A fire monitoring method and system

Abstract

The present application belongs to the technical field of fire precise monitoring and early warning, and discloses a fire monitoring method, which comprises the following steps: obtaining fire monitoring data, and performing prediction and estimation processing according to the fire monitoring data to obtain fire estimation data; comparing the fire estimation data with an initial empirical fire threshold value; in the case that the comparison result is that the fire estimation data is greater than or equal to the initial empirical fire threshold value, calculating the fire estimation data by using an area integral algorithm to obtain an area integral calculation value; comparing the area integral calculation value with the initial empirical fire threshold value; and in the case that the comparison result is that the area integral calculation value is greater than the initial empirical fire threshold value, performing fire alarm processing. The present application can accurately judge various fires, reduce fire risks, and realize precise fire monitoring and early warning.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire accurate monitoring and early warning, and particularly relates to a fire monitoring method and system. BACKGROUND

[0002] Fire monitoring and early warning is a complex problem in actual fire monitoring scenarios. Conventional fire prevention technical measures (such as smoke sensing, temperature sensing, flame detection, etc.) focus more on medium-term and late-stage fire prevention, and are difficult to effectively identify the early-stage fire risk of power equipment. When a fire actually occurs, it is difficult to monitor or there is a great delay.

[0003] The early-stage fire monitoring device identifies early-stage fire based on the combination of the cloud chamber primary detection and the optical scattering chamber secondary detection. The pyrolysis particle concentration data detected by the cloud chamber and the pyrolysis particle concentration data detected by the scattering chamber are fitted by a mixed numerical mathematical algorithm to obtain accurate on-site early-stage fire occurrence data.

[0004] However, the early-stage fire monitoring device still relies on specific threshold values for judgment. The existing threshold values are set by humans and are based on experience. If the threshold value is too small, false positives are likely to occur. If the threshold value is too large, detection delay is likely to occur, and accurate monitoring and early warning cannot be achieved.

[0005] A reasonable monitoring and early warning threshold setting method can timely obtain on-site fire risk information and reduce false positives caused by human factors, so that the system warning is more targeted. Therefore, how to effectively process and configure the data of the early-stage fire monitoring device is crucial for fire monitoring and early warning. SUMMARY

[0006] The present application provides a fire monitoring method and system to solve the problem that the prior art cannot accurately monitor and early warn fire.

[0007] The following presents a simplified summary of some aspects of the disclosed embodiments in order to provide a basic understanding of such embodiments. This summary is not an extensive overview of the embodiments described in this disclosure and is intended neither to identify key or critical elements nor to delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

[0008] According to a first aspect of the embodiments of the present application, a fire monitoring method is provided.

[0009] In one embodiment, the fire monitoring method comprises:

[0010] acquiring fire monitoring data, and performing prediction and estimation processing according to the fire monitoring data to obtain fire estimation data;

[0011] The fire estimation data is compared with the initial empirical fire threshold value, and in the case that the comparison result is that the fire estimation data is greater than or equal to the initial empirical fire threshold value, the area integral algorithm is used to calculate the fire estimation data to obtain an area integral calculation value;

[0012] The area integral calculation value is compared with the initial empirical fire threshold value, and in the case that the comparison result is that the area integral calculation value is greater than the initial empirical fire threshold value, a fire alarm processing is performed.

[0013] In one embodiment, the fire monitoring method further comprises:

[0014] The obtained fire monitoring data is judged to determine whether the fire monitoring data is abnormal, and in the case that the judgment result is that the fire monitoring data is normal, an estimation processing is performed according to the fire monitoring data; and in the case that the judgment result is that the fire monitoring data is abnormal, the fire monitoring data is reacquired.

[0015] In one embodiment, judging the obtained fire monitoring data to determine whether the fire monitoring data is abnormal comprises: judging the obtained fire monitoring data to determine whether the fire monitoring data is abnormal by using the 3-sigma principle.

[0016] In one embodiment, performing an estimation processing according to the fire monitoring data to obtain fire estimation data comprises: calculating the fire monitoring data by using a linear stochastic differential equation and a data observation equation to obtain a fire prediction value; processing the fire prediction value by using a Kalman filtering algorithm to obtain a fire prediction accurate value; and performing a Kalman gain estimation calculation according to the fire prediction accurate value to obtain the fire estimation data.

