accuracy of monitoring.

[0050] (2) Priority scheduling, dynamic power adjustment and encrypted fragmentation technology are introduced in the data transmission link to reduce node power consumption while ensuring real-time transmission of key data, thereby enhancing the reliability and security of data transmission in complex forest environments.

[0051] (3) The central processing module conducts comprehensive analysis of multi-dimensional data through a preset fire risk assessment model, introduces a dynamic weight adjustment mechanism for forest type and season, improves the adaptability and accuracy of risk assessment, can accurately determine the fire risk level, and issue corresponding warnings according to different levels, thereby improving the pertinence and effectiveness of fire prevention.

[0052] (4) Setting up mobile terminals enables staff to view monitoring data and receive early warning information anytime and anywhere, facilitating timely response measures and improving the flexibility and response speed of forest fire prevention and monitoring.

[0053] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of the composition structure of a forest fire prevention and monitoring system for forestry engineering according to the present invention;

[0055] Figure 2 This is a schematic diagram of the composition structure of the monitoring terminal of a forest fire prevention and monitoring system for forestry engineering according to the present invention;

[0056] Figure 3 This is a flowchart illustrating a forest fire prevention and monitoring method for forestry engineering according to the present invention. Detailed Implementation

[0057] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.

[0058] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0059] Example 1

[0060] like Figure 1 As shown, the present invention provides a forest fire prevention and monitoring system for forestry engineering, comprising:

[0061] The monitoring terminal includes monitoring nodes set up at different locations. In this embodiment, the monitoring nodes are distributed in the forest at a density of one node every 500 meters. Figure 2As shown, each monitoring node is equipped with a temperature sensor, a humidity sensor, a smoke sensor, an image acquisition device, and a microprocessor. The temperature sensor is used to collect forest environmental temperature, the humidity sensor is used to collect forest environmental humidity, the smoke sensor is used to collect forest environmental smoke concentration, and the image acquisition device is used to collect forest environmental image information; the microprocessor is connected to the temperature sensor, humidity sensor, smoke sensor, and image acquisition device respectively, and is used to perform preliminary processing and storage of the collected data.

[0062] The temperature sensor, humidity sensor, and smoke sensor all use common models. The image acquisition unit uses a high-definition camera, capable of capturing clear images both day and night.

[0063] The data transmission module, connected to the microprocessor of the monitoring terminal, transmits the data collected and preliminarily processed by the monitoring terminal to the central processing module. The data transmission module uses wireless communication methods, including but not limited to 4G, 5G, and LoRa, featuring low power consumption and long-distance transmission. This embodiment uses LoRa wireless communication (SX1278 chip), with a communication distance of 3-5 kilometers, suitable for use in complex environments such as forests.

[0064] The central processing module includes a data receiving unit, a data storage unit, a data analysis unit, and a control unit. The data receiving unit receives data transmitted by the data transmission module. The data storage unit stores the received data. The data analysis unit analyzes and processes the received data, and, in conjunction with a preset fire risk assessment model, determines the forest fire risk level. The control unit controls the operation of the early warning module based on the fire risk level.

[0065] The early warning module, connected to the control unit of the central processing module, includes an audible and visual alarm and an information push device. The audible and visual alarm issues an on-site warning, emitting a 1000Hz / 120dB siren and a red strobe (10Hz) for high-risk situations; and a 500Hz / 80dB siren and a yellow strobe (5Hz) for medium-risk situations. The information push device sends the warning information to the mobile terminals of relevant personnel. Pushing warnings to mobile terminals via a 2G network ensures signal stability.

[0066] The mobile terminal is wirelessly connected to the central processing module and the early warning module. It is used to receive monitoring data sent by the central processing module and early warning information sent by the early warning module. Staff can view real-time monitoring data and perform remote operations through the mobile terminal.

[0067] like Figure 3 As shown, the present invention also provides a method for forest fire prevention and monitoring in forestry engineering, comprising the following steps:

[0068] S1. The monitoring terminal uses various sensors to collect and perceive ring information, and transmits the collected data to the microprocessor for preliminary processing and storage.

