Multi-data fusion fire-fighting early warning method and platform

Abstract

The invention provides a multi-data fusion fire-fighting early warning method and platform, and relates to the technical field of fire fighting, and the method comprises the steps: collecting a multi-dimensional environment data set of a target region; performing noise filtering on the multi-dimensional environment data set to obtain a multi-dimensional environment de-noised data set; comprehensively analyzing the plurality of data sources based on the multi-dimensional environment de-noised data set to generate fire-fighting comprehensive data, and fusing the multi-dimensional environment de-noised data set to obtain a multi-dimensional environment fused data set; building a fire risk model according to the fire-fighting comprehensive data, synchronizing the multi-dimensional environment fusion data set to the fire risk model for evaluation according to a plurality of data sources, and obtaining a fire risk level of the target area; and generating a fire-fighting early warning instruction based on the fire risk level, and sending the instruction to the remote control terminal. According to the method, the technical problem that a traditional fire early warning method is single in monitoring means and is easily interfered by environmental factors to cause false alarm or missing alarm is solved, and the accuracy and response speed of fire early warning are remarkably improved.

Description

Technical Field

[0001] The present application relates to the field of fire protection technology, and specifically to a fire warning method and platform based on multi-data fusion. Background Art

[0002] Fire warning systems play a vital role in the field of public safety. Their main function is to detect signs of fire early so that timely measures can be taken to reduce the losses caused by fire. Traditional fire warning methods usually rely on a single sensor device, such as a smoke detector or a heat detector. These devices can issue an alarm in time when they detect smoke or abnormal temperature in the early stage of a fire, helping people to evacuate quickly and take countermeasures. However, the reliance on a single data source makes the existing warning system likely to have false alarms or missed alarms due to factors such as environmental interference when facing a complex environment. For example, a smoke detector may be interfered by kitchen smoke, while a heat detector may trigger an alarm due to direct sunlight or other non-fire factors. Secondly, most traditional warning methods are simple threshold judgments, lacking the ability to comprehensively monitor and analyze complex environmental conditions, unable to comprehensively assess fire risks, and unable to adjust the warning level in a timely and accurate manner according to actual conditions. This limitation results in firefighters being unable to obtain accurate and real-time environmental information when facing fire risks, thus affecting their judgment and decision-making. Summary of the invention

[0003] This application provides a multi-data fusion fire warning method and platform, which solves the technical problems of traditional fire warning methods that have a single monitoring method and are easily interfered by environmental factors, resulting in false alarms or missed alarms, and achieves the technical effect of significantly improving the accuracy and response speed of fire warnings.

[0004] In view of the above problems, on the one hand, the present application provides a fire warning method of multi-data fusion, which includes: collecting environmental data of a target area through multiple data sensing devices to obtain a multidimensional environmental data set; filtering the multidimensional environmental data set in combination with the fire equipment layout data of the target area to obtain a multidimensional environmental denoised data set; comprehensively analyzing multiple data sources based on the multidimensional environmental denoised data set to generate fire comprehensive data, and fusing the multidimensional environmental denoised data set according to the fire comprehensive data to obtain a multidimensional environmental fused data set; training and learning based on the fire comprehensive data to construct a fire risk model, and synchronizing the multidimensional environmental fused data set to the fire risk model for evaluation according to the multiple data sources to obtain the fire risk level of the target area; making a judgment based on the fire risk level, generating a fire warning instruction, and sending the fire warning instruction to a remote control terminal for automatic warning of the target area.