[0017] In one embodiment, the calculation formula of the linear stochastic differential equation is:

[0018] ε(t) = Aε(t-1) + Bμ(t) + ω(t); and the calculation formula of the data observation equation is: CFS(t) = Hε(t) + v(t); wherein, ε(t) is a fire prediction value of the fire monitoring data at t time; μ(t) is an influencing factor of the fire monitoring data at t time; A and B are observation influencing factors of the fire monitoring data, and A and B are matrices for the complex interference environment of the fire scene; CFS(t) is the fire monitoring data at t time; H is a characteristic parameter of an extremely early measurement device for obtaining the fire monitoring data; ω(t) and v(t) are noises for processes and measurements.

[0019] In one embodiment, the calculation formula when the fire prediction value is processed by using the Kalman filtering algorithm to obtain the fire prediction accurate value is:

[0020] ε(t|t-1) = Aε(t-1|t-1) + Bμ(t)

[0021] P(t|t-1) = AP(t-1|t-1)A' + Q

[0022] wherein, ε(t|t-1) is a fire prediction value of the fire monitoring data at a previous state of t time; ε(t-1|t-1) is an optimal fire prediction value of the fire monitoring data at a previous state of t time; μ(t) is an influencing factor of the fire monitoring data at t time; P(t|t-1) is a covariance corresponding to ε(t|t-1); P(t-1|t-1) is a covariance corresponding to ε(t-1|t-1) at t time; A' is a transpose of A; and Q is a covariance of a system process.

[0023] In one embodiment, a calculation formula for obtaining fire estimation data by performing Kalman gain estimation calculation according to the fire prediction accurate value is as follows:

[0024] ε(t|t) = ε(t|t-1) + Kg(t)(CFS(t) - Hε(t|t-1))

[0025]

[0026] wherein, ε(t|t) is fire estimation data; ε(t|t-1) is a fire prediction value of the fire monitoring data at a previous state of t time; Kg is a Kalman gain; P(t|t-1) is a covariance corresponding to ε(t|t-1); H is a characteristic parameter of an early-stage measurement device for obtaining the fire monitoring data; H' is a transpose of H; and R is a covariance of v(t).

[0027] In one embodiment, a calculation formula for obtaining an area integral calculation value by performing calculation on the fire estimation data by using an area integral algorithm is as follows:

[0028]

[0029] wherein, η k is an area integral calculation value from a time t after triggering to a k time; and ε(k) is fire estimation data at the k time.

[0030] According to a second aspect of the embodiment of the present application, a fire monitoring system is provided.

[0031] In one embodiment, the fire monitoring system comprises:

[0032] an estimation processing module, configured to obtain fire monitoring data, and perform prediction estimation processing according to the fire monitoring data to obtain fire estimation data;

[0033] The integral calculation module is configured to compare the fire estimation data with an initial empirical fire threshold value, and calculate the fire estimation data by using an area integral algorithm to obtain an area integral calculation value, in a case where the comparison result is that the fire estimation data is greater than or equal to the initial empirical fire threshold value.

[0034] The fire judgment module is configured to compare the area integral calculation value with the initial empirical fire threshold value, and perform a fire alarm processing in a case where the comparison result is that the area integral calculation value is greater than the initial empirical fire threshold value.

[0035] In an embodiment, the fire monitoring system further comprises an abnormality judgment module configured to judge the obtained fire monitoring data, judge whether the fire monitoring data is abnormal, and perform the estimation processing according to the fire monitoring data in a case where the judgment result is that the fire monitoring data is normal, and re-obtain fire monitoring data in a case where the judgment result is that the fire monitoring data is abnormal.

[0036] In an embodiment, the abnormality judgment module judges the obtained fire monitoring data by using a 3-sigma principle to judge whether the fire monitoring data is abnormal.

[0037] In an embodiment, the estimation processing module comprises a prediction submodule, an accurate processing submodule and an estimation calculation submodule, wherein the prediction submodule is configured to calculate the fire monitoring data by using a linear stochastic differential equation and a data observation equation to obtain a fire prediction value; the accurate processing submodule is configured to process the fire prediction value by using a Kalman filtering algorithm to obtain a fire prediction accurate value; and the estimation calculation submodule is configured to perform Kalman gain estimation calculation according to the fire prediction accurate value to obtain fire estimation data.

