Method, apparatus, equipment and medium for generating acoustic fire trend results based on HRR

Abstract

This application discloses a method, apparatus, equipment, and medium for generating acoustic fire trend results based on HRR (Heat Release Rate), relating to the field of fire detection technology. The method includes: acquiring a sequence of flame energy characteristic values ​​through an acoustic monitoring terminal; converting this sequence into time-series heat release rate values ​​using a preset physical correlation model; and after anomaly processing, curve fitting, and standardization, combining this with a multi-scenario heat release rate trend model to generate fire trend analysis results through multi-dimensional visualization mapping. This achieves non-contact, precise monitoring, solves the problem of incomparable data across different scenarios, intuitively presents fire trends, provides accurate data for emergency response, and reduces fire hazards.

Description

Technical Field

[0001] This invention relates to the field of fire detection technology, and in particular to a method, apparatus, equipment and medium for generating acoustic fire trend results based on HRR. Background Technology

[0002] Existing technologies for analyzing the trend of fire heat release rate mainly employ two approaches: One involves using contact-type devices such as temperature sensors and heat flow meters to directly measure heat-related parameters at the fire scene, calculate the heat release rate through simple conversion, and then roughly determine the fire trend by combining this with limited historical data. The other approach utilizes acoustic monitoring equipment to receive acoustic signals from the fire scene, extract basic energy characteristics, and convert them into heat release rate values ​​through a simple linear mapping relationship. This outputs only single-rate data or simple time-series curves, without standardization or multi-scenario comparison. While some solutions can classify fire types, they only output type identifiers and cannot generate complete trend results that include trend evolution patterns and scenario difference analysis. Furthermore, they do not consider the impact of ventilation conditions on the heat release rate and fail to construct multi-scenario comparison models.

[0003] Existing technologies have significant shortcomings and are unable to meet the needs for precise and comprehensive fire trend monitoring: First, contact-based measurement equipment is susceptible to the effects of high temperatures and smoke corrosion in fire scenes, resulting in low measurement accuracy and poor stability. Furthermore, it cannot achieve large-scale monitoring and is difficult to obtain continuous and stable time-series data on heat release rates. Second, the heat release rate curves have not undergone time axis transformation and amplitude normalization, making it difficult to compare rate data from different fire scenarios and different burning durations with standard scenarios. Third, the technology has not incorporated different fire types and ventilation coefficients to construct multi-scenario heat release rate trend models, making it impossible to accurately identify the differences between the current fire and standard scenarios.

[0004] Therefore, how to achieve accurate quantitative analysis of fire heat release rate based on acoustic perception, and how to generate accurate and comprehensive fire trend analysis results by combining multi-scenario heat release rate trend models, has become an urgent problem to be solved. Summary of the Invention

[0005] The main objective of this application is to provide a method, apparatus, device, and medium for generating acoustic fire trend results based on HRR, aiming to solve the technical problem of how to achieve accurate quantification of HRR and generate accurate fire trend analysis results based on acoustic perception.

[0006] To achieve the above objectives, this application proposes a method for generating acoustic fire trend results based on HRR, comprising:

[0007] The system receives a multi-frame continuous sequence of flame energy feature values ​​for the current monitoring scene uploaded by an acoustic monitoring terminal. The flame energy feature value sequence is obtained by the acoustic monitoring terminal by transmitting ultrasonic waves to the monitoring area, receiving flame reflected echoes, and extracting energy features.

[0008] The flame energy characteristic value sequence is converted into a time-series heat release rate value according to a preset physical correlation model, wherein the preset physical correlation model is a model that integrates ultrasonic wave propagation delay and fire temperature distribution.

[0009] The time-series heat release rate values ​​are processed by outlier removal and trend completion to obtain the processed time-series rate values.

[0010] The processed time-series rate values ​​are continuously fitted along the time axis to obtain the heat release rate curve.

[0011] The heat release rate curve is subjected to time axis transformation and amplitude normalization to obtain standardized heat release rate data;

[0012] Based on preset fire type parameters and ventilation condition parameters, a multi-scenario heat release rate trend model was constructed, and standard trend datasets of fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover fires under different ventilation coefficients were obtained.

[0013] Based on the standardized heat release rate data and the standard trend dataset, multi-dimensional visualization mapping and chart rendering are performed to obtain fire trend analysis results.

[0014] In one embodiment, the step of performing time axis transformation and amplitude normalization on the heat release rate curve to obtain standardized heat release rate data includes:

[0015] Obtain the start and end points of time and the extreme values ​​of amplitude of the heat release rate curve, and generate time amplitude reference parameters;

[0016] Based on the time amplitude reference parameter, the heat release rate curve is subjected to a time axis linear stretching transformation to obtain a fixed duration rate curve;

[0017] Based on the extreme values ​​of the amplitude of the fixed-duration rate curve, the amplitude of the curve is linearly normalized to obtain the normalized amplitude rate curve.

[0018] The normalized amplitude rate curve is sampled at equal intervals to obtain standardized heat release rate data.

[0019] In one embodiment, the step of constructing a multi-scenario heat release rate trend model based on preset fire type parameters and ventilation condition parameters to obtain standard trend datasets for fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover fires under different ventilation coefficients includes:

[0020] Retrieve preset fire type parameters, wherein the preset fire type parameters include the combustion characteristic parameters of each of fuel-controlled, ventilation-restricted, pulsed, and ventilation-induced flashover fires;

[0021] Multiple sets of different ventilation coefficient parameters are set, which cover three ventilation conditions: low ventilation, medium ventilation, and high ventilation.

[0022] Based on the principles of fire combustion dynamics, combined with the preset fire type parameters and ventilation coefficient parameters of each group, a multi-scenario heat release rate trend model is constructed.

[0023] The multi-scenario heat release rate trend model is used to simulate and generate standard curves of heat release rate for various types of fires under different ventilation coefficients.

[0024] All the heat release rate standard curves were categorized and organized according to fire type and ventilation coefficient to form an initial trend dataset;

[0025] The initial trend dataset is validated, and standard curves whose simulated deviations exceed a preset range are removed to obtain a standard trend dataset.

[0026] In one embodiment, the step of constructing a multi-scenario heat release rate trend model based on the principles of fire combustion dynamics, combined with the preset fire type parameters and various sets of ventilation coefficient parameters, includes:

[0027] Obtain standard experimental results and validation data;

[0028] A fire combustion rate equation is introduced, and the basic combustion model for various types of fires is determined by combining preset fire type parameters.

[0029] By substituting different ventilation coefficient parameters into the basic combustion model and correcting the oxygen supply coefficient and combustion efficiency parameters in the model, a single-scenario heat release rate model under different ventilation conditions is obtained.

[0030] Based on the single-scenario heat release rate model, a heat radiation attenuation factor is added to compensate for the influence of ventilation conditions on fire heat release, and the corresponding single-scenario optimization model is obtained.

[0031] The verification data is input into the single-scenario optimization model to obtain the simulation results;

[0032] The model parameters of the single-scenario heat release rate model are adjusted by an iterative optimization algorithm until the deviation between the simulation results and the standard experimental results is less than a preset deviation threshold. The model parameters of all the single-scenario optimization models are then integrated to construct a complete multi-scenario heat release rate trend model.

[0033] In one embodiment, the step of classifying and organizing all the heat release rate standard curves according to fire type and ventilation coefficient to form an initial trend dataset includes:

[0034] Extract the fire type identifier and ventilation coefficient identifier corresponding to all generated heat release rate standard curves;

[0035] Using the fire type identifier as the primary classification dimension, all heat release rate standard curves are divided into four categories: fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover.

[0036] Within each group of curves, the ventilation coefficient is used as the secondary classification dimension, and the curves are sorted and arranged in ascending order of ventilation coefficient to form a classification subgroup.

[0037] Add a unique classification label to each group of curves and each subgroup of classification, and label the corresponding fire type and ventilation coefficient to obtain a subset of data;

[0038] All the aforementioned subsets are integrated to form the initial trend dataset.

[0039] In one embodiment, the step of performing multi-dimensional visualization mapping and chart rendering based on the standardized heat release rate data and the standard trend dataset to obtain fire trend analysis results includes:

[0040] The standardized heat release rate data is converted into a visual time-series curve to obtain the current monitored heat release rate visualization curve.

[0041] From the standard trend dataset, heat release rate standard curves that are compatible with the current monitoring scenario are selected according to preset rules to obtain the adapted standard curves. The preset rule is that the features of the standardized heat release rate data have the greatest similarity to the features of each heat release rate standard curve in the standard trend dataset.

