Self-adaptive alarm triggering method and device based on environment perception

Abstract

The invention discloses a self-adaptive alarm triggering method and device based on environmental perception, and belongs to the field of forest fire control, and the method comprises the steps: collecting distributed perception data, and obtaining multi-source positioning data; establishing an environment sensing model, performing environment sensing on the distributed sensing data, and determining a fire-fighting danger basic index; performing fusion processing on the multi-source positioning data by using an adaptive Kalman filtering algorithm to obtain target positioning information; correcting the fire-fighting danger basic index to obtain a fire-fighting danger evaluation index; and when the fire hazard index exceeds the preset fire hazard index threshold value, alarm information is sent through a long-distance redundancy communication mechanism. According to the invention, the technical problem of difficult search and rescue communication when a positioning communication signal is unstable and is lost and trapped due to a complex terrain environment in a forest fire-fighting scene in the prior art is solved; the technical effects of realizing high-reliability environment perception, accurate personnel positioning and stable dual-channel redundant communication in a forest fire-fighting complex environment are achieved.

Description

Technical Field

[0001] The present invention relates to the field of forest fire fighting, and in particular to an adaptive alarm triggering method and device based on environment perception. Background Art

[0002] With the continuous development of forest fire fighting, the reliability requirements for firefighters' positioning and communication are constantly increasing. At present, the Beidou positioning system combined with wireless communication is mainly used in the field of forest fire fighting to locate personnel and call for help. However, in the actual application of forest fire fighting, due to the influence of complex terrain and environmental conditions, the existing technology has the following problems: First, a single positioning technology is difficult to adapt to complex environments. The existing technology mainly relies on the Beidou positioning system, and fails to effectively integrate multi-source positioning data such as air pressure, acceleration, gyroscope, magnetometer and shoe-mounted inertial navigation, resulting in insufficient positioning accuracy, affecting the safety of firefighters. Secondly, the environmental perception ability is insufficient. The existing technology lacks comprehensive analysis of distributed perception data such as temperature, humidity, light intensity and smoke concentration in the forest environment, and cannot timely and accurately assess the degree of fire danger, affecting the timeliness and accuracy of the alarm. Then, when firefighters are lost or trapped, a single communication method is prone to communication interruption due to insufficient signal coverage, making it difficult to ensure the reliability of communication. Summary of the invention

[0003] The present application provides an adaptive alarm triggering method and device based on environmental perception, aiming to solve the technical problems in the prior art of unstable positioning communication signals and difficult search and rescue communications when lost and trapped due to complex terrain environments in forest fire fighting scenarios.

[0004] In view of the above problems, the present application provides an adaptive alarm triggering method and device based on environmental perception.

[0005] The first aspect disclosed in the present application provides an adaptive alarm triggering method based on environmental perception, which includes: collecting distributed perception data of the forest environment, the distributed perception data including temperature, humidity, light intensity and smoke concentration; obtaining multi-source positioning data, the multi-source positioning data including Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data; establishing an environmental perception model, using the environmental perception model to perform environmental perception on the distributed perception data, and determining a basic fire hazard index; using an adaptive Kalman filter algorithm to fuse the multi-source positioning data to obtain target positioning information; correcting the basic fire hazard index according to the target positioning information to obtain a fire hazard assessment index; when the fire hazard assessment index exceeds a preset fire hazard index threshold, sending an alarm message through a long-distance redundant communication mechanism, the long-distance redundant communication mechanism including satellite short message communication and narrowband Internet of Things communication.

[0006] Another aspect disclosed in the present application provides an adaptive alarm triggering device based on environmental perception, which includes: an environmental acquisition module, which is used to collect distributed perception data of the forest environment, and the distributed perception data includes temperature, humidity, light intensity and smoke concentration; a multi-source positioning module, which is used to obtain multi-source positioning data, and the multi-source positioning data includes Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data; a perception modeling module, which is used to establish an environmental perception model, and use the environmental perception model to perform environmental perception on the distributed perception data to determine the basic fire hazard index; a positioning fusion module, which is used to use an adaptive Kalman filter algorithm to fuse the multi-source positioning data to obtain target positioning information; a hazard assessment module, which is used to correct the basic fire hazard index according to the target positioning information to obtain a fire hazard assessment index; an alarm communication module, which is used to send an alarm message through a long-distance redundant communication mechanism when the fire hazard assessment index exceeds a preset fire hazard index threshold, and the long-distance redundant communication mechanism includes satellite short message communication and narrowband Internet of Things communication.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By collecting distributed perception data of the forest environment, including temperature, humidity, light intensity and smoke concentration, the forest environment conditions can be fully understood; at the same time, multi-source positioning data, including Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data, are obtained to lay the foundation for subsequent precise positioning; an environmental perception model is established and used to perceive the distributed perception data, determine the basic fire hazard index, and achieve a preliminary assessment of the degree of environmental hazard; the adaptive Kalman filter algorithm is used to fuse the multi-source positioning data to obtain accurate target positioning information, solving the problem of insufficient accuracy of a single positioning method; on this basis In particular, the basic fire hazard index is corrected according to the target positioning information to obtain a more accurate fire hazard assessment index, thereby improving the reliability of the hazard assessment; when the fire hazard assessment index exceeds the preset fire hazard index threshold, an alarm message is sent through a long-distance redundant communication mechanism including satellite short message communication and narrowband Internet of Things communication, thereby ensuring the reliability of communication. This technical solution solves the technical problems in the prior art of unstable positioning communication signals and difficult search and rescue communications when lost and trapped due to complex terrain environments in forest fire fighting scenarios, thereby achieving the technical effect of highly reliable environmental perception, accurate personnel positioning and stable dual-channel redundant communication in the complex environment of forest fire fighting.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flow chart of an adaptive alarm triggering method based on environment perception is provided for an embodiment of the present application;