[0038] In an embodiment, a calculation formula of the linear stochastic differential equation is: ε(t)=Aε(t-1)+Bμ(t)+ω(t); and a calculation formula of the data observation equation is: CFS(t)=Hε(t)+ν(t); wherein ε(t) is a fire prediction value of the fire monitoring data at t time; μ(t) is an influence factor of the fire monitoring data at t time; A and B are observation influence factors of the fire monitoring data, and are matrices for a complex interference environment of a fire scene; CFS(t) is the fire monitoring data at t time; H is a characteristic parameter of an early measurement device for obtaining the fire monitoring data; and ω(t) and ν(t) are noises for a process and measurement.

[0039] In one embodiment, the precise processing submodule utilizes a Kalman filtering algorithm to process the fire prediction value, and the calculation formula when obtaining a fire prediction precise value is:

[0040] ε(t|t-1)=Aε(t-1|t-1)+Bμ(t)

[0041] P(t|t-1)=AP(t-1|t-1)A'+Q

[0042] In the formula, ε(t|t-1) is a fire prediction value of fire monitoring data of a state at t time; ε(t-1|t-1) is an optimal fire prediction value of fire monitoring data of a state at t time; μ(t) is an influencing factor of fire monitoring data at t time; P(t|t-1) is a covariance corresponding to ε(t|t-1); P(t-1|t-1) is a covariance corresponding to ε(t-1|t-1); A' is a transpose of A; and Q is a covariance of a system process.

[0043] In one embodiment, the estimation calculation submodule utilizes a Kalman gain estimation calculation according to the fire prediction precise value, and the calculation formula when obtaining fire estimation data is:

[0044] ε(t|t)=ε(t|t-1)+Kg(t)(CFS(t)-Hε(t|t-1))

[0045]

[0046] In the formula, ε(t|t) is fire estimation data; ε(t|t-1) is a fire prediction value of fire monitoring data of a state at t time; Kg is a Kalman gain; P(t|t-1) is a covariance corresponding to ε(t|t-1); H is a characteristic parameter of an early measurement device for obtaining fire monitoring data; H' is a transpose of H; and R is a covariance of ν(t).

[0047] In one embodiment, the integral calculation module utilizes an area integral algorithm to calculate the fire estimation data, and the calculation formula when obtaining an area integral calculation value is:

[0048]

[0049] In the formula, η k is an area integral calculation value from t time after triggering to k time; and ε(k) is fire estimation data at k time.

[0050] The technical scheme provided by the embodiment of the present application can include the following beneficial effects:

[0051] This invention predicts fire monitoring data, processes the predicted data precisely, and then estimates the fire threshold, thereby obtaining an accurate fire threshold. This accurate fire threshold enables precise identification of various types of fires, reduces fire risk, and achieves accurate fire monitoring and early warning.

[0052] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0053] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0054] Figure 1 This is a flowchart illustrating a fire monitoring method according to an exemplary embodiment;

[0055] Figure 2 This is a schematic diagram of the structure of a fire monitoring system according to an exemplary embodiment;

[0056] Figure 3 This is a schematic diagram of the structure of a computer device according to an exemplary embodiment. Detailed Implementation

[0057] The following description and accompanying drawings fully illustrate specific embodiments described herein to enable those skilled in the art to practice them. Some embodiments may include or substitute parts and features of other embodiments. The scope of the embodiments herein encompasses the entire scope of the claims and all available equivalents thereof. Throughout this document, the terms “first,” “second,” etc., are used only to distinguish one element from another without requiring or implying any actual relationship or order between the elements. Indeed, a first element can also be referred to as a second element, and vice versa. Furthermore, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a structure, apparatus, or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the structure, apparatus, or device that includes said element. The various embodiments described herein are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments; similar or identical parts between embodiments can be referred to interchangeably.

[0058] The terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like as used herein to indicate orientation or positional relationships based on the orientations or positional relationships shown in the drawings, are for purposes of this description only, and are not intended to indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus is not to be construed as limiting the application to the particular embodiment illustrated and described. In the description of the present application, unless otherwise stated and limited, the terms "mount", "connect", "connection" should be construed broadly, for example, can be mechanical or electrical connection, can be internal connection of two elements, can be direct connection, or indirect connection through intermediate medium, the specific meaning of the above terms can be understood by the person skilled in the art according to the specific circumstances.