[0042] A multi-dimensional mapping is performed between the current monitored heat release rate visualization curve and the adapted standard curve to obtain a curve comparison visualization layer;

[0043] Extract the amplitude change, time-series slope, and peak characteristic data of the current monitored heat release rate visualization curve, and render and generate amplitude change chart, time-series slope chart, and peak characteristic chart respectively;

[0044] By integrating the curve comparison visualization layer, amplitude change chart, time series slope chart, and peak characteristic chart, and adding chart descriptions and trend analysis annotations, a complete fire trend analysis result is obtained.

[0045] In one embodiment, the step of performing multi-dimensional mapping between the currently monitored heat release rate visualization curve and the adapted standard curve to obtain a curve comparison visualization layer includes:

[0046] Extract the first time-series data, the first amplitude peak value, and the first time-series slope of the current monitored heat release rate visualization curve, and simultaneously extract the second time-series data, the second amplitude peak value, and the second time-series slope corresponding to the adaptation standard curve to obtain the corresponding multi-dimensional feature parameters;

[0047] Based on the first time series data and the second time series data, the current monitored heat release rate visualization curve and the adaptation standard curve are synchronously calibrated to obtain the current monitored heat release rate visualization curve and the time series synchronized adaptation standard curve.

[0048] The current monitored heat release rate visualization curve after time synchronization and the adapted standard curve after time synchronization are mapped to the same visualization coordinate system to obtain the first curve and the second curve;

[0049] Mark the peak amplitude positions and peak time nodes of the first and second curves in the coordinate system, and label the peak difference and peak time difference to form feature labeling information;

[0050] Set different line colors, line thicknesses, and timeline styles for the first and second curves, add legends to distinguish the two curves, and generate a basic contrast layer.

[0051] The feature annotation information is superimposed on the basic comparison layer to optimize the layer display clarity and obtain a curve comparison visualization layer.

[0052] Furthermore, to achieve the above objectives, this application also proposes an acoustic fire trend result generation device based on HRR, wherein the HRR-based acoustic fire trend result generation device includes:

[0053] The receiving module is used to receive a multi-frame continuous flame energy characteristic value sequence of the current monitoring scene uploaded by the acoustic monitoring terminal;

[0054] The conversion module is used to convert the flame energy characteristic value sequence into a time-series heat release rate value according to a preset physical correlation model, wherein the preset physical correlation model is a model that integrates ultrasonic wave propagation delay and fire temperature distribution.

[0055] The processing module is used to perform outlier removal and trend completion processing on the time-series heat release rate values ​​to obtain the processed time-series rate values.

[0056] The curve simulation module is used to continuously fit the processed time-series rate values ​​to the time axis to obtain the heat release rate curve.

[0057] The normalization module is used to perform time axis transformation and amplitude normalization on the heat release rate curve to obtain standardized heat release rate data.

[0058] The module is used to build a multi-scenario heat release rate trend model based on preset fire type parameters and ventilation condition parameters, and to obtain standard trend datasets for fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover fires under different ventilation coefficients.

[0059] The results module is used to perform multi-dimensional visualization mapping and chart rendering based on the standardized heat release rate data and the standard trend dataset to obtain fire trend analysis results.

[0060] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the HRR-based acoustic fire trend result generation method described above.

[0061] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the HRR-based acoustic fire trend result generation method described above.

[0062] This application acquires flame energy characteristic value sequences through an acoustic monitoring terminal, converts them into time-series heat release rate values ​​using a preset physical correlation model, and after anomaly processing, curve fitting, and standardization, combines them with a multi-scenario heat release rate trend model to generate fire trend analysis results through multi-dimensional visualization mapping. This achieves non-contact, precise monitoring, solves the problem of incomparable data across different scenarios, intuitively presents fire trends, provides accurate data for emergency response, and reduces fire hazards. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1This is a flowchart illustrating the first embodiment of the acoustic fire trend result generation method based on HRR of this application.

[0065] Figure 2 This is a flowchart illustrating the second embodiment of the acoustic fire trend result generation method based on HRR in this application.

[0066] Figure 3 This is a schematic diagram of the module structure of the acoustic fire trend result generation device based on HRR in this application;

[0067] Figure 4 This is a schematic diagram of the device structure of the hardware operating environment involved in the HRR-based acoustic fire trend result generation method in the embodiments of this application.

[0068] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0069] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0070] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0071] Existing technologies for analyzing the trend of fire heat release rate mainly employ two approaches: One involves using contact-type devices such as temperature sensors and heat flow meters to directly measure heat-related parameters at the fire scene, calculate the heat release rate through simple conversion, and then roughly determine the fire trend by combining this with limited historical data. The other approach utilizes acoustic monitoring equipment to receive acoustic signals from the fire scene, extract basic energy characteristics, and convert them into heat release rate values ​​through a simple linear mapping relationship. This outputs only single-rate data or simple time-series curves, without standardization or multi-scenario comparison. While some solutions can classify fire types, they only output type identifiers and cannot generate complete trend results that include trend evolution patterns and scenario difference analysis. Furthermore, they do not consider the impact of ventilation conditions on the heat release rate and fail to construct multi-scenario comparison models.

[0072] Existing technologies have significant shortcomings and are unable to meet the needs for precise and comprehensive fire trend monitoring: First, contact-based measurement equipment is susceptible to the effects of high temperatures and smoke corrosion in fire scenes, resulting in low measurement accuracy and poor stability. Furthermore, it cannot achieve large-scale monitoring and is difficult to obtain continuous and stable time-series data on heat release rates. Second, the heat release rate curves have not undergone time axis transformation and amplitude normalization, making it difficult to compare rate data from different fire scenarios and different burning durations with standard scenarios. Third, the technology has not incorporated different fire types and ventilation coefficients to construct multi-scenario heat release rate trend models, making it impossible to accurately identify the differences between the current fire and standard scenarios.

[0073] Therefore, how to achieve accurate quantitative analysis of fire heat release rate based on acoustic perception, and how to generate accurate and comprehensive fire trend analysis results by combining multi-scenario heat release rate trend models, has become an urgent problem to be solved.

[0074] Based on the above, this application also provides a method for generating acoustic fire trend results based on HRR, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the acoustic fire trend result generation method based on HRR of this application.

[0075] In this embodiment, the method for generating acoustic fire trend results based on HRR includes steps S10 to S70:

[0076] Step S10: Receive a sequence of multiple consecutive flame energy characteristic values ​​for the current monitoring scene uploaded by the acoustic monitoring terminal.

[0077] It should be noted that the flame energy characteristic value sequence is obtained by the acoustic monitoring terminal by transmitting ultrasonic waves into the current monitoring scene, receiving the flame reflection echo, and extracting energy characteristics. The current monitoring scene is a pre-defined spatial range for fire detection and data collection, covering the target location where the flame appears. The ultrasonic signal is an acoustic signal formed by loading a basic signal frame onto a high-frequency carrier wave. The frequency of this signal is higher than the range of human hearing, thus avoiding noise interference to the environment. The flame reflection echo is the acoustic signal that the emitted ultrasonic signal propagates back after passing through the flame area and contacting the reflecting surface, carrying all the characteristic information of how the flame affects the sound wave transmission.

[0078] Specifically, firstly, a data communication connection is established with the acoustic monitoring terminal, network communication parameters or serial port communication parameters are configured, the data transmission protocol stack is initialized, a connection request is sent, and a handshake response from the acoustic monitoring terminal is awaited. After successful connection establishment, a heartbeat detection mechanism is maintained to ensure stable communication link. Secondly, a data acquisition command is sent to the acoustic monitoring terminal to initiate the acquisition process: transmitting ultrasonic signals modulated to a high-frequency carrier wave to the monitoring area, receiving echo signals reflected from the flame area and reflective surface, demodulating and estimating the channel impulse response data to obtain channel impulse response data, extracting the flame impact delay range from the channel impulse response data, and calculating the total energy within that delay range. The data buffer status of the acoustic monitoring terminal is periodically polled. The system waits for data packets actively pushed by the acoustic monitoring terminal. Then, it receives data packets uploaded by the acoustic monitoring terminal, parses the packet header to obtain frame number, timestamp, and data length information, verifies the integrity of the data packet, and extracts flame energy feature values ​​from the packet payload if the verification passes. The extracted flame energy feature values ​​are then sorted by frame number and timestamp. If a discontinuous frame number or timestamp jump is detected, a retransmission request is sent to the acoustic monitoring terminal. If the verification fails, the data packet is discarded and a retransmission request is requested. Finally, the verified and sorted sequence of multiple consecutive flame energy feature values ​​is stored in the data buffer, the reception time and status flag of each frame are recorded, and the data packet memory resources are released, completing the reception of the flame energy feature value sequence for the current monitoring scenario. This is done because establishing a stable communication connection is the foundation of data transmission; actively sending acquisition commands can synchronize the working status of the acoustic monitoring terminal; the data packet verification and retransmission mechanism ensures the integrity and reliability of the received data; and sorting by frame number and timestamp ensures the temporal consistency of the data, providing a complete and continuous input data stream for subsequent heat release rate conversion.