[0011] Figure 2 A structural schematic diagram of an adaptive alarm triggering device based on environmental perception is provided for an embodiment of the present application.

[0012] Explanation of the accompanying drawings: environment acquisition module 11, multi-source positioning module 12, perception modeling module 13, positioning fusion module 14, danger assessment module 15, alarm communication module 16. DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows:

[0014] The embodiment of the present application provides an adaptive alarm triggering method and device based on environmental perception. First, by collecting distributed perception data including temperature, humidity, light intensity and smoke concentration, and simultaneously acquiring Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data and other multi-source positioning data, a comprehensive data collection system is constructed. On this basis, an environmental perception model is established to process the distributed perception data to obtain a basic fire hazard index; an adaptive Kalman filter algorithm is used to fuse the multi-source positioning data to obtain accurate target positioning information; the target positioning information is further used to correct the basic fire hazard index to obtain a more reliable fire hazard assessment index. When the assessment index exceeds a preset threshold, an alarm message is sent through a long-distance redundant communication mechanism that combines satellite short message communication and narrowband Internet of Things communication.

[0015] Through the above technical solution, intelligent environmental perception, precise personnel positioning and reliable communication guarantee are realized in the complex environment of forest fire fighting, which effectively solves the technical problems in the existing technology of unstable positioning communication signals caused by complex terrain environment and difficult search and rescue communications when lost and trapped.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides an adaptive alarm triggering method based on environment perception, the method comprising:

[0018] S1: Collect distributed perception data of the forest environment, where the distributed perception data includes temperature, humidity, light intensity, and smoke concentration.

[0019] Specifically, an environment perception module is integrated in the smart terminal carried by forest firefighters. The environment perception module includes a variety of sensor units for real-time monitoring of the forest environment. The environment perception module integrates a temperature sensor unit, a humidity sensor unit, a light sensor unit, and a smoke sensor unit. Among them, the temperature sensor unit corresponds to collecting the temperature of the forest environment, the humidity sensor unit corresponds to collecting the humidity of the forest environment, the light sensor unit corresponds to collecting the light intensity of the forest environment, and the smoke sensor unit corresponds to collecting the smoke concentration of the forest environment. The temperature sensor unit collects the temperature of the forest environment in real time to promptly reflect the temperature anomaly caused by the forest fire; the humidity sensor unit collects the humidity of the forest environment in real time to reflect the possibility of forest fire; the light sensor unit collects the light intensity of the forest environment in real time to assist in judging whether a fire has occurred; the smoke sensor unit collects the smoke concentration of the forest environment in real time to directly reflect the situation of the fire.

[0020] The data collected by each sensor unit is pre-processed by the signal processing circuit of the environmental perception module to form distributed perception data. By collecting the above distributed perception data, the real-time status of the forest environment can be fully understood, providing a data basis for subsequent environmental perception and risk assessment.

[0021] S2: Acquire multi-source positioning data, where the multi-source positioning data includes Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data, and shoe-mounted inertial navigation data.

[0022] Specifically, a positioning module is integrated in the smart terminal carried by forest firefighters. The positioning module integrates a variety of positioning sensor units to achieve collaborative positioning of multi-source data. Specifically, the positioning module includes a Beidou positioning unit, an air pressure sensor unit, an acceleration sensor unit, a gyroscope unit, a magnetometer unit, and an inertial navigation unit integrated in the firefighter's special shoes. Among them, the Beidou positioning unit obtains absolute position coordinates by receiving Beidou satellite signals; the air pressure sensor unit obtains altitude information by detecting changes in atmospheric pressure; the acceleration sensor unit is used to detect motion acceleration and obtain mobile state information; the gyroscope unit is used to detect angular velocity and obtain steering information; the magnetometer unit is used to detect the geomagnetic field and obtain azimuth information; the shoe-mounted inertial navigation unit obtains relative displacement information by detecting gait characteristics.

[0023] The data acquired by each positioning sensor unit is pre-processed by the signal processing circuit of the positioning module to form multi-source positioning data. By acquiring the above multi-source positioning data, multi-dimensional positioning information can be provided for subsequent data fusion processing, thereby improving positioning accuracy and reliability.

[0024] S3: Establish an environmental perception model, use the environmental perception model to perform environmental perception on the distributed perception data, and determine a basic fire risk index.