[0059] In this article, unless otherwise stated, the term "a plurality of" means two or more.

[0060] In this article, the character " / " represents the relationship of "or" between the front and rear objects. For example, A / B means: A or B.

[0061] In this article, the term "and / or" is a description of the relationship between the objects, which means that there can be three relationships. For example, A and / or B means: A or B, or, A and B, three relationships.

[0062] It should be understood that although each step in the flowchart is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other order. Moreover, at least part of the steps in the figure can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0063] Each module in the device or system of the present application can be realized by software, hardware and their combination in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so as to call and execute the operations corresponding to the above modules by the processor.

[0064] In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0065] Figure 1An embodiment of a fire monitoring method of the present application is shown.

[0066] In this alternative embodiment, the fire monitoring method comprises:

[0067] In step S101, fire monitoring data is acquired, and prediction and estimation processing is performed according to the fire monitoring data to obtain fire estimation data.

[0068] In step S103, the fire estimation data is compared with an initial empirical fire threshold value, and in the case where the comparison result is that the fire estimation data is greater than or equal to the initial empirical fire threshold value, an area integral algorithm is used to calculate the fire estimation data to obtain an area integral calculation value.

[0069] In step S105, the area integral calculation value is compared with the initial empirical fire threshold value, and in the case where the comparison result is that the area integral calculation value is greater than the initial empirical fire threshold value, fire alarm processing is performed.

[0070] In one embodiment, in order to ensure the accuracy of the later fire threshold estimation, the fire monitoring method can further comprise: judging the acquired fire monitoring data to determine whether the fire monitoring data is abnormal, and in the case where the judgment result is that the fire monitoring data is normal, performing estimation processing according to the fire monitoring data again; and in the case where the judgment result is that the fire monitoring data is abnormal, re-acquiring fire monitoring data.

[0071] Specifically, when the acquired fire monitoring data is judged to determine whether the fire monitoring data is abnormal, the acquired fire monitoring data is judged using the 3 Sigma principle to determine whether the fire monitoring data is abnormal.

[0072] The specific process of judging the acquired fire monitoring data using the 3 Sigma principle is as follows:

[0073] The calculation method of the fire measurement mean value is as follows:

[0074]

[0075] Wherein, is the mean value of the acquired very early monitoring data at time t, CFS t is the acquired very early monitoring data at time t; T0 is the current time, T N-1 is the Nth measurement time point before the current time.

[0076] The calculation formula of the standard deviation σ of the fire measurement is as follows:

[0077]

[0078] When the measured point real-time data exceeds the interval, it is considered that the data is abnormal, and needs to be measured again, and the value is saved.

[0079] In one embodiment, the fire measurement data comes from an extremely early fire monitoring device, and considering that there will be certain errors in the fire monitoring process affected by the environment, accurate fire measurement data needs to be estimated; the estimation process is: linear random differential equation and data observation equation are used to calculate the fire monitoring data to obtain fire prediction value; Kalman filtering algorithm is used to process the fire prediction value to obtain fire prediction accurate value; according to the fire prediction accurate value, Kalman gain estimation calculation is carried out to obtain fire estimation data.

[0080] In application, the fire monitoring data is obtained through early fire identification by combining cloud and fog chamber early detection and optical scattering chamber secondary detection, and the data acquisition process of the fire monitoring data at a certain moment is represented as an offline process system under the influence of the external environment, which is expressed by a linear random differential equation and a data observation equation of the fire monitoring data, as follows:

[0081] The calculation formula of the linear random differential equation is: ε(t)=Aε(t-1)+Bμ(t)+ω(t); the calculation formula of the data observation equation is: CFS(t)=Hε(t)+ν(t); wherein, ε(t) is the fire prediction value of the fire monitoring data at t time; μ(t) is the influence factor of the fire monitoring data at t time; A and B are observation influence factors of the fire monitoring data, and A and B are matrices for the complex interference environment of the fire scene; CFS(t) is the fire monitoring data at t time; H is a characteristic parameter of the extremely early measurement device for obtaining the fire monitoring data; ω(t) and ν(t) are process and measurement noises.