[0079] Step S20: Convert the flame energy feature value sequence into a time-series heat release rate value according to the preset physical correlation model.

[0080] It should be noted that the preset physical correlation model is a model that integrates ultrasonic wave propagation delay and fire temperature distribution. This model is based on the relationship that the propagation speed of sound in a gaseous medium is proportional to the square root of the gas temperature. It couples the heat released by the flame with the temperature field distribution through the principle of energy conservation, achieving accurate conversion between acoustic feature data and heat release rate data.

[0081] Specifically, firstly, the flame energy feature value sequence is read frame by frame from the data buffer, and the flame energy value and its associated flame influence delay range parameter are extracted for each frame. This delay range parameter characterizes the propagation time span of sound waves through the high-temperature region of the flame. Secondly, the equivalent flame diameter is calculated based on the flame influence delay range, and the delay range is multiplied by the sound wave propagation speed to obtain the geometric scale of the high-temperature region. The flame volume estimate is calculated based on the equivalent flame diameter. Assuming the flame is a hemispherical or cylindrical geometry, the flame volume estimate is substituted into the ideal gas law to calculate the fire temperature distribution. Subsequently, the flame energy value and fire temperature distribution are input into a preset physical correlation model, and the model calculations are performed. The initial value of the heat release rate for the current frame is calculated by comprehensively considering the spatial scale information reflected by the sound wave propagation delay and the intensity information reflected by the energy value. Next, preset fuel type parameters are retrieved, and the corresponding combustion efficiency coefficient and stoichiometry are looked up according to the fuel type of the current monitoring scenario. The initial heat release rate value is multiplied by the combustion efficiency coefficient for combustion completeness correction, and then divided by the stoichiometry for standardization, eliminating systematic biases caused by differences in combustion characteristics of different fuel types, resulting in a calibrated heat release rate value. Finally, the calibrated heat release rate values ​​of each frame are arranged in time-stamp order to form a time-series heat release rate value sequence, which is stored in the heat release rate data buffer. This is done because flame energy characteristic values ​​are indirect parameters obtained from acoustic measurements. They need to be converted into a heat release rate with clear physical meaning through a physical correlation model that integrates ultrasonic wave propagation delay and fire temperature distribution. This model establishes a theoretical bridge between acoustic parameters and thermophysical quantities, enabling the conversion results to truly reflect the energy release level of the fire. The introduction of fuel type parameters enables adaptive calibration under different combustion scenarios, ensuring the accuracy and comparability of the time-series heat release rate values.

[0082] Step S30: Perform outlier removal and trend completion processing on the time-series heat release rate values ​​to obtain the processed time-series rate values.

[0083] It should be noted that outlier removal is a process of filtering and removing abnormal data from the time-series heat release rate values. These abnormal data are usually caused by signal interference or acquisition fluctuations, and deviate significantly from normal combustion patterns. Removing them ensures the overall validity of the data. Trend completion processing, after outlier removal, involves supplementing missing values ​​based on the changing patterns of the remaining normal data. Completion follows the natural changing trend of the fire heat release rate, ensuring data continuity and conformity to actual combustion logic.

[0084] Specifically, firstly, the time-series thermal release rate numerical sequence is retrieved from the thermal release rate data buffer. The timestamps and corresponding thermal release rate values ​​of each data point are identified, and the time intervals between adjacent data points are calculated, marking abnormal jumps in time intervals. Secondly, a preset anomaly detection threshold is set. Each data point in the time-series thermal release rate numerical sequence is traversed, and the first difference between the current data point and the previous data point, as well as the second difference between the current data point and the next data point, are calculated. The first and second differences are compared with the preset anomaly detection thresholds. When both the first and second differences exceed the preset anomaly detection thresholds and their signs are opposite, the current data point is determined to be an isolated anomaly. When the first difference exceeds the preset anomaly detection threshold while the second difference falls within the preset anomaly detection threshold, the current data point is determined to be an isolated anomaly. Within a defined threshold range, the current data point is identified as a trend abrupt change point. Then, for data points identified as isolated outliers, their values ​​are marked as invalid, and replaced with the linear interpolation result of the previous and next valid data points. For data points identified as trend abrupt changes, their values ​​are retained but marked as pending verification. For missing time periods caused by timestamp jumps, two valid data points before and after the missing period are detected. A linear extrapolation model is established based on the changing trends of these four valid data points to perform trend extrapolation for data points within the missing period. Finally, the sequence after outlier replacement and trend completion is output as the processed time-series rate value, and a data quality report is generated recording the outlier location and completion operation information. This is done because acoustic monitoring may be affected by environmental noise, equipment vibration, signal obstruction, and other factors, causing some data points to deviate from the true trend. Outlier removal eliminates the influence of these interfering data, and trend completion repairs data loss caused by communication interruptions or acquisition failures, ensuring the continuity and smoothness of subsequent curve fitting and improving the reliability and usability of the heat release rate curve.

[0085] Step S40: Perform continuous time-axis fitting on the processed time-series rate values ​​to obtain the heat release rate curve.

[0086] Specifically, firstly, the processed time-series rate values ​​are retrieved from the data buffer, the timestamps and corresponding heat release rate values ​​of each data point are identified, the time intervals between adjacent data points are calculated, and the uniformity of the time intervals is checked. If the time intervals are not uniform, the data is resampled and interpolated to ensure that the time intervals between data points are consistent. Secondly, a cubic spline interpolation method is used to smoothly connect the discrete data points of the processed time-series rate values. Boundary conditions are set as natural boundary conditions or fixed slope boundary conditions. The spline coefficients are solved to generate a continuously differentiable spline function expression, or a method is used... The polynomial fitting method fits discrete data points into a polynomial curve, optimizing the polynomial coefficients using the least squares method to minimize the fitting error. Then, at equally spaced time points, the spline function expression or polynomial curve is densely sampled at a preset multiple of the original data density, generating a densely sampled heat release rate curve data sequence. Finally, the heat release rate curve data sequence is structured and stored with time as the horizontal axis and heat release rate as the vertical axis, recording the curve's start time, end time, sampling interval, and total number of data points. The structured heat release rate curve is then output to the next processing module. This is done because the processed time-series rate values ​​are discrete sampling points; continuous fitting along the time axis generates a smooth and continuous curve shape, eliminating the step-like discontinuities caused by discrete sampling. This facilitates subsequent trend analysis, feature extraction, and visualization. Simultaneously, dense sampling improves the curve's temporal resolution, allowing for a more refined depiction of the details of fire evolution.

[0087] Step S50: Perform time axis transformation and amplitude normalization on the heat release rate curve to obtain standardized heat release rate data.

[0088] It should be noted that step S50 includes: obtaining the time start and end points and amplitude extreme values ​​of the heat release rate curve, and generating time amplitude reference parameters; performing a time axis linear stretching transformation on the heat release rate curve according to the time amplitude reference parameters to obtain a fixed-duration rate curve; performing linear normalization processing on the curve amplitude according to the amplitude extreme values ​​of the fixed-duration rate curve to obtain a normalized amplitude rate curve; and performing equally spaced discrete sampling on the normalized amplitude rate curve to obtain standardized heat release rate data.

[0089] Specifically, firstly, the start and end timestamps of the heat release rate curve are read from the data structure, and the time difference is calculated to obtain the original time span. Then, all data points in the heat release rate curve are traversed to identify the maximum and minimum heat release rate values. The start and end timestamps, the original time span, the maximum and minimum heat release rate values ​​are combined to form a time amplitude reference parameter. Secondly, based on the original time span and the preset standard time interval in the time amplitude reference parameter, a time stretching ratio coefficient is calculated. The start timestamp is subtracted from the timestamp of each data point in the heat release rate curve to obtain the relative time. The relative time is multiplied by the time stretching ratio coefficient to obtain the stretched standard time. The heat release rate values ​​are then linearly interpolated and resampled based on the stretched standard time. The process involves generating a fixed-duration rate curve, the total duration of which equals a preset standard time interval. Then, the maximum and minimum amplitude values ​​within this curve are identified, the amplitude span is calculated, and a normalization upper limit is set to a unit amplitude. The minimum amplitude value is subtracted from the heat release rate value of each data point in the fixed-duration rate curve to obtain an offset value. This offset value is then divided by the amplitude span and multiplied by the normalization upper limit to obtain a normalized amplitude rate curve. The amplitude range of this curve is mapped to the interval from zero to the normalization upper limit. Finally, an equal-interval sampling step size is calculated based on a preset number of sampling points. Starting from the starting point of the normalized amplitude rate curve, data points are extracted sequentially according to the equal-interval sampling step size, generating an equal-interval discrete sampling sequence. This sequence is then output as standardized heat release rate data. This approach is employed because the duration and intensity of fires vary across different monitoring scenarios. Linear stretching of the time axis unifies the time scale for easier horizontal comparison, linear normalization of the amplitude eliminates absolute intensity differences and highlights relative variation patterns, and equal-interval discrete sampling generates data in a uniform format for subsequent comparison and analysis with standard trend models.