[0005] On the other hand, the present application also provides a multi-data fusion fire warning platform, which includes: an environmental data acquisition module, which is used to collect the environment of the target area through multiple data sensing devices to obtain a multidimensional environmental data set; a data denoising module, which is used to filter the noise of the multidimensional environmental data set in combination with the fire equipment layout data of the target area to obtain a multidimensional environmental denoised data set; a data fusion module, which is used to perform a comprehensive analysis of multiple data sources based on the multidimensional environmental denoised data set to generate fire comprehensive data, and fuse the multidimensional environmental denoised data set according to the fire comprehensive data to obtain a multidimensional environmental fusion data set; a fire risk assessment module, which is used to train and learn according to the fire comprehensive data to construct a fire risk model, and synchronize the multidimensional environmental fusion data set to the fire risk model for evaluation according to the multiple data sources to obtain the fire risk level of the target area; a fire warning module, which is used to make a judgment based on the fire risk level, generate a fire warning instruction, and send the fire warning instruction to the remote control terminal for automatic warning of the target area.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The target area is collected by multiple data sensing devices to obtain a multidimensional environmental data set. The multidimensional environmental data set covers various information related to the fire risk in the target area, such as temperature, smoke concentration, humidity and other environmental parameters, providing comprehensive raw data for subsequent analysis. The multidimensional environmental data set is combined with the fire equipment layout data of the target area to remove noise and obtain a multidimensional environmental denoising data set. This step improves the quality and accuracy of the data by cleaning up irrelevant or interfering data, making subsequent analysis more reliable. Based on the multidimensional environmental denoising data set, a comprehensive analysis of multiple data sources is performed to generate fire comprehensive data, and the multidimensional environmental denoising data set is fused according to the fire comprehensive data to obtain a multidimensional environmental fusion data set. This step integrates information from different sources to make the data more comprehensive and representative, forming a comprehensive environmental view, thereby more accurately reflecting the fire risk status. Training and learning are performed based on the fire comprehensive data to build a fire risk model. According to the multiple data sources, the multidimensional environmental fusion data set is synchronized to the fire risk model for evaluation, and the fire risk level of the target area is quantified, providing a key basis for subsequent early warning decisions. This step can dynamically adapt to different environmental changes and optimize the accuracy of fire risk prediction through machine learning. Based on the fire risk level, a fire warning instruction is generated, and the fire warning instruction is sent to the remote control terminal for automatic warning of the target area. This step realizes a rapid response mechanism to ensure that relevant personnel can receive fire risk information in time when a fire occurs and take corresponding prevention or rescue measures.

[0008] In summary, this application collects environmental data through multi-data sensing equipment, builds a fire risk model for evaluation after noise filtering, comprehensive analysis and data fusion, and finally generates warning instructions to realize automatic fire warning. This multi-data fusion method overcomes the limitations of traditional single data warning, comprehensively considers multiple environmental factors and eliminates data noise interference, making fire risk assessment more accurate. At the same time, automated warning ensures timely notification of relevant personnel, effectively improving the accuracy, timeliness and reliability of fire warning, thereby improving the effectiveness of the entire fire warning system and ensuring fire safety in the target area.

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

[0010] Figure 1 A flowchart of a multi-data fusion fire warning method provided in an embodiment of the present application.

[0011] Figure 2 A schematic diagram of a process for obtaining a multi-dimensional environmental denoised data set in a multi-data fusion fire warning method provided in an embodiment of the present application.

[0012] Figure 3 A schematic diagram of the process of generating comprehensive fire data in the multi-data fusion fire warning method provided in an embodiment of the present application.

[0013] Figure 4 A schematic diagram of the structure of a multi-data fusion fire warning platform provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: environmental data acquisition module 10 , data denoising module 20 , data fusion module 30 , fire risk assessment module 40 , fire warning module 50 . DETAILED DESCRIPTION

[0015] The embodiment of the present application provides a multi-data fusion fire warning method and platform, which collects environmental data through multi-data sensing equipment, builds a fire risk model for evaluation after noise filtering, comprehensive analysis and data fusion, and finally generates warning instructions to realize automatic fire warning. This application solves the technical problem that the traditional fire warning method has a single monitoring means and is easily interfered by environmental factors, resulting in false alarms or missed alarms, and achieves the technical effect of significantly improving the accuracy and response speed of fire warnings.

[0016] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a multi-data fusion fire warning method, the method comprising:

[0017] Step S1: Collect the environment of the target area through multiple data sensing devices to obtain a multi-dimensional environmental data set.

[0018] Specifically, data sensing devices refer to sensors used to collect environmental information, such as temperature sensors, humidity sensors, smoke detectors, and gas detectors. Target areas refer to specific locations that need to be monitored, such as buildings, factories, or warehouses. Multidimensional environmental datasets are a collection of various environmental data collected by multiple sensors, covering information in multiple dimensions such as temperature, smoke concentration, and humidity.

[0019] First, a variety of data sensing devices are used to monitor the environment of the target area. These sensors are placed at various key locations in the target area to continuously collect environmental data of the target area. For example, in a warehouse, the temperature sensor monitors the temperature in the warehouse in real time, the smoke sensor detects whether there is smoke or harmful gases in the air, and the humidity sensor obtains the air humidity. Each sensor transmits the collected data in a certain format (such as digital signal format) to the data processing center or storage device, and finally forms a multidimensional environmental data set, which provides rich basic information for subsequent analysis.

[0020] Step S2: noise filtering is performed on the multidimensional environment dataset in combination with the firefighting equipment layout data of the target area to obtain a multidimensional environment denoised dataset.