[0082] In one embodiment, the process and measurement of the linear random differential equation are Gaussian white noises, so Kalman filtering needs to be used to obtain accurate fire monitoring data, and the calculation formula when the Kalman filtering algorithm is used to process the fire prediction value to obtain the fire prediction accurate value is:

[0083] ε(t|t-1)=Aε(t-1|t-1)+Bμ(t)

[0084] P(t|t-1)=AP(t-1|t-1)A'+Q

[0085] In the formula, ε (t|t-1) is the fire prediction value of the fire monitoring data at the previous state of t time; ε (t-1|t-1) is the optimal fire prediction value of the fire monitoring data at the previous state of t time; μ (t) is the influencing factor of the fire monitoring data at t time; P (t|t-1) is the covariance corresponding to ε (t|t-1) ; P (t-1|t-1) is the covariance corresponding to ε (t-1|t-1) at the moment; A' is the transpose of A; and Q is the covariance of the system process.

[0086] In one embodiment, the calculation formula when the fire estimation data is obtained by performing Kalman gain estimation calculation according to the fire prediction accurate value is as follows:

[0087] ε (t|t) = ε (t|t-1) + Kg (t) (CFS (t) - Hε (t|t-1) )

[0088]

[0089] In the formula, ε (t|t) is the fire estimation data; ε (t|t-1) is the fire prediction value of the fire monitoring data at the previous state of t time; Kg is the Kalman gain; P (t|t-1) is the covariance corresponding to ε (t|t-1) ; H is the characteristic parameter of the early measurement device for obtaining the fire monitoring data; H' is the transpose of H; and R is the covariance of v (t).

[0090] In addition, considering that the fire monitoring data is a multi-time observation process, the above filtering process needs to be continuously performed to continuously update the covariance of ε (t|t) at t time, and the formula is as follows:

[0091] P (t|t) = (I-Kg (t) H) P (t|t-1)

[0092] Wherein, the data observation of the fire monitoring data is single modulus, and I is 1.

[0093] In one embodiment, the initial empirical fire threshold is actually the fire L0 level alarm threshold given by the equipment according to the manufacturer. When the area integral algorithm is used to calculate the fire estimation data, the calculation formula for obtaining the area integral calculation value is as follows:

[0094]

[0095] In the formula, η k is the calculation value of the area integral from the t time when the trigger occurs to the k time; and ε (k) is the fire estimation data at the k time.

[0096] Figure 2 An embodiment of a fire monitoring system of the present application is shown.

[0097] In the optional embodiment, the fire monitoring system comprises:

[0098] The estimation processing module 201 is configured to acquire fire monitoring data and perform prediction estimation processing according to the fire monitoring data to obtain fire estimation data.

[0099] The integral calculation module 203 is configured to compare the fire estimation data with an initial experience fire threshold value, and perform calculation on the fire estimation data by using an area integral algorithm to obtain an area integral calculation value in a case where the comparison result is that the fire estimation data is greater than or equal to the initial experience fire threshold value.

[0100] The fire judgment module 205 is configured to compare the area integral calculation value with the initial experience fire threshold value, and perform fire alarm processing in a case where the comparison result is that the area integral calculation value is greater than the initial experience fire threshold value.

[0101] In one embodiment, in order to ensure the accuracy of the later fire threshold estimation, the fire monitoring system further comprises an abnormality judgment module (not shown in the figure) configured to judge the acquired fire monitoring data to determine whether the fire monitoring data is abnormal, and perform estimation processing according to the fire monitoring data in a case where the judgment result is that the fire monitoring data is normal; and reacquire fire monitoring data in a case where the judgment result is that the fire monitoring data is abnormal.

[0102] Specifically, when judging the acquired fire monitoring data to determine whether the fire monitoring data is abnormal, the abnormality judgment module judges the acquired fire monitoring data by using the 3 Sigma principle to determine whether the fire monitoring data is abnormal.

[0103] In one embodiment, correspondingly, the estimation processing module 201 comprises a prediction submodule (not shown in the figure), an accurate processing submodule (not shown in the figure), and an estimation calculation submodule (not shown in the figure), wherein the prediction submodule is configured to calculate the fire monitoring data by using a linear stochastic differential equation and a data observation equation to obtain a fire prediction value; the accurate processing submodule is configured to process the fire prediction value by using a Kalman filtering algorithm to obtain a fire prediction accurate value; and the estimation calculation submodule is configured to perform Kalman gain estimation calculation according to the fire prediction accurate value to obtain fire estimation data.