[0090] Step S60: Construct a multi-scenario heat release rate trend model based on preset fire type parameters and ventilation condition parameters, and obtain standard trend datasets for fuel-controlled, ventilation-restricted, pulsating, and ventilation-induced flashover fires under different ventilation coefficients.

[0091] It should be noted that the preset fire type parameters are fundamental parameters pre-set to distinguish the combustion characteristics of different fires. These parameters correspond to the development patterns and heat release characteristics of different fires. Ventilation condition parameters are quantitative parameters characterizing the air supply at the fire scene. This parameter directly affects the degree of combustion completeness and is a crucial external condition determining the trend of heat release rate changes. The multi-scenario heat release rate trend model is a computational model constructed by combining multiple fire types and ventilation conditions. This model can simulate the change of fire heat release rate over time under different operating conditions and output standardized trend data.

[0092] Specifically, firstly, preset growth and decay coefficients for fuel-controlled fires are retrieved. A first baseline curve, showing a monotonically increasing trend followed by a stable decay, is generated based on a preset standard time interval. This first baseline curve is then coupled and modulated with different ventilation coefficients to obtain a first standard trend subset of fuel-controlled fires under different ventilation coefficients. Secondly, preset peak value limiting parameters for ventilation-limited fires are retrieved. The amplitude of the first baseline curve is truncated based on these parameters, and peak intensity is adjusted using the ventilation coefficient gradient to obtain a second standard trend subset of ventilation-limited fires under different ventilation coefficients. Finally, preset delay parameters for ventilation-induced flashover fires are retrieved. The system introduces time delays within a preset standard time interval based on parameters and abrupt change coefficients. An exponential growth segment is then introduced after the delay based on the abrupt change coefficients to obtain the third standard trend subset for ventilation-induced flashover fires. Next, the preset oscillation frequency and amplitude coefficients for pulsating fires are retrieved, and periodic sinusoidal fluctuations are superimposed on the baseline trend. The oscillation amplitude is adjusted according to the ventilation coefficient to obtain the fourth standard trend subset for pulsating fires under different ventilation coefficients. Finally, the first, second, third, and fourth standard trend subsets are summarized to form a standard trend dataset covering four fire types and multiple ventilation conditions. This approach is taken because different fire types have different combustion mechanisms and evolution patterns. Parametric modeling can generate standard heat release rate trends for various fire types under different ventilation conditions, providing a reference benchmark for subsequent fire type identification and trend comparison.

[0093] Step S70: Perform multi-dimensional visualization mapping and chart rendering based on standardized heat release rate data and standard trend dataset to obtain fire trend analysis results.

[0094] It should be noted that step S70 includes: First, converting the standardized heat release rate data into a visualized time-series curve to obtain the current monitored heat release rate visualization curve. Specifically, first, extracting the time series and corresponding heat release rate values ​​from the standardized heat release rate data, establishing a two-dimensional coordinate system with time as the horizontal axis and heat release rate as the vertical axis, and setting the display range, scale interval, and label format of the coordinate axes; second, plotting each data point in the standardized heat release rate data in chronological order on the two-dimensional coordinate system, connecting adjacent data points with polylines to form a time-series curve, setting the curve's color, line type, and line width attributes, and performing anti-aliasing rendering on the curve; then, adding chart auxiliary elements, including coordinate axis titles, legends, grid lines, and data labels, and setting the chart's background color and border style; finally, outputting the rendered time-series curve as a vector graphics format or bitmap format to obtain the current monitored heat release rate visualization curve. This is done because the visualized time-series curve can intuitively present the dynamic evolution process of the fire's heat release rate, making it easier for firefighters to quickly grasp the fire's development trend.

[0095] Next, standard heat release rate curves suitable for the current monitoring scenario are selected from the standard trend dataset according to preset rules, resulting in adapted standard curves. It should be noted that the preset rule is that the features of the standardized heat release rate data have the greatest similarity to the features of each heat release rate standard curve in the standard trend dataset. Specifically, firstly, feature extraction is performed on the standardized heat release rate data, calculating the peak heat release rate, peak time, average heat release rate, and decay rate as measured feature vectors; secondly, each heat release rate standard curve in the standard trend dataset is traversed, and the same feature extraction calculation is performed on each standard curve to obtain standard feature vectors; then, the Euclidean distance or cosine similarity between the measured feature vectors and each standard feature vector is calculated, and the standard curve with the highest similarity value is marked as a candidate curve for adaptation; finally, the candidate curve with the highest similarity value is output as the adapted standard curve. This is done because feature similarity matching can select the reference curve most similar to the current monitoring scenario from standard trend datasets of multiple types and scenarios, providing the optimal reference benchmark for subsequent fire type determination and trend comparison.

[0096] Subsequently, a multi-dimensional mapping was performed between the current monitored heat release rate visualization curve and the adapted standard curve to obtain a curve comparison visualization layer. It should be noted that the process involves extracting the first time-series data, the first peak value, and the first time-series slope of the current monitored heat release rate visualization curve, and simultaneously extracting the second time-series data, the second peak value, and the second time-series slope corresponding to the adaptation standard curve, thus obtaining the corresponding multi-dimensional feature parameters. Based on the first and second time-series data, the current monitored heat release rate visualization curve and the adaptation standard curve are synchronously calibrated to obtain a time-synchronized current monitored heat release rate visualization curve and a time-synchronized adaptation standard curve. These two time-synchronized curves are then mapped to the same visualization coordinate system to obtain the first curve and the second curve. The peak value positions and peak time nodes of the first and second curves are marked in the coordinate system, and the peak value difference and peak time difference are labeled to form feature annotation information. Differentiated line colors, line thicknesses, and timeline styles are set for the first and second curves, and legends are added to distinguish the two curves, generating a basic comparison layer. The feature annotation information is then overlaid onto the basic comparison layer, and the layer display clarity is optimized to obtain a curve comparison visualization layer.Specifically, firstly, the time series data is read from the data structure of the current monitored heat release rate visualization curve as the first time series data. The maximum amplitude value is identified by iterating through the heat release rate values ​​corresponding to the first time series data as the first amplitude peak value. The difference between adjacent data points is calculated and fitted to obtain the first time series slope. Simultaneously, the time series data is read from the data structure of the adapted standard curve as the second time series data. The maximum amplitude value is identified as the second amplitude peak value. The difference is calculated and fitted to obtain the second time series slope. The first time series data, the first amplitude peak value, the first time series slope, the second time series data, the second amplitude peak value, and the second time series slope are summarized into multi-dimensional feature parameters. Secondly, time axis alignment is performed based on the first and second time series data. The analysis involves identifying the first peak time index corresponding to the first amplitude peak and the second peak time index corresponding to the second amplitude peak, calculating the peak time difference, and then performing a translation transformation on either the first or second time-series data based on the peak time difference to align the peak positions of the two curves in time. The translated data is then interpolated and resampled to ensure consistent time axis scales, resulting in a time-synchronized visualization curve of the current monitored heat release rate and a time-synchronized adaptation standard curve. Next, a unified two-dimensional visualization coordinate system is established, with the horizontal axis representing standardized time and the vertical axis representing normalized heat release rate. The time-synchronized visualization curve of the current monitored heat release rate is mapped onto this coordinate system as the first curve, and the time-synchronized adaptation standard curve is mapped onto the coordinate system. The quasi-curve is mapped onto the coordinate system as the second curve, ensuring that the data range and display scale of the two curves are consistent. Then, the data points of the first and second curves are traversed in the coordinate system to locate the coordinate positions of the first and second amplitude peaks. Peak markers are drawn at these coordinate positions and numerical labels are added. The difference between the first and second amplitude peaks is calculated as the peak difference, and the difference between the first and second peak times is calculated as the peak time difference. Text boxes are added to the blank areas of the coordinate system or next to the legend to label the peak difference and peak time difference, forming feature annotation information. Finally, the first line color, first line thickness, and first timeline style are set for the first curve, and the second curve... Set the color, thickness, and style of the second line to visually distinguish it from the first curve. Add a legend box to the corner of the coordinate system. Draw a style sample of the first curve in the legend box and label it "Currently Monitored Curve". Draw a style sample of the second curve and label it "Adapted Standard Curve". Combine and render the coordinate system, the first curve, the second curve, and the legend into a base contrast layer. Finally, overlay and render the peak markers, numerical labels, and difference text boxes from the feature annotation information onto the base contrast layer. Adjust the hierarchy and transparency of each element to avoid occlusion. Perform anti-aliasing and color enhancement on the layer to optimize display clarity. Output the optimized layer as a curve contrast visualization layer to the display terminal.This is done because extracting multi-dimensional feature parameters enables quantitative comparison of two curves, time-series synchronization calibration eliminates time offset to make the comparison more accurate, unified coordinate system mapping ensures visual alignment, feature annotation information highlights key differences, differentiated visual styles and legends facilitate the distinction of curve attributes, layer overlay and optimization processing improve visualization quality, and the final generated curve comparison visualization layer can intuitively present the difference between the current monitored fire and the standard trend, assisting firefighters in determining the fire type and assessing the situation.