[0069] The monitoring nodes of the monitoring terminal are distributed in different areas of the forest. Temperature sensors, humidity sensors, smoke sensors and image acquisition devices collect temperature, humidity, smoke concentration and image information of the area respectively. The monitoring nodes collect environmental data every 30 seconds and transmit the collected data to the microprocessor for preliminary processing and storage.

[0070] S2. The microprocessor sends the pre-processed data to the data receiving unit of the central processing module through the data transmission module, specifically including the following steps:

[0071] S21. First, prioritize the data, dividing it into three priority levels: abnormal data (P1 level), routine monitoring data (P2 level), and node status information (P3 level). The priority weights satisfy P1:P2:P3 = 5:3:2. The transmission priority index is calculated using the formula:

[0072]

[0073] Among them, P i ω represents the transmission priority index of the i-th level of data; i To ensure that P1 level data occupies the transmission channel with priority, the corresponding level weights are assigned.

[0074] S22. A transmission strategy combining time-slotted ALOHA protocol and dynamic backoff mechanism is adopted. P1 level data directly occupies the current time slot for transmission. If a conflict occurs, the backoff time T is used to resolve the conflict. b =2 n ×Δt, where n is the number of collisions and Δt is the base time interval. If Δt = 10ms, retry. P2 / P3 level data needs to wait for an idle time slot, with initial backoff times of 50ms and 100ms respectively.

[0075] S23. The microprocessor collects the received signal strength indicator (RSSI) in real time. When RSSI ≤ -100dBm, it automatically increases the transmit power to 20dBm; when RSSI ≥ -70dBm, it decreases it to 10dBm, achieving a dynamic balance between power consumption and transmission distance. The power adjustment formula is as follows:

[0076]

[0077] In the formula, P t This indicates the adjusted transmit power.

[0078] S24. Large data packets are fragmented into 1024-byte segments, and the AES-128-GCM encryption algorithm is used. Each segment is appended with a 16-byte checksum and a 3-byte segment index, and transmitted through the FRMPayload field of the LoRaWAN protocol to ensure data integrity and security.

[0079] S3. The data receiving unit transmits the received data to the data storage unit for storage, and at the same time transmits it to the data analysis unit.

[0080] S4. The data analysis unit calls the preset fire risk assessment model to comprehensively analyze temperature, humidity, smoke concentration, and image information, and determines the risk level based on preset thresholds. This includes the following steps:

[0081] S41. Extract feature parameters;

[0082] In addition to temperature T, humidity H, smoke concentration S, and image confidence I, forest type parameter λ and seasonal coefficient β are added.

[0083] Among them, the forest type parameter λ: coniferous forest = 1.2, broad-leaved forest = 0.8, mixed forest = 1.0; the seasonal coefficient β: dry season = 1.3, wet season = 0.7, transitional season = 1.0.

[0084] S42. Adjust the weights of each indicator dynamically based on forest type and season, using the following formula:

[0085] ω T =0.3×λ×β,ω H =0.2×(2-λ×β)

[0086] ω S =0.3×λ×β,ω I =0.2×(2-λ×β)

[0087] In the formula, ω T ω H ω S ω I The weights are respectively for temperature, humidity, smoke concentration, and image information; and satisfy: ω T +ω H +ω S +ω I =1

[0088] S43. Standardization processing, the calculation formula is as follows:

[0089]

[0090] The temperature threshold is set to T0 = 35℃, and the critical temperature is T. c =80℃; humidity threshold H0 = 40%, critical humidity Hc =20%; smoke threshold S0 = 0.5 mg / m³ 3 ;T s H s S s I s These are the standardized scores for temperature, humidity, smoke concentration, and image information, respectively; T represents the measured temperature; H represents the measured humidity; S represents the measured smoke concentration; and I represents the confidence level of image recognition for suspected fire, ranging from 0 to 1.

[0091] S44. Risk Index Calculation:

[0092] FRI = ω T +ω H ×H s +ω s ×S s +ω I ×I s

[0093] S45. When at least one of the following conditions exists—temperature exceeding a preset temperature threshold, humidity below a preset humidity threshold, or smoke concentration exceeding a preset smoke concentration threshold—and suspected fire features appear in the image, the fire risk level is determined to be high.