[0021] Specifically, noise filtering refers to the use of specific algorithms or methods to remove irrelevant or interfering information in the data to improve data quality. Fire equipment layout data is data that describes the specific location distribution and type, quantity and other related information of fire equipment (such as fire extinguishers, sprinkler systems, etc.). For example, the specific location coordinates of a fire hydrant on a certain floor, the placement point of a fire extinguisher, and the coverage of the sprinkler system. The multidimensional environmental denoising dataset is a data set obtained after noise filtering of the multidimensional environmental dataset, which can more accurately reflect the real environmental status of the target area.

[0022] First, the fire equipment layout data of the target area is obtained, and the multidimensional environmental data set is combined with the fire equipment layout data. The multidimensional environmental data set is processed through specific algorithms, such as filtering algorithms, Kalman filtering algorithms, etc. For example, on a certain floor, some electronic components of the fire sprinkler system may generate weak electromagnetic interference signals from the smoke sensor. Using the Kalman filtering algorithm, combined with the fire equipment layout data (such as the location and electromagnetic characteristics of the sprinkler system, etc.), these interference data caused by the fire equipment are identified and removed, thereby obtaining a multidimensional environmental denoising data set. The multidimensional environmental denoising data set after noise filtering can more truly reflect the actual environmental status of the target area, laying the foundation for accurate fire risk assessment.

[0023] Step S3: Based on the multidimensional environment denoising data set, a plurality of data sources are comprehensively analyzed to generate fire protection comprehensive data, and the multidimensional environment denoising data set is fused according to the fire protection comprehensive data to obtain a multidimensional environment fusion data set.

[0024] Specifically, fire protection comprehensive data is obtained by comprehensive analysis of multidimensional environmental denoising datasets and multiple data sources, and is comprehensive data that can fully reflect the safety status of the target area. The multidimensional environmental fusion dataset is a dataset obtained by fusing the multidimensional environmental denoising dataset with the fire protection comprehensive data. This dataset is no longer a simple list of multiple sensor data, but a data set that can better reflect the relationship between the overall environmental characteristics of the target area and the fire risk after comprehensive analysis and fusion.

[0025] Use data analysis software or algorithm libraries to conduct in-depth mining of multiple data sources, comprehensively analyze the relationship between various environmental data, and generate comprehensive fire protection data. For example, analyze the relationship between temperature data and smoke concentration data, consider the impact of humidity on the possibility of fire; combine data such as temperature, humidity and smoke concentration, and use statistical analysis methods (such as principal component analysis) to identify potential fire risk factors. Then, based on the comprehensive fire protection data, use data fusion algorithms (such as weighted average method, Bayesian estimation method, etc.) to fuse the multidimensional environmental denoising data set, and integrate the scattered data into a multidimensional environmental fusion data set, making the data more comprehensive and representative, thereby more accurately reflecting the fire risk situation.

[0026] Step S4: Perform training and learning based on the comprehensive fire protection data to construct a fire risk model, and synchronize the multi-dimensional environment fusion data set to the fire risk model for evaluation according to the multiple data sources to obtain the fire risk level of the target area.

[0027] Specifically, the fire risk model is a model built by analyzing historical and real-time data to assess the risk of fire in the target area. The model is trained and learned from comprehensive fire protection data and can output the fire risk level of the target area based on the input multi-dimensional environmental fusion data set.

[0028] Machine learning algorithms (such as decision tree algorithms, neural network algorithms, etc.) are used to build fire risk models using comprehensive fire data as training data. For example, when using the decision tree algorithm, various features in the comprehensive fire data (such as temperature, smoke concentration, humidity, etc.) are used as input, and historically known fire occurrences (whether a fire occurred, the severity of the fire, etc.) are used as output labels for training. After the model is built, the multidimensional environmental fusion dataset is input into the fire risk model according to multiple data sources (i.e., the data sources previously collected and processed). The algorithm logic in the model is used for calculation and evaluation, and the fire risk level of the target area is finally obtained. This level can be a numerical value (such as a value between 0-1, 0 means no fire risk, 1 means a fire is about to occur) or a classification level (such as low risk, medium risk, high risk). Inputting the multidimensional environmental fusion dataset into the model for evaluation can quantify the fire risk level of the target area and provide a key basis for subsequent early warning decisions.

[0029] Step S5: Making a determination based on the fire risk level, generating a fire warning instruction, and sending the fire warning instruction to the remote control terminal to automatically warn the target area.

[0030] Specifically, the fire warning instruction is a response instruction generated based on the fire risk level, which can be to immediately start the sprinkler system, notify the fire department, etc. The remote control terminal is a device or system used to receive and execute warning instructions, such as a fire monitoring center.