[0097] Then, the amplitude change, time-series slope, and peak characteristic data of the current monitored heat release rate visualization curve are extracted, and amplitude change charts, time-series slope charts, and peak characteristic charts are rendered respectively. Specifically, firstly, the heat release rate values ​​are read point by point from the data structure of the current monitored heat release rate visualization curve, the amplitude difference between adjacent data points is calculated to obtain the amplitude change sequence, a two-dimensional coordinate system is established with time as the horizontal axis and amplitude change as the vertical axis, and the data points in the amplitude change sequence are plotted and connected in time order, coordinate axis labels, grid lines, and titles are set, and an amplitude change chart is rendered. Secondly, the heat release rate values ​​are subjected to first-order difference operation to obtain the instantaneous rate of change, and the instantaneous rate of change is converted into a time-series slope sequence according to the time interval. A two-dimensional coordinate system is established with time as the horizontal axis and time-series slope as the vertical axis, a zero-value baseline is introduced as the boundary between rising and falling values, and the data points in the time-series slope sequence are plotted in time order. The process involves sequentially plotting points and connecting them with lines, marking positive and negative slope regions, and rendering a time-series slope chart. Then, iterating through the heat release rate values, all local maxima are identified as peak candidate points. These candidate points are compared with a preset peak threshold to select valid peaks. The amplitude values ​​and corresponding timestamps of each valid peak are recorded as peak feature data. A histogram coordinate system is established with the peak sequence number as the horizontal axis and the peak amplitude as the vertical axis. An amplitude histogram for each valid peak is drawn, with specific values ​​labeled above the bars and peak timestamps added as data labels. This process generates a peak feature chart. Finally, the amplitude variation chart, time-series slope chart, and peak feature chart are arranged and combined according to a preset layout, with a unified color scheme and font style, to generate a multi-dimensional feature chart set. This is done because the amplitude variation chart can intuitively present the fluctuation range and frequency of the heat release rate, the time-series slope chart can reflect the speed and turning trend of fire growth, and the peak feature chart can quantify the distribution of extreme points in fire energy release. The combination of these three charts depicts the fire evolution characteristics from different perspectives, providing multi-dimensional data support for a comprehensive understanding of the fire situation.

[0098] Finally, the curve comparison visualization layer, amplitude change chart, time series slope chart, and peak characteristic chart are integrated, and chart descriptions and trend analysis annotations are added to obtain complete fire trend analysis results. Specifically, firstly, the curve comparison visualization layer, amplitude change chart, time-series slope chart, and peak characteristic chart are retrieved. The size ratio and visual center of gravity of each chart are analyzed, and a hierarchical integrated layout scheme is designed. The curve comparison visualization layer is placed in the center of the layout as the core analysis area, and the amplitude change chart, time-series slope chart, and peak characteristic chart are arranged around the core analysis area as auxiliary analysis areas. A unified color mapping system and font specifications are established to ensure visual consistency. Secondly, chart description text is added to each chart area. Next to the curve comparison visualization layer, it is labeled "Comparison of the current monitoring curve with the adapted standard curve; the peak difference and peak time difference reflect the degree of deviation of the fire type." Next to the amplitude change chart, it is labeled "The fluctuation amplitude of the heat release rate reflects the combustion stability." Next to the time-series slope chart, it is labeled "The positive / negative slope and magnitude reflect the rate of fire growth / decline and the turning point." Next to the peak characteristic chart, it is labeled "The number and amplitude of peaks reflect the distribution characteristics of extreme energy release values." Then, based on the data of each chart, trend analysis conclusions are extracted and added to the curve... Trend analysis annotations are added to the comparative visualization layers. When the peak value of the current monitoring curve is higher than the adapted standard curve and the peak time is earlier, it is annotated "The fire is developing rapidly, and it is recommended to strengthen prevention and control." When the fluctuation frequency of the amplitude change chart exceeds the preset high-frequency threshold, it is annotated "The combustion is unstable and there is a risk of pulsation." When the time series slope chart is continuously negative in the later stage, it is annotated "The fire has entered the decline stage, and the rescue strategy can be adjusted appropriately." When the number of peaks in the peak characteristic chart exceeds the preset multi-peak threshold, it is annotated "Multiple signs of flashover, be alert to the risk of reignition." Then, a legend explanation area is added to the corner of the integrated layout to explain in detail the meaning of the line color, symbol mark and data unit of each chart. A data source description and generation timestamp are added at the bottom, and a fire trend analysis report title and current monitoring scene identifier are added at the top. Finally, the layers and text elements are rendered and composited, the hierarchical relationship and transparency are adjusted to avoid occlusion conflicts, resolution adaptation and clarity optimization are performed, and the rendered integrated chart is output as a complete fire trend analysis result to the display terminal and storage unit. This is done because the integrated layout enables the centralized presentation of multi-dimensional information, charts and graphs help to understand the physical meaning of each chart, trend analysis annotations directly provide judgment conclusions and lower the interpretation threshold, and complete fire trend analysis results provide fire commanders with full-chain information support from data display to decision-making suggestions.

[0099] This embodiment acquires a sequence of flame energy characteristic values ​​through an acoustic monitoring terminal, converts them into time-series heat release rate values ​​using a preset physical correlation model, and then performs anomaly processing, curve fitting, and standardization. Combined with a multi-scenario heat release rate trend model, it generates fire trend analysis results through multi-dimensional visualization mapping. This achieves non-contact, precise monitoring, solves the problem of incomparable data across different scenarios, intuitively presents fire trends, provides accurate data for emergency response, and reduces fire hazards.

[0100] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The method for generating acoustic fire trend results based on HRR, step S60, further includes steps S201 to S206:

[0101] Step S201: Retrieve preset fire type parameters.

[0102] It should be noted that the preset fire type parameters include the combustion characteristic parameters of each of the fuel-controlled, ventilation-restricted, pulsed, and ventilation-induced flashover fires.

[0103] Specifically, firstly, the system queries the storage path and access permissions of the fire type parameter table from the system configuration database, establishes a connection session with the parameter database, and sets the query timeout and error retry mechanism. Secondly, it sends a query command to the parameter database to retrieve the record entries corresponding to fuel-controlled fires, extracting combustion characteristic parameters for this type of fire, including the fuel mass loss rate coefficient, combustion efficiency factor, and maximum heat release rate limit. It also retrieves the record entries corresponding to ventilation-limited fires, extracting the ventilation coefficient influence factor, oxygen consumption rate, and peak limiting ratio parameters. Furthermore, it retrieves the record entries corresponding to pulsating fires, extracting the oscillation frequency baseline value, amplitude attenuation coefficient, and periodic stability threshold. Finally, it retrieves the record entries corresponding to ventilation-induced flashover fires, extracting the delay time characteristic value, flashover mutation index, and critical ventilation volume parameters. Then, it encapsulates the extracted fire combustion characteristic parameters into structured data objects according to their type, performs unit unification and dimensional verification on the numerical parameters, and marks missing or abnormal parameter values ​​as pending updates and triggers alarm notifications. Finally, it loads the structured data objects into the memory cache as preset fire type parameters, while simultaneously recording the parameter retrieval log, including retrieval time, parameter version, and validity period information.

[0104] Step S202: Set multiple sets of different ventilation coefficient parameters.

[0105] It should be noted that the ventilation coefficient parameter covers three ventilation conditions: low ventilation, medium ventilation, and high ventilation.

[0106] Specifically, the system retrieves the definition range and grading standards of ventilation coefficient parameters from the system configuration database to identify the numerical interval boundaries corresponding to low, medium, and high ventilation conditions. Next, within the low ventilation interval, a first set of ventilation coefficient parameters is selected at equal intervals or in an exponentially decreasing manner; within the medium ventilation interval, a second set is selected at equal intervals; and within the high ventilation interval, a third set is selected at equal intervals or in an exponentially increasing manner. This ensures that the three sets of parameters cover a complete spectrum of ventilation conditions and that there is reasonable overlap between the sets. Then, the selected sets of ventilation coefficient parameters are numbered and labeled, and the ventilation condition category and physical meaning of each set are recorded. The parameter values ​​are validated to ensure they are within a reasonable physical range. Finally, the validated sets of ventilation coefficient parameters are encapsulated into a ventilation coefficient parameter set and loaded into the memory cache for subsequent trend model construction. This is done because ventilation conditions are a key environmental factor affecting fire development. Setting multiple sets of different ventilation coefficients can simulate various ventilation scenarios, from restricted to abundant, providing parameter input for generating a standard trend dataset covering different ventilation conditions.