[0094] When at least one of the temperature, humidity, or smoke concentration exceeds a preset threshold, but no suspected fire features appear in the image, it is determined to be a medium fire risk level.

[0095] When the temperature, humidity, and smoke concentration are all within the normal range, and there are no abnormalities in the image, it is judged to be a low fire risk level.

[0096] In this implementation, FRI ≥ 0.7 is defined as high risk, 0.3 ≤ FRI < 0.7 as medium risk, and FRI < 0.3 as low risk.

[0097] S5. The control unit controls the early warning module to work based on the fire risk level determined by the data analysis unit.

[0098] If the fire risk level is high, the sound and light alarm will be controlled to issue a sound and light warning at the maximum power set, and at the same time the information push device will push emergency warning information to the mobile terminal, including the fire risk location, risk level and relevant monitoring data.

[0099] If the fire risk level is medium, the sound and light alarm will issue a medium-power sound and light warning, and the information push device will push the warning information to the mobile terminal.

[0100] If the fire risk level is low, the early warning module will not work, and the central processing module will only periodically send the monitoring data to the mobile terminal.

[0101] Therefore, the present invention adopts the above-mentioned forestry engineering forest fire prevention and monitoring system and method, which improves the accuracy and timeliness of forest fire prevention and monitoring through multi-dimensional monitoring and intelligent analysis, and can effectively reduce the probability of forest fires.

[0102] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A forestry engineering forest fire prevention and monitoring system, characterized in that, include: The monitoring terminal includes monitoring nodes set at different locations. Each monitoring node is equipped with a temperature sensor, a humidity sensor, a smoke sensor, an image acquisition device, and a microprocessor. The microprocessor is connected to the temperature sensor, humidity sensor, smoke sensor, and image acquisition device respectively, and is used to perform preliminary processing and storage of the collected data. The data transmission module is connected to the microprocessor of the monitoring terminal and is used to transmit the data collected and preliminarily processed by the monitoring terminal to the central processing module. The central processing module includes a data receiving unit, a data storage unit, a data analysis unit, and a control unit; The early warning module, connected to the control unit of the central processing module, includes an audible and visual alarm and an information push device; The mobile terminal is wirelessly connected to the central processing module and the early warning module, and is used to receive monitoring data sent by the central processing module and early warning information sent by the early warning module.

2. The forest fire prevention and monitoring system and method for forestry engineering according to claim 1, characterized in that: The data transmission module uses wireless communication methods, including but not limited to 4G, 5G, and LoRa.

3. A method for forest fire prevention and monitoring in forestry engineering, characterized in that, Includes the following steps: S1. The monitoring terminal uses various sensors to collect and perceive the ring information, and transmits the collected data to the microprocessor for preliminary processing and storage. S2. The microprocessor sends the pre-processed data to the data receiving unit of the central processing module through the data transmission module; S3. The data receiving unit transmits the received data to the data storage unit for storage, and simultaneously transmits it to the data analysis unit. S4. The data analysis unit calls the preset fire risk assessment model to comprehensively analyze temperature, humidity, smoke concentration and image information, and determines the risk level according to the preset threshold. S5. The control unit controls the early warning module to work based on the fire risk level determined by the data analysis unit.

4. The forest fire prevention and monitoring method for forestry engineering according to claim 3, characterized in that: In S1, the monitoring nodes of the monitoring terminal are distributed in different areas of the forest. Temperature sensors, humidity sensors, smoke sensors and image acquisition devices collect temperature, humidity, smoke concentration and image information of their respective areas, and transmit the collected data to the microprocessor for preliminary processing and storage.