[0025] Specifically, the intelligent analysis and processing of distributed perception data is achieved by establishing an environmental perception model. First, a standard parameter library for forest environment is established, which stores benchmark parameters such as standard temperature range, standard humidity range, standard light intensity range and standard smoke concentration range. Then, the historical environmental data within a preset time period is obtained, and the historical environmental data is processed by feature extraction to obtain environmental characteristic parameters. The environmental characteristic parameters are compared with the benchmark parameters in the standard parameter library to establish an environmental parameter deviation mapping relationship. Based on the above environmental parameter deviation mapping relationship, the data is normalized and weighted according to the preset weights to establish a corresponding relationship between the comprehensive deviation value of the sample environment and the basic fire hazard index of the sample, thereby training and forming an environmental perception model. The model can convert the distributed perception data collected in real time into a basic fire hazard index that characterizes the current degree of environmental hazard.

[0026] By establishing and applying environmental perception models, intelligent assessment of forest environmental conditions can be achieved, providing a basic basis for subsequent risk assessments.

[0027] S4: Using an adaptive Kalman filter algorithm to fuse the multi-source positioning data to obtain target positioning information.

[0028] Specifically, in order to improve the positioning accuracy, an adaptive Kalman filter algorithm is used to fuse the multi-source positioning data. First, the state equation and observation equation are established. Among them, the state equation is used to describe the time evolution relationship between the position and velocity of the firefighters, and the observation equation is used to describe the measurement values ​​of each positioning sensor. Based on the above equation, the initial state prediction value is calculated. Then, the measurement residual sequence is constructed according to the actual measurement values ​​and the initial state prediction values ​​of the multi-source positioning data. By performing sliding window processing on the measurement residual sequence, the statistical mean and variance of the window measurement residual sequence are calculated, and the measurement error covariance matrix is ​​constructed, which characterizes the credibility of the measurement data of each sensor. Based on the measurement error covariance matrix, the dynamic weight coefficient is adaptively calculated, and the Kalman gain is adaptively adjusted. Afterwards, the initial state prediction value is corrected using the adjusted Kalman gain to obtain accurate target positioning information.

[0029] By using the adaptive Kalman filter algorithm to fuse multi-source data, the positioning accuracy can be effectively improved, the limitations of a single positioning method can be overcome, and reliable location information can be provided for firefighters.

[0030] S5: Correcting the fire risk basic index according to the target positioning information to obtain a fire risk assessment index.

[0031] Specifically, the target positioning information is combined with geographic information data to correct the basic fire hazard index. First, the current area of ​​the firefighters is determined by the target positioning information. Based on the area information, the corresponding geographic information data, including terrain information, vegetation information and water source distribution information, are retrieved from the geographic information database. The terrain information reflects the undulation and difficulty of the terrain, the vegetation information reflects the distribution of combustibles, and the water source distribution information reflects the availability of rescue resources. Then, the firefighting difficulty coefficient is calculated based on the above geographic information data. The firefighting difficulty coefficient refers to a comprehensive evaluation index that indicates the difficulty of firefighting and rescue operations when a forest fire occurs. The firefighting difficulty coefficient is calculated based on four factors: terrain complexity, vegetation density, water source accessibility, and communication interconnection and visualization. The higher the terrain complexity, the higher the firefighting difficulty coefficient score; the greater the vegetation density, the higher the firefighting difficulty coefficient score; the worse the water source accessibility, the higher the firefighting difficulty coefficient score; the worse the communication interconnection and visualization, the higher the firefighting difficulty coefficient score. The firefighting difficulty coefficient is obtained by weighted calculation of these four factors. The higher this coefficient is, the more difficult it is to carry out firefighting and rescue operations in the area, and more rescue resources and more cautious rescue strategies are needed. After that, the firefighting difficulty coefficient and the basic firefighting hazard index are weighted to obtain a more accurate firefighting hazard assessment index. This assessment index not only reflects the degree of danger of the environment itself, but also takes into account the impact of the geographical environment on firefighting and rescue, thereby achieving a comprehensive assessment of the degree of danger.

[0032] By introducing geographic information data for correction, the accuracy and practicality of hazard assessment can be improved, providing a more reliable basis for the safety protection of firefighters.

[0033] S6: When the fire risk assessment index exceeds a preset fire risk index threshold, an alarm message is sent through a long-distance redundant communication mechanism, and the long-distance redundant communication mechanism includes satellite short message communication and narrowband Internet of Things communication.

[0034] Specifically, long-distance redundant communication is achieved by establishing a dual-channel communication link. The communication mechanism includes two independent communication links: satellite short message communication is used for long-distance data transmission, and narrowband Internet of Things communication is used for medium-distance data transmission. When the fire risk assessment index exceeds the preset threshold and triggers an alarm, the alarm information is firstly packetized according to the preset format to generate redundant data packets. Data packetization can improve the reliability of transmission, and even if some data packets fail to be transmitted, the basic integrity of the information can be guaranteed. Then, the redundant data packets are sent in parallel through two independent communication links. Among them, the satellite short message communication link has the advantages of wide coverage and is not restricted by ground facilities, which is suitable for long-distance communication; the narrowband Internet of Things communication link has the characteristics of fast data transmission rate and low power consumption, which is suitable for medium-distance communication. The narrowband Internet of Things communication link is based on NB-IoT technology and is realized through the 4G / 5G cellular network base station of the mobile operator. It can be deployed based on the existing mobile communication network infrastructure. Since NB-IoT has a low operating frequency band and strong signal penetration ability, it can achieve effective coverage even in complex terrain with poor visibility conditions. In areas with weak signal coverage, temporary base stations can also be deployed to supplement it. Afterwards, the redundant data packets received are checked and reassembled at the receiving end, and the integrity and accuracy of the alarm information are ensured through cross-verification of dual-channel data.