[0107] Step S203: Based on the principles of fire combustion dynamics and combined with preset fire type parameters and ventilation coefficient parameters of each group, construct a multi-scenario heat release rate trend model.

[0108] It should be noted that step S203 includes: obtaining standard experimental results and verification data; introducing the fire combustion rate equation and determining the basic combustion model for various types of fires by combining preset fire type parameters; substituting different ventilation coefficient parameters into the basic combustion model, correcting the oxygen supply coefficient and combustion efficiency parameters in the model, and obtaining a single-scenario heat release rate model under different ventilation conditions; adding a heat radiation attenuation factor based on the single-scenario heat release rate model to compensate for the influence of ventilation conditions on fire heat release, and obtaining the corresponding single-scenario optimized model; inputting the verification data into the single-scenario optimized model to obtain simulation results; adjusting the model parameters of the single-scenario heat release rate model through an iterative optimization algorithm until the deviation between the simulation results and the standard experimental results is less than a preset deviation threshold, integrating the model parameters of all single-scenario optimized models, and constructing a complete multi-scenario heat release rate trend model.

[0109] It should be noted that the standard experimental results are data related to the actual heat release rate obtained through standardized fire simulation experiments. These results have undergone rigorous experimental design and multiple repeated verifications, accurately reflecting the true variation patterns of heat release rate under different fire scenarios. Validation data are dedicated data used to verify the accuracy of model calculations. This data is consistent with the standard experimental results but independent of each other, preventing model overfitting. The fire combustion rate equation is a mathematical equation describing the relationship between the rate of combustible consumption and heat release during fire combustion. This equation is constructed based on the principles of fire combustion dynamics and can quantify the intrinsic correlation between combustion rate and heat release rate. The basic combustion model is a heat release rate calculation model constructed only incorporating fire type parameters. This model can reflect the inherent combustion characteristics of different types of fires and clarify the basic trends in heat release rate for various fire types. The oxygen supply coefficient is a quantitative parameter characterizing the sufficiency of oxygen supply at a fire scene. This parameter is directly related to ventilation conditions; the more abundant the oxygen supply, the larger the coefficient, and vice versa, directly affecting the completeness of the combustion reaction. The combustion efficiency parameter is an indicator describing the completeness of combustible combustion. This parameter reflects the proportion of combustible material converted into heat; the more complete the combustion, the higher the efficiency, and the higher the heat release rate. The single-scenario heat release rate model is a specialized computational model built for a specific fire type and a particular ventilation condition. This model can accurately simulate the temporal variation of the heat release rate under a single operating condition. The heat radiation attenuation factor is a correction parameter used to compensate for the impact of ventilation conditions on heat radiation propagation. This factor quantifies the degree of heat radiation loss caused by changes in ventilation volume, making the model's calculation results more closely resemble the actual heat release situation in a real fire.

[0110] Specifically, firstly, standard experimental results for fuel-controlled, ventilation-restricted, pulsating, and ventilation-induced flashover fires are retrieved from the standard fire experiment database. These results include measured heat release rate curves, peak data, and temporal characteristics. Simultaneously, independently collected validation data is obtained from the validation dataset interface. The standard experimental results and validation data are then stored in the model training buffer according to fire type. Secondly, a fire combustion rate equation is introduced as the basic framework. Based on the fuel mass loss rate coefficient and combustion efficiency factor in the preset fire type parameters, the basic combustion model structure for each type of fire is determined, and the initial parameter values ​​and boundary constraints of the model are set. Then, multiple sets of ventilation coefficient parameters are substituted into the basic combustion model one by one. The oxygen supply coefficient in the model is corrected to be proportional to the ventilation coefficient, and the combustion efficiency parameter is adjusted to reflect the influence of ventilation conditions on the degree of complete combustion, resulting in single-scenario heat release rate models under different ventilation conditions. Subsequently, a single-scenario heat release rate model is developed. A thermal radiation attenuation factor is added to the heat release rate model. The proportion of thermal radiation loss from the flame surface is calculated based on the ventilation coefficient to compensate for the increased heat dissipation caused by enhanced ventilation on the heat release rate, resulting in a single-scenario optimized model. Then, validation data is input into the single-scenario optimized model for forward simulation calculations to obtain simulation results. The root mean square error or relative deviation between the simulation results and the standard experimental results is calculated as a deviation index. Next, iterative optimization algorithms such as gradient descent or genetic algorithms are used to adjust the fuel mass loss rate coefficient, combustion efficiency factor, and thermal radiation attenuation factor of the single-scenario heat release rate model. The forward simulation and deviation calculation process is repeated until the deviation index is less than a preset deviation threshold. Finally, the model parameters of all converged single-scenario optimized models are integrated and organized into a matrix according to fire type and ventilation conditions to construct a complete multi-scenario heat release rate trend model covering four types of fires and multiple ventilation conditions. The model parameter file and applicable scope description are output. This is done because standard experimental results and validation data provide a real benchmark for model construction, the fire combustion rate equation provides a theoretical framework, the substitution of ventilation coefficients and parameter corrections realize the quantitative coupling of environmental conditions, the thermal radiation attenuation factor compensates for the integrity of the physical mechanism, iterative optimization ensures that the model accuracy meets the requirements of engineering applications, and the finally constructed multi-scenario trend model can provide a reliable standard reference for fire trend prediction and type identification.

[0111] Step S204: Using a multi-scenario heat release rate trend model, simulate and generate standard curves of heat release rates for various types of fires under different ventilation coefficients.

[0112] Specifically, firstly, the model parameter matrix for fuel-controlled fires is retrieved from the multi-scenario heat release rate trend model. The standard time interval is set to 0 to 300 seconds, and the time step is set to 1 second. The three ventilation coefficients (low, medium, and high ventilation) are substituted into the model to calculate the heat release rate values ​​at each time point, generating three standard heat release rate curves for fuel-controlled fires under low, medium, and high ventilation conditions. Secondly, the model parameter matrix for ventilation-limited fires is retrieved from the model. Using the same standard time interval and time step, the three ventilation coefficients are substituted into the model to calculate the heat release rate values ​​at each time point, generating three standard heat release rate curves for ventilation-limited fires under three ventilation conditions. These curves exhibit peak-limited characteristics, with the peak value increasing as the ventilation coefficient increases. Then, the model parameter matrix for pulsating fires is retrieved from the model. The model first extracts a parameter matrix, substitutes three ventilation coefficients into the model, superimposes periodic oscillation components, and calculates the heat release rate at each time point, generating three standard heat release rate curves for pulsating fires under three ventilation conditions. These curves exhibit obvious periodic fluctuation characteristics. Next, the model parameter matrix for ventilation-induced flashover fires is retrieved from the model, and the three ventilation coefficients are substituted into the model. A sudden increase segment is introduced after a delay time, and the heat release rate at each time point is calculated, generating three standard heat release rate curves for ventilation-induced flashover fires under three ventilation conditions. These curves exhibit a sharp increase after the delay. Finally, the generated 12 standard heat release rate curves are classified and labeled according to fire type and ventilation conditions, with unified time axes and amplitude ranges, smoothed, and noise suppressed. The processed standard curves are then packaged into a standard trend dataset for output. This approach is taken because forward numerical simulation using a multi-scenario trend model can systematically generate standard heat release rate curves covering four types of fires and three ventilation conditions. These standard curves serve as reference benchmarks for subsequent fire type identification and trend comparison, providing quantifiable comparative evidence for fire trend analysis.

[0113] Step S205: Organize all heat release rate standard curves according to fire type and ventilation coefficient to form an initial trend dataset.

[0114] It should be noted that step S205 includes: extracting the fire type identifier and ventilation coefficient identifier corresponding to all generated heat release rate standard curves; dividing all heat release rate standard curves into four categories based on the fire type identifier as the primary classification dimension: fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover; within each category, sorting the curves according to the ventilation coefficient identifier in ascending order to form subgroups; adding unique classification labels to each category and subgroup, labeling the corresponding fire type and ventilation coefficient, to obtain subset datasets; and integrating all subset datasets to form the initial trend dataset.

[0115] It's important to understand that the primary classification dimension is the first-level criterion used when classifying data. Here, fire type is used as the first-level classification standard to broadly categorize all standard curves. The secondary classification dimension is a further subdivision based on the primary classification. Here, ventilation coefficient is used as the second-level classification standard to achieve a more refined distinction between different ventilation condition curves under the same fire type.