[0031] A judgment is made based on the fire risk level evaluated in step S4 and a fire warning instruction is generated. During the judgment process, different thresholds or rules can be set to determine different operations. The generated alarm instruction is sent to the remote control terminal through a communication network (such as Ethernet, WiFi or mobile network, etc.). For example, in a large industrial park, if the fire risk level of a workshop reaches a high risk, a corresponding warning instruction is generated and sent to the remote control terminal of the monitoring center through the network of the park. The monitoring center can take corresponding fire-fighting measures according to the instruction, such as remotely starting the fire-fighting equipment in the workshop, and notifying the personnel in the workshop to evacuate, etc., to achieve automatic early warning of the target area.

[0032] The corresponding early warning instructions are generated according to the assessed fire risk level and automatically sent to the remote control terminal, realizing the automation of early warning operation, ensuring that relevant personnel can receive fire risk information in time, quickly take corresponding prevention or rescue measures, and effectively reduce potential losses.

[0033] Furthermore, step S1 of the embodiment of the present application further includes:

[0034] Retrieve historical environmental data archives for sensor analysis, and select and determine multiple data sensing devices; determine multiple data sources based on the historical environmental data archives, perform collection and analysis based on the multiple data sources, and determine multiple collection points; obtain data collection demand information, and deploy the multiple data sensing devices in accordance with the data collection demand information and the multiple collection points to construct a data sensing network; perform environmental traversal of the multiple data sources in the target area through the data sensing network to obtain the multidimensional environmental data set.

[0035] Specifically, the historical environmental data archive is a collection of environmental data related to the target area in the past, including but not limited to the changes in previous temperature, humidity, smoke concentration and other data over time. First, retrieve the historical environmental data archive of the target area. Use data analysis and data mining technology to analyze the historical environmental data archive to determine the appropriate data sensing equipment for collecting environmental data. For example, when analyzing the historical environmental data archive, it is found that the temperature fluctuations in a certain area are large and related to the fire risk, so a high-precision temperature sensor needs to be selected; if it is found that humidity also has a certain impact on the fire risk, a humidity sensor will be determined, thereby determining multiple data sensing devices.

[0036] Next, the correlation between the data in the historical environmental data archive and its relationship with fire risk are analyzed to determine multiple data sources, that is, specific types of environmental information sources, such as temperature, humidity, smoke, gas, etc. For example, if historical data shows that temperature and smoke concentration have a significant impact on fire risk, then temperature sensors and smoke detectors will be given priority. Subsequently, data collection and analysis are carried out based on the determined data sources, and specific collection points are further selected by comprehensively considering factors such as the layout and functional zoning of the target area. For example, in a building, sensors can be set up in the kitchen, stairwell, and near electrical equipment to ensure coverage of potential high-risk areas for fire.

[0037] Obtain data collection demand information, which can come from the safety regulations of the target area, previous fire accident analysis, or special usage requirements, including specific requirements for collection points and sensor layout. For example, for places where valuable cultural relics are preserved, the temperature and humidity collection accuracy may be required to reach a very high level, and the collection frequency may be very high. According to these data collection demand information and the multiple collection points that have been determined, multiple data sensing devices are deployed to build a data sensing network to collect monitoring information from multiple data sources in the target area.

[0038] Finally, through the constructed data sensor network, multiple data sources in the target area are traversed. Each data sensor device collects data from its own responsible data source according to the set collection frequency (such as collecting data every 5 minutes), and integrates the collected environmental data to form the required multi-dimensional environmental data set, providing an accurate and reliable data foundation for subsequent fire warnings.

[0039] Further, such as Figure 2 As shown, step S2 of the embodiment of the present application also includes:

[0040] Download a fire map of the target area, mark the target area according to the fire map, and determine the fire equipment layout data of the target area; integrate the multidimensional environmental data set in combination with the fire equipment layout data to obtain comprehensive fire environment data; perform noise identification based on the comprehensive fire environment data, determine multiple noise sources, perform feature analysis according to the multiple noise sources, and obtain multiple noise feature data; use a filtering algorithm in combination with the multiple noise feature data to filter out noise and generate initial filtered data; perform filtering verification on the initial filtered data to obtain a filtering effect, perform denoising analysis based on the filtering effect, and determine the multidimensional environmental denoising data set.

[0041] Specifically, a fire map is a map that specifically depicts fire-related information in a target area, including the location of fire-fighting equipment (such as fire hydrants, fire extinguishers, sprinklers, etc.), evacuation routes, emergency exits, and other information. First, download the fire map in the target area from the relevant system or database. Then, mark the target area based on the detailed information on the fire map to determine the layout data of the fire-fighting equipment in the target area. For example, in a hotel's fire warning system, download the fire map from the hotel's management system, and mark the fire-fighting equipment layout data such as the location of fire hydrants and fire extinguishers on each floor based on the map.