[0035] By adopting a dual-channel redundant communication mechanism, the communication reliability in forest fire fighting scenarios can be significantly improved, communication problems in complex terrain environments can be effectively solved, and strong support can be provided for the safety of firefighters.

[0036] Furthermore, the embodiment of the present application also includes:

[0037] A standard parameter library for forest environment is established, wherein the standard parameter library includes a standard temperature range, a standard humidity range, a standard light intensity range, and a standard smoke concentration range; historical environmental data within a preset time period is acquired; features are extracted from the historical environmental data to obtain environmental characteristic parameters; the environmental characteristic parameters are compared with the standard parameter library to establish an environmental parameter deviation mapping relationship; and the environmental perception model is established based on the environmental parameter deviation mapping relationship.

[0038] In a feasible implementation, in order to establish an environmental perception model, first, a standard parameter library for forest environment is established. The standard parameter library stores various reference values ​​reflecting the normal forest environment state, including: standard temperature range (such as 15°C-30°C), standard humidity range (such as 40%-70%), standard light intensity range (such as 1000-10000 lux) and standard smoke concentration range (such as 0-0.1mg / m 3). These standard range values ​​are obtained based on a large amount of statistical analysis of forest environmental data and can be used as a benchmark for judging environmental anomalies. Preferably, when constructing a standard parameter library, since the differences in forest geographical environments will significantly affect the distribution characteristics of environmental parameters, it is necessary to consider the impact of factors such as terrain undulation, vegetation coverage, and tree shielding on environmental parameters. Among them, terrain undulation is used to characterize the complexity of the terrain and its impact on the distribution of temperature and humidity, vegetation coverage is used to characterize the coverage of vegetation and its impact on light and air circulation, and tree density is used to characterize the distribution of trees per unit area and its comprehensive shielding effect on environmental parameters. By correcting the standard range values ​​through these geographical environmental parameters, the law of parameter changes under different geographical environments can be more accurately reflected, and the accuracy of judging environmental anomalies can be improved. Then, historical environmental data within a preset time period is obtained. The preset time period here can be nearly one year or nearly half a year, during which environmental data is collected and stored at a fixed sampling frequency (such as once every 10 minutes). These historical data contain the law of change of the forest environment and can reflect the normal fluctuation range of environmental parameters. Next, feature extraction is performed on the historical environmental data. By calculating statistical characteristics (such as mean, standard deviation, extreme value, etc.), time series characteristics (such as change trend, periodicity, etc.) and correlation characteristics (such as the correlation between parameters), environmental characteristic parameters that can characterize environmental characteristics are obtained.

[0039] Afterwards, the extracted environmental characteristic parameters are compared and analyzed with the benchmark values ​​in the standard parameter library. By calculating the degree of deviation between the actual parameters and the standard parameters, an environmental parameter deviation mapping relationship is established. This mapping relationship can be used to quantify the degree of environmental abnormality and provide a basis for subsequent risk assessment. Next, based on the established environmental parameter deviation mapping relationship, an environmental perception model is constructed. This model can map the real-time collected environmental data into corresponding risk level indicators to achieve intelligent assessment of forest environmental conditions. Through the established environmental perception model, timely identification and assessment of abnormal conditions in the forest environment can be effectively achieved.

[0040] Furthermore, the embodiment of the present application also includes:

[0041] The environmental parameter deviation mapping relationship is subjected to data normalization processing to obtain a normalized environmental parameter deviation; the normalized environmental parameter deviation is weightedly calculated according to a preset weight to obtain a sample environmental comprehensive deviation value; a correspondence between the sample environmental comprehensive deviation value and the sample fire hazard basic index is established; and an environmental perception model is trained based on the correspondence, so that the environmental perception model can convert the distributed perception data collected in real time into a fire hazard basic index.

[0042] In a preferred embodiment, first, the environmental parameter deviation mapping relationship is subjected to data normalization. Since the dimensions and numerical ranges of parameters such as temperature, humidity, light intensity and smoke concentration are different, it is necessary to uniformly map the deviation values ​​of each parameter to the interval [0, 1] through normalization processing, so as to obtain comparable normalized environmental parameter deviations. Then, the normalized environmental parameter deviations are weighted and calculated according to preset weights. Among them, the preset weights reflect the influence of different environmental parameters on the degree of fire hazard. For example, the weight of smoke concentration is higher than that of light intensity. The comprehensive deviation value of the sample environment is obtained by weighted summation calculation, which comprehensively reflects the overall degree of environmental abnormality.