[0104] In one embodiment, a computer device is provided, which can be a server, and an internal structure diagram of the computer device can be as shown in Figure 3As shown in the figure. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with the external terminal through the network connection. The computer program is executed by the processor to realize the steps in the above method embodiments.

[0105] Those skilled in the art can understand that, Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0106] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps in the above method embodiments.

[0107] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to realize the steps in the above method embodiments.

[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0109] The present application is not limited to the structures described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A fire monitoring method, characterized in that, include: Fire monitoring data is acquired, and prediction and estimation processing is performed based on the fire monitoring data to obtain fire estimation data. The prediction and estimation processing to obtain fire estimation data includes: calculating the fire monitoring data using linear stochastic differential equations and data observation equations to obtain fire prediction values; processing the fire prediction values ​​using a Kalman filter algorithm to obtain accurate fire prediction values; and performing Kalman gain estimation calculations based on the accurate fire prediction values ​​to obtain the fire estimation data. The fire estimation data is compared with the initial empirical fire threshold. If the comparison result shows that the fire estimation data is greater than or equal to the initial empirical fire threshold, the area integral algorithm is used to calculate the fire estimation data to obtain the area integral calculated value. The calculated area integral value is compared with the initial empirical fire threshold. If the calculated area integral value is greater than the initial empirical fire threshold, a fire alarm is triggered.

2. The fire monitoring method according to claim 1, characterized in that, Also includes: The acquired fire monitoring data is evaluated to determine whether it is abnormal. If the evaluation result indicates that the fire monitoring data is normal, estimation processing is performed based on the fire monitoring data. If the evaluation result indicates that the fire monitoring data is abnormal, the fire monitoring data is reacquired.

3. The fire monitoring method according to claim 2, characterized in that, The acquired fire monitoring data is evaluated to determine whether the fire monitoring data is abnormal, including: The three sigma principle is used to evaluate the acquired fire monitoring data to determine whether the fire monitoring data is abnormal.

4. The fire monitoring method according to claim 3, characterized in that, The calculation formula for the linear stochastic differential equation is: ε(t)=Aε(t-1)+Bμ(t)+ω(t); the calculation formula for the data observation equation is: CFS(t)=Hε(t)+ν(t); where ε(t) is the fire prediction value of the fire monitoring data at time t; μ(t) is the influencing factor on the fire monitoring data at time t; A and B are the observation influence factors of the fire monitoring data, and A and B are matrices for the complex interference environment at the fire scene; CFS(t) is the fire monitoring data at time t; H is the characteristic parameter of the very early measurement device for acquiring fire monitoring data; ω(t) and ν(t) are the noise of the process and measurement.

5. The fire monitoring method according to claim 4, characterized in that, The formula for calculating the accurate fire prediction value by processing the fire prediction value using the Kalman filter algorithm is as follows: ε(t|t-1)=Aε(t-1|t-1)+Bμ(t) P(t|t-1)=AP(t-1|t-1)A'+Q In the formula, ε(t|t-1) is the fire prediction value of the fire monitoring data in the previous state at time t; ε(t-1|t-1) is the optimal fire prediction value of the fire monitoring data in the previous state at time t; μ(t) is the influencing factor on the fire monitoring data at time t; P(t|t-1) is the covariance corresponding to ε(t|t-1); P(t-1|t-1) is the covariance corresponding to time ε(t-1|t-1); A' is the transpose of A; Q is the covariance of the system process.

6. The fire monitoring method according to claim 5, characterized in that, The formula for calculating the fire estimation data by performing Kalman gain estimation based on the accurate fire prediction value is as follows: ε(t|t)=ε(t|t-1)+Kg(t)(CFS(t)-Hε(t|t-1)) In the formula, ε(t|t) represents the fire estimation data; ε(t|t-1) is the fire prediction value of the fire monitoring data in the previous state at time t; Kg is the Kalman gain; P(t|t-1) is the covariance corresponding to ε(t|t-1); H is the characteristic parameter of the very early measurement device for acquiring fire monitoring data; H ' R is the transpose of H; R is the covariance of ν(t).

7. The fire monitoring method according to claim 6, characterized in that, The area integral algorithm is used to calculate the fire estimation data, and the calculation formula for obtaining the area integral value is as follows: In the formula, η k ε(k) is the calculated value of the area integral from the time of triggering at time t to time k; ε(k) is the fire estimation data at time k.