[0116] Specifically, firstly, all generated heat release rate standard curves are traversed, and the fire type identifier field and ventilation coefficient identifier field are extracted from the curve metadata to establish a mapping table between curve identifiers and classification attributes. Secondly, using the fire type identifier as the primary classification dimension, the records in the mapping table are grouped according to four values: fuel-controlled, ventilation-limiting, pulsating, and ventilation-induced flashover. The corresponding heat release rate standard curves are then divided into four curve groups: the first curve group, the second curve group, the third curve group, and the fourth curve group. Then, within each curve group, using the ventilation coefficient identifier as the secondary classification dimension, the curves within the group are arranged in ascending order of ventilation coefficient values, forming low ventilation subgroups, medium ventilation subgroups, and high ventilation subgroups. The system first divides the data into three subgroups. Then, a unique primary classification label is generated for each curve group, formatted as "fire type code - group number". A unique secondary classification label is also generated for each subgroup, formatted as "fire type code - ventilation coefficient code - subgroup number". The label attributes include the corresponding fire type name and ventilation coefficient value. Next, the heat release rate standard curves and their secondary classification labels within each subgroup are encapsulated into subsets, recording the number of curves, time range, and amplitude characteristics within each subset. Finally, all subsets are hierarchically integrated according to the primary classification dimension, establishing a dataset index structure to record the correspondence between each level of classification label and the subsets. The integrated data is then output as the initial trend dataset to the storage unit. This approach is used because organizing the standard curves through secondary classification dimensions enables rapid retrieval and location of fire types and ventilation conditions. Unique classification labels ensure the traceability of each standard curve, and the hierarchical dataset structure facilitates subsequent querying, retrieval, and comparative analysis, providing a standardized data organization foundation for the fire trend analysis system.

[0117] Step S206: Validate the initial trend dataset, remove standard curves whose simulation deviation exceeds the preset range, and obtain the standard trend dataset.

[0118] Specifically, firstly, standard heat release rate curves are retrieved one by one from the initial trend dataset to identify the fire type and ventilation coefficient corresponding to each curve. Measured heat release rate curves under the same fire type and ventilation conditions are retrieved from the standard experimental database as validation benchmarks. Secondly, the point-by-point deviation between the standard curves and the validation benchmark curves is calculated. The root mean square error or mean absolute percentage error is used as a comprehensive deviation index. The comprehensive deviation index is compared with a preset deviation threshold. If the comprehensive deviation index is greater than the preset deviation threshold, the standard curve is determined to be an abnormal curve. If the comprehensive deviation index is less than or equal to the preset deviation threshold, the standard curve is determined to be a normal curve. Then, the standard curves determined to be abnormal are removed from the initial trend dataset. The reason for removal and the deviation value are recorded. The missing positions after removal are marked. A validation pass mark is added to the standard curves determined to be normal. Next, a consistency check is performed on the validated standard curves to ensure the complete coverage of various fire types and ventilation conditions. If a certain type of curve is detected to be missing, the model regeneration process is triggered. Finally, all the validated and consistent standard curves are repackaged, the dataset index structure and classification labels are updated, and the processed dataset is output as the standard trend dataset. This is done because the initial trend dataset is generated by model simulation and may contain deviations from real fire experiments. By verifying and removing outlier curves, the accuracy and reliability of the standard trend dataset can be ensured, providing a reliable reference benchmark for subsequent fire type identification and trend comparison.

[0119] This embodiment retrieves combustion characteristic parameters for four types of fires, sets multiple sets of ventilation coefficients (low, medium, and high), and constructs a multi-scenario heat release rate trend model based on fire combustion dynamics principles. It simulates and generates corresponding standard curves, which are then categorized and organized by type and coefficient to form an initial dataset. After verification, curves with excessive deviations are removed to obtain a standard trend dataset. This approach allows for the rapid establishment of multi-condition benchmark curves, with well-organized classifications for easy retrieval. Verified data exhibits higher accuracy, providing a reliable reference for subsequent monitoring and comparison, and improving the accuracy and stability of fire trend judgment.

[0120] Based on the first embodiment of this application, this application also provides an acoustic fire trend result generation device based on HRR, please refer to... Figure 3 The device includes:

[0121] The receiving module 10 is used to receive a multi-frame continuous flame energy characteristic value sequence of the current monitoring scene uploaded by the acoustic monitoring terminal.

[0122] The conversion module 20 is used to convert the flame energy characteristic value sequence into a time-series heat release rate value according to a preset physical correlation model, wherein the preset physical correlation model is a model that integrates ultrasonic wave propagation delay and fire temperature distribution.

[0123] The processing module 30 is used to perform outlier removal and trend completion processing on the time-series heat release rate values ​​to obtain the processed time-series rate values.

[0124] The curve simulation module 40 is used to continuously fit the processed time-series rate values ​​to obtain the heat release rate curve.

[0125] The normalization module 50 is used to perform time axis transformation and amplitude normalization on the heat release rate curve to obtain standardized heat release rate data.

[0126] Module 60 is used to construct a multi-scenario heat release rate trend model based on preset fire type parameters and ventilation condition parameters, and to obtain standard trend datasets for fuel-controlled, ventilation-restricted, pulsating, and ventilation-induced flashover fires under different ventilation coefficients.

[0127] Results module 70 is used to perform multi-dimensional visualization mapping and chart rendering based on standardized heat release rate data and standard trend datasets to obtain fire trend analysis results.

[0128] The HRR-based acoustic fire trend result generation device provided in this application, employing the HRR-based acoustic fire trend result generation method in the above embodiments, can solve the technical problem of how to achieve accurate HRR quantification and generate accurate fire trend analysis results based on acoustic perception. Compared with the prior art, the beneficial effects of the HRR-based acoustic fire trend result generation device provided in this application are the same as those of the HRR-based acoustic fire trend result generation method provided in the above embodiments, and other technical features in the HRR-based acoustic fire trend result generation device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0129] This application provides an acoustic fire trend result generation device based on HRR. The HRR-based acoustic fire trend result generation device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the HRR-based acoustic fire trend result generation method in the above embodiment 1.

[0130] The following is for reference. Figure 4The diagram illustrates a structural schematic of an acoustic fire trend result generation device based on HRR suitable for implementing embodiments of this application. The HRR-based acoustic fire trend result generation device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The HRR-based acoustic fire trend result generation device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0131] like Figure 4 As shown, the HRR-based acoustic fire trend result generation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the HRR-based acoustic fire trend result generation device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the HRR-based acoustic fire trend result generation device to communicate wirelessly or wiredly with other devices to exchange data. Although various HRR-based acoustic fire trend result generation devices are shown in the figures, it should be understood that implementation or possession of all of them is not required. More or fewer may be implemented alternatively.

[0132] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0133] The HRR-based acoustic fire trend result generation device provided in this application, employing the HRR-based acoustic fire trend result generation method described in the above embodiments, solves the technical problem of how to achieve accurate HRR quantification and generate accurate fire trend analysis results based on acoustic perception. Compared with the prior art, the beneficial effects of the HRR-based acoustic fire trend result generation device provided in this application are the same as those of the HRR-based acoustic fire trend result generation method provided in the above embodiments, and other technical features in this HRR-based acoustic fire trend result generation device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0134] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0135] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0136] This application provides a computer-readable medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the HRR-based acoustic fire trend result generation method in the above embodiments.

[0137] The computer-readable medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any combination thereof. More specific examples of computer-readable media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be executed by instructions, used by a device, or used in conjunction with it. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0138] The aforementioned computer-readable medium may be included in an HRR-based acoustic fire trend result generation device; or it may exist independently and not assembled into an HRR-based acoustic fire trend result generation device.

[0139] The aforementioned computer-readable medium carries one or more programs that, when executed by an HRR-based acoustic fire trend result generation device, enable the HRR-based acoustic fire trend result generation device to write computer program code for performing the operations of this application in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this application. In this regard, all blocks in the flowcharts or block diagrams may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that all blocks in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using dedicated hardware-based implementations that perform the specified functions or operations, or using a combination of dedicated hardware and computer instructions.

[0141] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0142] The readable medium provided in this application is a computer-readable medium, which stores computer-readable program instructions (i.e., a computer program) for executing the above-described HRR-based acoustic fire trend result generation method. This solves the technical problem of how to achieve accurate HRR quantification and generate accurate fire trend analysis results based on acoustic sensing. Compared with the prior art, the beneficial effects of the computer-readable medium provided in this application are the same as those of the HRR-based acoustic fire trend result generation method provided in the above embodiments, and will not be repeated here.

[0143] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the HRR-based acoustic fire trend result generation method described above.

[0144] The computer program product provided in this application can solve the technical problem of how to achieve accurate HRR quantification and generate accurate fire trend analysis results based on acoustic sensing. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the HRR-based acoustic fire trend result generation method provided in the above embodiments, and will not be repeated here.