[0043] Next, establish the correspondence between the sample environment comprehensive deviation value and the sample fire hazard basic index. By analyzing the fire cases in the historical data, determine the actual danger level corresponding to different environmental comprehensive deviation values, and establish the correspondence between the two. Subsequently, train the environmental perception model based on the above correspondence. Use machine learning methods (such as support vector machines, neural networks, etc.) to train the model so that it can accurately convert the distributed perception data collected in real time into a fire hazard basic index that characterizes the current environmental danger level. During the training process, the model parameters are adjusted to minimize the error between the predicted results and the actual danger level. Through the above processing steps, an accurate environmental perception model is established to achieve intelligent assessment of the danger level of the forest environment.

[0044] Furthermore, the embodiment of the present application also includes:

[0045] Establish a state equation and an observation equation, wherein the state equation describes the time evolution relationship between the target position and velocity, and the observation equation describes the measurement value of the multi-source positioning data; calculate the initial state prediction value according to the state equation and the observation equation; construct a measurement residual sequence based on the measurement value of the multi-source positioning data and the initial state prediction value; use the measurement residual sequence to online estimate the measurement error characteristics, and adaptively adjust the Kalman gain according to the measurement error characteristics; use the Kalman gain to correct the initial state prediction value to obtain the target positioning information.

[0046] In a preferred embodiment, when the adaptive Kalman filter algorithm is used to fuse the multi-source positioning data, first, a state equation and an observation equation are established. The state equation uses a uniform motion model to describe the time evolution relationship between the target position and velocity, and the state vector contains the three-dimensional spatial position coordinates and their corresponding velocity components; the observation equation describes the relationship between the measured values ​​of multi-source positioning data such as Beidou positioning, air pressure, acceleration, gyroscope, magnetometer and shoe-mounted inertial navigation and the state vector. Then, the initial state prediction value is calculated according to the established state equation and observation equation. The state estimate value at the previous moment is used to predict the state value at the current moment through the state equation; at the same time, the predicted measurement value of each sensor at the current moment is calculated based on the observation equation. Then, the actual measurement value of the multi-source positioning data is compared with the predicted measurement value to construct a measurement residual sequence. The measurement residual reflects the deviation between the predicted value and the actual measurement value, which can be used to evaluate the reliability of each sensor data. After that, the measurement residual sequence is analyzed online using a sliding time window to estimate the statistical characteristics of the measurement error. According to the change of the error characteristics, the gain matrix of the Kalman filter is dynamically adjusted so that the filter can adaptively adjust the weights of different sensor data. Then, the initial state prediction value is corrected using the adaptively adjusted Kalman gain. By weighted fusion of the prediction value and the actual measurement value, more accurate target positioning information is obtained.

[0047] Through the adaptive Kalman filter algorithm, multi-source positioning data is effectively integrated to improve positioning accuracy and reliability. At the same time, the fusion weight is automatically adjusted according to the quality of real-time measurement data, which has strong environmental adaptability.

[0048] Furthermore, the embodiment of the present application also includes:

[0049] Extract a preset time window, perform sliding processing on the measurement residual sequence, obtain the window measurement residual sequence, and calculate the statistical mean and variance of the window measurement residual sequence; use the statistical mean and variance of the window measurement residual sequence to construct a measurement error covariance matrix, wherein the measurement error covariance matrix characterizes the credibility of measurement data of each sensor; adaptively calculate a dynamic weight coefficient based on the measurement error covariance matrix, and adaptively adjust the Kalman gain according to the dynamic weight coefficient.

[0050] In a preferred embodiment, first, a preset time window is extracted and a sliding process is performed. The length of the time window can be set to 10-30 sampling cycles, and the measurement residual sequence is slid according to a fixed step size. For each sliding window position, the measurement residual sequence in the window is extracted, and the statistical characteristics of the sequence are calculated. Specifically, the arithmetic mean (statistical mean) and the degree of dispersion (statistical variance) of the measurement residuals of each sensor in the window are calculated. Then, a measurement error covariance matrix is ​​constructed based on the calculated statistical mean and variance. The matrix is ​​a symmetric matrix, and the main diagonal elements represent the variance of the measurement data of each sensor, reflecting the degree of dispersion of the data; the non-diagonal elements represent the covariance between different sensors, reflecting the correlation between the data. The numerical value in the matrix directly represents the credibility of the measurement data of each sensor, and the smaller the value, the higher the credibility. Afterwards, the dynamic weight coefficient is calculated according to the measurement error covariance matrix. The inverse matrix of the covariance matrix is ​​used as the basis for weight calculation, so that the sensor with smaller measurement error obtains a larger weight. The calculated dynamic weight coefficient is substituted into the gain calculation formula of the Kalman filter to realize the adaptive adjustment of the Kalman gain.

[0051] Through the above processing, the reliability of sensor data can be dynamically evaluated, and the data fusion weight can be adaptively adjusted accordingly. This method can effectively improve the accuracy and robustness of multi-source positioning data fusion and adapt to the dynamic changes of sensor performance in different environments.

[0052] Furthermore, the embodiment of the present application also includes:

[0053] Determine the area where the target is located according to the target positioning information; obtain geographic information data of the area where the target is located, the geographic information data including terrain information, vegetation information and water source distribution information; calculate a firefighting difficulty coefficient according to the geographic information data, the firefighting difficulty coefficient characterizes the difficulty of firefighting and rescue in the area where the target is located; use the firefighting difficulty coefficient to correct the fire hazard basic index to obtain the fire hazard assessment index.