5. A forest fire prevention and monitoring method for forestry engineering according to claim 3, characterized in that: S2 specifically includes the following steps: S21. First, prioritize the data, dividing it into three priority levels: abnormal data (P1 level), routine monitoring data (P2 level), and node status information (P3 level). The priority weights satisfy P1:P2:P3 = 5:3:

2. The transmission priority index is calculated using the formula: Among them, P i ω represents the transmission priority index of the i-th level of data; i To ensure that P1 level data has priority in occupying the transmission channel, the corresponding level weights are assigned. S22. A transmission strategy combining time-slotted ALOHA protocol and dynamic backoff mechanism is adopted. P1 level data directly occupies the current time slot for transmission. If a conflict occurs, the backoff time T is used to resolve the conflict. b =2 n ×Δt, where n is the number of collisions and Δt is the base time interval. If Δt = 10ms, retry. P2 / P3 level data needs to wait for an idle time slot, with initial backoff times of 50ms and 100ms respectively. S23. The microprocessor collects the received signal strength indicator (RSSI) in real time. When RSSI ≤ -100dBm, it automatically increases the transmit power to 20dBm; when RSSI ≥ -70dBm, it decreases it to 10dBm, achieving a dynamic balance between power consumption and transmission distance. The power adjustment formula is as follows: In the formula, P t This indicates the adjusted transmit power; S24. Large data packets are fragmented into 1024-byte segments, and the AES-128-GCM encryption algorithm is used. Each segment is appended with a 16-byte checksum and a 3-byte segment index, and transmitted through the FRMPayload field of the LoRaWAN protocol to ensure data integrity and security.

6. A forest fire prevention and monitoring method for forestry engineering according to claim 3, characterized in that: S4 specifically includes the following steps: S41. Extract feature parameters; In addition to temperature T, humidity H, smoke concentration S, and image confidence I, forest type parameter λ and seasonal coefficient β are added. Among them, the forest type parameter λ: coniferous forest = 1.2, broad-leaved forest = 0.8, mixed forest = 1.0; the seasonal coefficient β: dry season = 1.3, wet season = 0.7, transitional season = 1.0; S42. Adjust the weights of each indicator dynamically based on forest type and season, using the following formula: oh T =0.3×λ×β,ω H =0.2×(2-λ×β); oh S =0.3×λ×β,ω I =0.2×(2-λ×β); In the formula, ω T ω H ω S ω I The weights are respectively for temperature, humidity, smoke concentration, and image information; and satisfy: ω T +ω H +ω S +ω I =1; S43. Standardization processing, the calculation formula is as follows: Is=I; The temperature threshold is set to T0 = 35℃, and the critical temperature is T. c =80℃; humidity threshold H0 = 40%, critical humidity H c =20%; smoke threshold S0 = 0.5 mg / m³ 3 ;T s H s S s I s These are the standardized scores for temperature, humidity, smoke concentration, and image information, respectively; T represents the measured temperature; H represents the measured humidity; S represents the measured smoke concentration; and I represents the confidence level of image recognition for suspected fire, ranging from 0 to 1. S44. Risk Index Calculation: FRI=ω T +oh H ×H s +oh s ×S s +oh I ×I s ; S45. When at least one of the following conditions exists, namely, the temperature exceeds the preset temperature threshold, the humidity is lower than the preset humidity threshold, or the smoke concentration exceeds the preset smoke concentration threshold, and suspected fire features appear in the image, it is determined to be a high fire risk level. When at least one of the temperature, humidity, and smoke concentration exceeds a preset threshold, but no suspected fire features appear in the image, it is judged to be at a medium fire risk level. When the temperature, humidity, and smoke concentration are all within the normal range, and there are no abnormalities in the image, it is judged to be a low fire risk level.

7. A forest fire prevention and monitoring method for forestry engineering according to claim 6, characterized in that: In S45, FRI ≥ 0.7 is considered high risk, 0.3 ≤ FRI < 0.7 is considered medium risk, and FRI < 0.3 is considered low risk.

8. A forest fire prevention and monitoring method for forestry engineering according to claim 3, characterized in that: In S5, if the fire risk level is high, the sound and light alarm will be controlled to issue a sound and light warning at the maximum power set. At the same time, the information push device will push emergency warning information to the mobile terminal, including the fire risk location, risk level and related monitoring data. If the fire risk level is medium, the sound and light alarm will issue a medium-power sound and light warning, and the information push device will push the warning information to the mobile terminal. If the fire risk level is low, the early warning module will not work, and the central processing module will only periodically send the monitoring data to the mobile terminal.

Images