8. A fire monitoring system, characterized in that, include: The estimation processing module is used to acquire fire monitoring data and perform prediction estimation processing based on the fire monitoring data to obtain fire estimation data. The estimation processing module includes a prediction submodule, an accuracy processing submodule, and an estimation calculation submodule. The prediction submodule is used to calculate the fire monitoring data using linear stochastic differential equations and data observation equations to obtain a fire prediction value. The accuracy processing submodule is used to process the fire prediction value using a Kalman filter algorithm to obtain an accurate fire prediction value. The estimation calculation submodule is used to perform Kalman gain estimation calculations based on the accurate fire prediction value to obtain fire estimation data. The integral calculation module is used to compare the fire estimation data with the initial empirical fire threshold. If the comparison result shows that the fire estimation data is greater than or equal to the initial empirical fire threshold, the area integral algorithm is used to calculate the fire estimation data to obtain the area integral calculated value. The fire detection module is used to compare the calculated area integral value with the initial empirical fire threshold, and to perform fire alarm processing if the comparison result shows that the calculated area integral value is greater than the initial empirical fire threshold.

9. The fire monitoring system according to claim 8, characterized in that, Also includes: The anomaly detection module is used to judge the acquired fire monitoring data to determine whether the fire monitoring data is abnormal. If the judgment result is that the fire monitoring data is normal, estimation processing is performed based on the fire monitoring data; if the judgment result is that the fire monitoring data is abnormal, the fire monitoring data is reacquired.

10. The fire monitoring system according to claim 9, characterized in that, When the anomaly detection module judges the acquired fire monitoring data to determine whether the fire monitoring data is abnormal, it uses the 3 sigma principle to judge the acquired fire monitoring data to determine whether the fire monitoring data is abnormal.

11. The fire monitoring system according to claim 10, characterized in that, The calculation formula for the linear stochastic differential equation is: ε(t)=Aε(t-1)+Bμ(t)+ω(t); the calculation formula for the data observation equation is: CFS(t)=Hε(t)+ν(t); where ε(t) is the fire prediction value of the fire monitoring data at time t; μ(t) is the influencing factor on the fire monitoring data at time t; A and B are the observation influence factors of the fire monitoring data, and A and B are matrices for the complex interference environment at the fire scene; CFS(t) is the fire monitoring data at time t; H is the characteristic parameter of the very early measurement device for acquiring fire monitoring data; ω(t) and ν(t) are the noise of the process and measurement.

12. The fire monitoring system according to claim 11, characterized in that, The precise processing submodule uses the Kalman filter algorithm to process the fire prediction value and obtains the precise fire prediction value using the following formula: ε(t|t-1)=Aε(t-1|t-1)+Bμ(t) P(t|t-1)=AP(t-1|t-1)A'+Q In the formula, ε(t|t-1) is the fire prediction value of the fire monitoring data in the previous state at time t; ε(t-1|t-1) is the optimal fire prediction value of the fire monitoring data in the previous state at time t; μ(t) is the influencing factor on the fire monitoring data at time t; P(t|t-1) is the covariance corresponding to ε(t|t-1); P(t-1|t-1) is the covariance corresponding to time ε(t-1|t-1); A' is the transpose of A; Q is the covariance of the system process.

13. The fire monitoring system according to claim 12, characterized in that, The calculation formula used by the estimation submodule to perform Kalman gain estimation based on the accurate fire prediction value and obtain the fire estimation data is as follows: ε(t|t)=ε(t|t-1)+Kg(t)(CFS(t)-Hε(t|t-1)) In the formula, ε(t|t) represents the fire estimation data; ε(t|t-1) is the fire prediction value of the fire monitoring data in the previous state at time t; Kg is the Kalman gain; P(t|t-1) is the covariance corresponding to ε(t|t-1); H is the characteristic parameter of the very early measurement device for acquiring fire monitoring data; H ' R is the transpose of H; R is the covariance of ν(t).

14. The fire monitoring system according to claim 13, characterized in that, The integral calculation module uses an area integral algorithm to calculate the fire estimation data, and the calculation formula for obtaining the area integral value is as follows: In the formula, η k ε(k) is the calculated value of the area integral from the time of triggering at time t to time k; ε(k) is the fire estimation data at time k.

Images