[0054] In a feasible implementation, first, the target area is determined based on the target positioning information. By matching the positioning coordinates with the electronic map, the specific area where the firefighters are currently located is determined. The size of the area can be set according to actual needs, such as a 500-meter radius centered on the current location. Then, the geographic information data of the area is retrieved from the geographic information database. Specifically including: terrain information reflecting the undulating terrain (such as altitude, slope, slope direction, etc.), vegetation information reflecting the distribution of combustibles (such as vegetation type, coverage, density, etc.), and water source distribution information reflecting the availability of rescue resources (such as the location and capacity of natural water sources and artificial water sources, etc.).

[0055] Next, the firefighting difficulty coefficient is calculated based on the acquired geographic information data. This coefficient is determined by comprehensively evaluating multiple factors: terrain factors (such as the greater the slope, the higher the difficulty), vegetation factors (such as the greater the vegetation density, the higher the difficulty), water source factors (such as the farther the distance from the water source, the higher the difficulty), etc. The weighted summation method is used to combine the various factors to obtain the final firefighting difficulty coefficient. The larger the coefficient, the greater the difficulty of firefighting and rescue. After that, the firefighting difficulty coefficient and the firefighting hazard basic index are weighted and fused to obtain the firefighting hazard assessment index. The specific calculation method is: firefighting hazard assessment index = firefighting hazard basic index × (1 + firefighting difficulty coefficient). In this way, the influencing factors of the geographical environment on firefighting and rescue are taken into consideration, making the hazard assessment results more comprehensive and accurate, thereby realizing the dynamic assessment and correction of the degree of environmental hazard, and providing a more reliable decision-making basis for the safety protection of firefighters.

[0056] Furthermore, the embodiment of the present application also includes:

[0057] A dual-channel communication link is established, including a first communication link and a second communication link, wherein the first communication link adopts satellite short message communication for long-distance data transmission, and the second communication link adopts narrowband Internet of Things communication for medium-distance data transmission; the alarm information is packetized according to a preset format to generate redundant data packets; the redundant data packets are sent in parallel through the first communication link and the second communication link; and data verification and reorganization are performed on the received redundant data packets to ensure the integrity of the alarm information.

[0058] In a preferred embodiment, first, a dual-channel communication link is established. The communication link includes two independent communication channels: the first communication link adopts satellite short message communication technology, which has the characteristics of wide coverage and no geographical restrictions, and is suitable for long-distance data transmission, and the communication distance can reach hundreds of kilometers; the second communication link adopts narrowband Internet of Things communication technology, which has the characteristics of low power consumption and strong penetration, and is suitable for medium-distance data transmission, and the communication distance can reach tens of kilometers. Then, the alarm information to be sent is processed by data packetization according to a preset format. The preset format includes a header, a data segment and a check segment, wherein the header includes information such as a packet sequence number and a timestamp, the data segment includes the alarm information content, and the check segment is used for data integrity verification. Data packets with redundant characteristics can be generated by data packetization, and even if part of the data packets fail to be transmitted, it will not affect the restoration of the overall information. Then, redundant data packets are sent in parallel through dual channels. The same data packet is sent through the first communication link and the second communication link at the same time to achieve redundant backup of data transmission. The two communication links use different transmission protocols and frequency bands, which can effectively reduce the risk of communication interruption. Afterwards, the received redundant data packets are processed at the receiving end. First, data verification is performed to verify the integrity of the data packet through methods such as checksum and CRC. Then, the verified data packets are reorganized according to the packet sequence number, and the data packets from different communication links are integrated into complete alarm information. If a data packet of a communication link is lost or erroneous, it can be supplemented with a data packet from another link.

[0059] The dual-channel redundant communication mechanism can significantly improve the reliability of alarm information transmission and effectively solve the communication problem in forest environments. Even in complex terrain environments, it can ensure timely and reliable transmission of alarm information.

[0060] In summary, the adaptive alarm triggering method based on environment perception provided by the embodiment of the present application has the following technical effects:

[0061] Collect distributed perception data of the forest environment, including temperature, humidity, light intensity and smoke concentration, to perceive the state of the forest environment. Obtain multi-source positioning data, including Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data, for subsequent precise positioning. Establish an environmental perception model, use the environmental perception model to perceive the distributed perception data, determine the basic index of fire danger, and obtain preliminary results of the degree of danger assessment. Use the adaptive Kalman filter algorithm to fuse the multi-source positioning data to obtain target positioning information, improve positioning accuracy through multi-source data fusion, and overcome the limitations of a single positioning method. Correct the basic index of fire danger according to the target positioning information to obtain the fire danger assessment index, and optimize the degree of danger assessment in combination with the location information to improve the accuracy of the assessment results. When the fire danger assessment index exceeds the preset fire danger index threshold, send an alarm message through a long-distance redundant communication mechanism. The long-distance redundant communication mechanism includes satellite short message communication and narrowband Internet of Things communication. In dangerous situations, dual channels are used to ensure the reliable transmission of alarm information.