[0145] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for generating acoustic fire trend results based on HRR, characterized in that, The method includes: The system receives a multi-frame continuous sequence of flame energy feature values ​​for the current monitoring scene uploaded by an acoustic monitoring terminal. The flame energy feature value sequence is obtained by the acoustic monitoring terminal by transmitting ultrasonic waves to the monitoring area, receiving flame reflected echoes, and extracting energy features. The flame energy characteristic value sequence is converted into a time-series heat release rate value according to a preset physical correlation model, wherein the preset physical correlation model is a model that integrates ultrasonic wave propagation delay and fire temperature distribution. The time-series heat release rate values ​​are processed by outlier removal and trend completion to obtain the processed time-series rate values. The processed time-series rate values ​​are continuously fitted along the time axis to obtain the heat release rate curve. The heat release rate curve is subjected to time axis transformation and amplitude normalization to obtain standardized heat release rate data; Based on preset fire type parameters and ventilation condition parameters, a multi-scenario heat release rate trend model was constructed, and standard trend datasets of fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover fires under different ventilation coefficients were obtained. Based on the standardized heat release rate data and the standard trend dataset, multi-dimensional visualization mapping and chart rendering are performed to obtain fire trend analysis results. The steps of constructing a multi-scenario heat release rate trend model based on preset fire type parameters and ventilation condition parameters to obtain standard trend datasets for fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover fires under different ventilation coefficients include: Retrieve preset fire type parameters, wherein the preset fire type parameters include the combustion characteristic parameters of each of fuel-controlled, ventilation-restricted, pulsed, and ventilation-induced flashover fires; Multiple sets of different ventilation coefficient parameters are set, which cover three ventilation conditions: low ventilation, medium ventilation, and high ventilation. Based on the principles of fire combustion dynamics, combined with the preset fire type parameters and ventilation coefficient parameters of each group, a multi-scenario heat release rate trend model is constructed. The multi-scenario heat release rate trend model is used to simulate and generate standard curves of heat release rate for various types of fires under different ventilation coefficients. All the heat release rate standard curves were categorized and organized according to fire type and ventilation coefficient to form an initial trend dataset; The initial trend dataset is validated, and standard curves whose simulated deviations exceed a preset range are removed to obtain a standard trend dataset.

2. The method as described in claim 1, characterized in that, The step of performing time axis transformation and amplitude normalization on the heat release rate curve to obtain standardized heat release rate data includes: Obtain the start and end points of time and the extreme values ​​of amplitude of the heat release rate curve, and generate time amplitude reference parameters; Based on the time amplitude reference parameter, the heat release rate curve is subjected to a time axis linear stretching transformation to obtain a fixed duration rate curve; Based on the extreme values ​​of the amplitude of the fixed-duration rate curve, the amplitude of the curve is linearly normalized to obtain the normalized amplitude rate curve. The normalized amplitude rate curve is sampled at equal intervals to obtain standardized heat release rate data.

3. The method as described in claim 1, characterized in that, The steps for constructing a multi-scenario heat release rate trend model based on the principles of fire combustion dynamics, combined with the preset fire type parameters and various ventilation coefficient parameters, include: Obtain standard experimental results and validation data; A fire combustion rate equation is introduced, and the basic combustion model for various types of fires is determined by combining preset fire type parameters. By substituting different ventilation coefficient parameters into the basic combustion model and correcting the oxygen supply coefficient and combustion efficiency parameters in the model, a single-scenario heat release rate model under different ventilation conditions is obtained. Based on the single-scenario heat release rate model, a heat radiation attenuation factor is added to compensate for the influence of ventilation conditions on fire heat release, and the corresponding single-scenario optimization model is obtained. The verification data is input into the single-scenario optimization model to obtain the simulation results; The model parameters of the single-scenario heat release rate model are adjusted by an iterative optimization algorithm until the deviation between the simulation results and the standard experimental results is less than a preset deviation threshold. The model parameters of all the single-scenario optimization models are then integrated to construct a complete multi-scenario heat release rate trend model.

4. The method as described in claim 1, characterized in that, The step of classifying and organizing all the heat release rate standard curves according to fire type and ventilation coefficient to form an initial trend dataset includes: Extract the fire type identifier and ventilation coefficient identifier corresponding to all generated heat release rate standard curves; Using the fire type identifier as the primary classification dimension, all heat release rate standard curves are divided into four categories: fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover. Within each group of curves, the ventilation coefficient is used as the secondary classification dimension, and the curves are sorted and arranged in ascending order of ventilation coefficient to form a classification subgroup. Add a unique classification label to each group of curves and each subgroup of classification, and label the corresponding fire type and ventilation coefficient to obtain a subset of data; All the aforementioned subsets are integrated to form the initial trend dataset.

5. The method as described in claim 1, characterized in that, The steps for performing multi-dimensional visualization mapping and chart rendering based on the standardized heat release rate data and the standard trend dataset to obtain fire trend analysis results include: The standardized heat release rate data is converted into a visual time-series curve to obtain the current monitored heat release rate visualization curve. From the standard trend dataset, heat release rate standard curves that are compatible with the current monitoring scenario are selected according to preset rules to obtain the adapted standard curves. The preset rule is that the features of the standardized heat release rate data have the greatest similarity to the features of each heat release rate standard curve in the standard trend dataset. A multi-dimensional mapping is performed between the current monitored heat release rate visualization curve and the adapted standard curve to obtain a curve comparison visualization layer; Extract the amplitude change, time-series slope, and peak characteristic data of the current monitored heat release rate visualization curve, and render and generate amplitude change chart, time-series slope chart, and peak characteristic chart respectively; By integrating the curve comparison visualization layer, amplitude change chart, time series slope chart, and peak characteristic chart, and adding chart descriptions and trend analysis annotations, a complete fire trend analysis result is obtained.

6. The method as described in claim 5, characterized in that, The step of performing multi-dimensional mapping between the current monitored heat release rate visualization curve and the adapted standard curve to obtain a curve comparison visualization layer includes: Extract the first time-series data, the first amplitude peak value, and the first time-series slope of the current monitored heat release rate visualization curve, and simultaneously extract the second time-series data, the second amplitude peak value, and the second time-series slope corresponding to the adaptation standard curve to obtain the corresponding multi-dimensional feature parameters; Based on the first time series data and the second time series data, the current monitored heat release rate visualization curve and the adaptation standard curve are synchronously calibrated to obtain the current monitored heat release rate visualization curve and the time series synchronized adaptation standard curve. The current monitored heat release rate visualization curve after time synchronization and the adapted standard curve after time synchronization are mapped to the same visualization coordinate system to obtain the first curve and the second curve; Mark the peak amplitude positions and peak time nodes of the first and second curves in the coordinate system, and label the peak difference and peak time difference to form feature labeling information; Set different line colors, line thicknesses, and timeline styles for the first and second curves, add legends to distinguish the two curves, and generate a basic contrast layer. The feature annotation information is superimposed on the basic comparison layer to optimize the layer display clarity and obtain a curve comparison visualization layer.

7. A device for generating acoustic fire trend results based on HRR, characterized in that, The apparatus is applied to the HRR-based acoustic fire trend result generation method as described in any one of claims 1-6, and the apparatus comprises: The receiving module is used to receive a multi-frame continuous flame energy characteristic value sequence of the current monitoring scene uploaded by the acoustic monitoring terminal; The conversion module is used to convert the flame energy characteristic value sequence into a time-series heat release rate value according to a preset physical correlation model, wherein the preset physical correlation model is a model that integrates ultrasonic wave propagation delay and fire temperature distribution. The processing module is used to perform outlier removal and trend completion processing on the time-series heat release rate values ​​to obtain the processed time-series rate values. The curve simulation module is used to continuously fit the processed time-series rate values ​​to the time axis to obtain the heat release rate curve. The normalization module is used to perform time axis transformation and amplitude normalization on the heat release rate curve to obtain standardized heat release rate data. The module is used to build a multi-scenario heat release rate trend model based on preset fire type parameters and ventilation condition parameters, and to obtain standard trend datasets for fuel-controlled, ventilation-limited, pulsating, and ventilation-induced flashover fires under different ventilation coefficients. The results module is used to perform multi-dimensional visualization mapping and chart rendering based on the standardized heat release rate data and the standard trend dataset to obtain fire trend analysis results.

8. A device for generating acoustic fire trend results based on HRR, characterized in that, The device includes: a memory, a processor, and an HRR-based acoustic fire trend result generation program stored on the memory and running on the processor, the HRR-based acoustic fire trend result generation program being configured to implement the steps of the HRR-based acoustic fire trend result generation method as described in any one of claims 1-6.

9. A storage medium, characterized in that, The storage medium stores an acoustic fire trend result generation program based on HRR, which, when executed by a processor, implements the steps of the acoustic fire trend result generation method based on HRR as described in any one of claims 1-6.

Images