[0062] Embodiment 2 is based on the same inventive concept as the adaptive alarm triggering method based on environment perception in the above embodiment. Figure 2 As shown, an embodiment of the present application provides an adaptive alarm triggering device based on environment perception, the device comprising:

[0063] The environment collection module 11 is used to collect distributed perception data of the forest environment, and the distributed perception data includes temperature, humidity, light intensity and smoke concentration.

[0064] The multi-source positioning module 12 is used to obtain multi-source positioning data, wherein the multi-source positioning data includes Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data.

[0065] The perception modeling module 13 is used to establish an environmental perception model, use the environmental perception model to perform environmental perception on the distributed perception data, and determine the basic fire risk index.

[0066] The positioning fusion module 14 is used to fuse the multi-source positioning data using an adaptive Kalman filter algorithm to obtain target positioning information.

[0067] The risk assessment module 15 is used to correct the fire risk basic index according to the target positioning information to obtain a fire risk assessment index.

[0068] The alarm communication module 16 is used to send an alarm message through a long-distance redundant communication mechanism when the fire risk assessment index exceeds a preset fire risk index threshold. The long-distance redundant communication mechanism includes satellite short message communication and narrowband Internet of Things communication.

[0069] Furthermore, the perception modeling module 13 includes the following execution steps:

[0070] A standard parameter library for forest environment is established, wherein the standard parameter library includes a standard temperature range, a standard humidity range, a standard light intensity range, and a standard smoke concentration range; historical environmental data within a preset time period is acquired; features are extracted from the historical environmental data to obtain environmental characteristic parameters; the environmental characteristic parameters are compared with the standard parameter library to establish an environmental parameter deviation mapping relationship; and the environmental perception model is established based on the environmental parameter deviation mapping relationship.

[0071] Furthermore, the perception modeling module 13 further includes the following execution steps:

[0072] The environmental parameter deviation mapping relationship is subjected to data normalization processing to obtain a normalized environmental parameter deviation; the normalized environmental parameter deviation is weightedly calculated according to a preset weight to obtain a sample environmental comprehensive deviation value; a correspondence between the sample environmental comprehensive deviation value and the sample fire hazard basic index is established; and an environmental perception model is trained based on the correspondence, so that the environmental perception model can convert the distributed perception data collected in real time into a fire hazard basic index.

[0073] Furthermore, the positioning fusion module 14 includes the following execution steps:

[0074] Establish a state equation and an observation equation, wherein the state equation describes the time evolution relationship between the target position and velocity, and the observation equation describes the measurement value of the multi-source positioning data; calculate the initial state prediction value according to the state equation and the observation equation; construct a measurement residual sequence based on the measurement value of the multi-source positioning data and the initial state prediction value; use the measurement residual sequence to online estimate the measurement error characteristics, and adaptively adjust the Kalman gain according to the measurement error characteristics; use the Kalman gain to correct the initial state prediction value to obtain the target positioning information.

[0075] Furthermore, the positioning fusion module 14 further includes the following execution steps:

[0076] Extract a preset time window, perform sliding processing on the measurement residual sequence, obtain the window measurement residual sequence, and calculate the statistical mean and variance of the window measurement residual sequence; use the statistical mean and variance of the window measurement residual sequence to construct a measurement error covariance matrix, wherein the measurement error covariance matrix characterizes the credibility of measurement data of each sensor; adaptively calculate a dynamic weight coefficient based on the measurement error covariance matrix, and adaptively adjust the Kalman gain according to the dynamic weight coefficient.

[0077] Furthermore, the risk assessment module 15 includes the following execution steps:

[0078] Determine the area where the target is located according to the target positioning information; obtain geographic information data of the area where the target is located, the geographic information data including terrain information, vegetation information and water source distribution information; calculate a firefighting difficulty coefficient according to the geographic information data, the firefighting difficulty coefficient characterizes the difficulty of firefighting and rescue in the area where the target is located; use the firefighting difficulty coefficient to correct the fire hazard basic index to obtain the fire hazard assessment index.

[0079] Furthermore, the alarm communication module 16 includes the following execution steps:

[0080] A dual-channel communication link is established, including a first communication link and a second communication link, wherein the first communication link adopts satellite short message communication for long-distance data transmission, and the second communication link adopts narrowband Internet of Things communication for medium-distance data transmission; the alarm information is packetized according to a preset format to generate redundant data packets; the redundant data packets are sent in parallel through the first communication link and the second communication link; and data verification and reorganization are performed on the received redundant data packets to ensure the integrity of the alarm information.

[0081] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0082] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to the selection of multiple elements individually or in whole. Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. An adaptive alarm triggering method based on environmental perception, characterized in that: include: Collecting distributed sensing data of the forest environment, wherein the distributed sensing data includes temperature, humidity, light intensity and smoke concentration; Acquire multi-source positioning data, wherein the multi-source positioning data includes Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data; Establishing an environmental perception model, using the environmental perception model to perform environmental perception on the distributed perception data, and determining a basic fire risk index; Using an adaptive Kalman filter algorithm to fuse the multi-source positioning data to obtain target positioning information; Correcting the fire risk basic index according to the target positioning information to obtain a fire risk assessment index; When the fire risk assessment index exceeds a preset fire risk index threshold, an alarm message is sent through a long-distance redundant communication mechanism, and the long-distance redundant communication mechanism includes satellite short message communication and narrowband Internet of Things communication.

2. The method for adaptive alarm triggering based on environmental perception according to claim 1, characterized in that: Build an environmental perception model, including: Establishing a standard parameter library for forest environment, the standard parameter library includes a standard temperature range, a standard humidity range, a standard light intensity range and a standard smoke concentration range; Obtain historical environmental data within a preset time period; Extracting features from the historical environmental data to obtain environmental feature parameters; Comparing the environmental characteristic parameters with the standard parameter library to establish an environmental parameter deviation mapping relationship; Based on the environmental parameter deviation mapping relationship, the environmental perception model is established.

3. The method for adaptive alarm triggering based on environmental perception according to claim 2 is characterized in that: Based on the environmental parameter deviation mapping relationship, the environmental perception model is established, including: Performing data normalization processing on the environmental parameter deviation mapping relationship to obtain a normalized environmental parameter deviation; The normalized environmental parameter deviation is weighted and calculated according to the preset weight to obtain the sample environment comprehensive deviation value; Establish the corresponding relationship between the comprehensive deviation value of sample environment and the basic index of sample fire hazard; The environmental perception model is trained based on the corresponding relationship, so that the environmental perception model can convert the distributed perception data collected in real time into a basic fire risk index.

4. The method for adaptive alarm triggering based on environmental perception according to claim 1, characterized in that: The multi-source positioning data is fused using an adaptive Kalman filter algorithm to obtain target positioning information, including: Establishing a state equation and an observation equation, wherein the state equation describes the time evolution relationship between the target position and velocity, and the observation equation describes the measurement value of the multi-source positioning data; Calculate the initial state prediction value according to the state equation and the observation equation; Constructing a measurement residual sequence based on the measurement values ​​of the multi-source positioning data and the initial state prediction value; Using the measurement residual sequence to estimate the measurement error characteristics online, and adaptively adjusting the Kalman gain according to the measurement error characteristics; The initial state prediction value is corrected using the Kalman gain to obtain the target positioning information.

5. The method for adaptive alarm triggering based on environmental perception according to claim 4 is characterized in that: The measurement error characteristics are estimated online using the measurement residual sequence, and the Kalman gain is adaptively adjusted according to the measurement error characteristics, including: Extracting a preset time window, performing sliding processing on the measurement residual sequence, obtaining a window measurement residual sequence, and calculating a statistical mean and variance of the window measurement residual sequence; Using the statistical mean and variance of the window measurement residual sequence, a measurement error covariance matrix is ​​constructed, wherein the measurement error covariance matrix represents the credibility of the measurement data of each sensor; A dynamic weight coefficient is adaptively calculated according to the measurement error covariance matrix, and the Kalman gain is adaptively adjusted according to the dynamic weight coefficient.

6. The method for adaptive alarm triggering based on environmental perception according to claim 1, characterized in that: Correcting the fire risk basic index according to the target positioning information to obtain a fire risk assessment index includes: Determine the area where the target is located according to the target positioning information; Acquire geographic information data of the area where the target is located, wherein the geographic information data includes terrain information, vegetation information and water source distribution information; Calculating a firefighting difficulty coefficient according to the geographic information data, wherein the firefighting difficulty coefficient represents the difficulty of firefighting and rescue in the target area; The firefighting difficulty coefficient is used to correct the firefighting hazard basic index to obtain the firefighting hazard assessment index.

7. The method for adaptive alarm triggering based on environmental perception according to claim 1, characterized in that: Send alarm information through long-distance redundant communication mechanism, including: Establishing a dual-channel communication link, including a first communication link and a second communication link, wherein the first communication link uses satellite short message communication for long-distance data transmission, and the second communication link uses narrowband Internet of Things communication for medium-distance data transmission; The alarm information is divided into data packets according to a preset format to generate redundant data packets; sending the redundant data packets in parallel via the first communication link and the second communication link; The received redundant data packets are checked and reassembled to ensure the integrity of the alarm information.

8. An adaptive alarm triggering device based on environmental perception, characterized in that: include: An environment acquisition module, the environment acquisition module is used to collect distributed perception data of the forest environment, the distributed perception data including temperature, humidity, light intensity and smoke concentration; A multi-source positioning module, wherein the multi-source positioning module is used to obtain multi-source positioning data, wherein the multi-source positioning data includes Beidou positioning data, air pressure data, acceleration data, gyroscope data, magnetometer data and shoe-mounted inertial navigation data; A perception modeling module, wherein the perception modeling module is used to establish an environmental perception model, use the environmental perception model to perform environmental perception on the distributed perception data, and determine a basic fire risk index; A positioning fusion module, wherein the positioning fusion module is used to fuse the multi-source positioning data using an adaptive Kalman filter algorithm to obtain target positioning information; A risk assessment module, the risk assessment module is used to correct the fire risk basic index according to the target positioning information to obtain a fire risk assessment index; An alarm communication module, wherein the alarm communication module is used to send an alarm message through a long-distance redundant communication mechanism when the fire risk assessment index exceeds a preset fire risk index threshold, and the long-distance redundant communication mechanism includes satellite short message communication and narrowband Internet of Things communication.

Images