[0042] Use data merging tools (such as Excel or database management systems) to integrate multidimensional environmental data sets and fire equipment layout data to generate comprehensive fire environment data. The comprehensive fire environment data integrates the environmental information and fire facility layout information of the target area to more comprehensively consider various factors related to fire warning.

[0043] Noise identification is performed based on comprehensive fire environment data. Multiple noise sources are identified through data analysis algorithms (such as outlier detection algorithms) combined with an understanding of the operating principles of fire equipment and environmental factors. The noise source is the source of interference in the data during the collection of multi-dimensional environmental data sets. For example, if it is found that the smoke sensor data in a certain area often fluctuates abnormally, and after analysis it is found that it is caused by the electromagnetic radiation of a nearby fire alarm device, then this fire alarm device is a noise source.

[0044] According to the determined multiple noise sources, feature analysis is performed, and multiple noise feature data are obtained using signal analysis tools (such as spectrum analyzer software) or data statistical methods (such as calculating the mean, variance and other statistics of noise data). These noise feature data describe the characteristics of the noise, such as the frequency range, intensity, and regularity of occurrence of the noise.

[0045] The filtering algorithm is used to combine multiple noise feature data to filter out noise, separate the useful signal from the noise, and obtain the preliminary cleaned data, that is, the initial filtered data. The initial filtered data is filtered and verified, and the filtering effect, that is, the degree of improvement of the data quality after filtering, is evaluated by comparing the data before and after cleaning. The filtering effect can be obtained by comparing with known accurate data (if there is a standard data sample or historical reliable data), or by cross-validation (dividing the data into multiple parts, one for filtering and the other for verification). For example, the filtered data is compared with the reference data collected under the same environment but without noise interference, and the degree of reduction of the data error is calculated to evaluate the filtering effect. If the filtering effect meets the expected requirements, it can be determined that the filtered data is a multidimensional environmental denoising data set; if the filtering effect is not ideal, it is necessary to adjust the filtering algorithm or re-analyze the noise feature data, and perform filtering again until a multidimensional environmental denoising data set that meets the requirements is obtained.

[0046] The above steps integrate multi-dimensional environmental data and fire equipment layout data, and use statistical analysis and filtering algorithms to identify and remove noise in the data to generate a high-quality multi-dimensional environmental denoised data set, which provides reliable data support for subsequent comprehensive analysis and risk assessment, thereby improving the accuracy and reliability of the fire warning system.

[0047] Furthermore, in step S2 of the embodiment of the present application, the filtering algorithm is used in combination with the plurality of noise feature data to perform noise filtering to generate initial filtered data, and the method further includes:

[0048] Based on the multiple noise characteristic data, analysis is performed to obtain a fire environment noise signal; wavelet decomposition is performed on the fire environment noise signal to obtain noise signal wavelet coefficients; threshold quantization is performed based on the noise signal wavelet coefficients to determine the noise signal wavelet selection threshold; the noise signal wavelet coefficients are truncated according to the noise signal wavelet selection threshold, and noise signals less than the noise signal wavelet selection threshold are set to zero to obtain valid signal information greater than the noise signal wavelet selection threshold; filtering and reconstructing the valid signal information to obtain the initial filtering data.

[0049] Specifically, the noise filtering consists of first processing the original monitoring data with the help of data analysis tools, identifying the characteristics of the interference signal, and extracting the noise signal in the fire environment. The fire environment noise signal is decomposed by wavelet to capture the changes of the signal at different times and frequencies, and the fire environment noise signal is decomposed into wavelet coefficients at different scales and frequencies, namely the noise signal wavelet coefficients.

[0050] According to the wavelet coefficients of the noise signal, the threshold value of the noise signal wavelet selection is determined. The selection threshold is used to intercept and judge the wavelet coefficients of the noise signal in subsequent operations. In this process, a statistical analysis method can be used, such as calculating the mean, standard deviation and other statistics of the wavelet coefficients of the noise signal, and then determining the wavelet selection threshold of the noise signal according to certain rules (such as soft threshold or hard threshold rule). For example, for the hard threshold rule, the mean plus three times the standard deviation can be used as the wavelet selection threshold of the noise signal.

[0051] According to the selected threshold, the wavelet coefficients of the noise signal are intercepted, the noise signal less than the threshold is set to zero, and the valid signal information greater than the threshold is retained. This process can effectively remove the signal components below the noise threshold, making the data purer. The inverse wavelet transform operation is performed on the screened effective signal information, and the denoised signal is restored to the time domain signal in combination with the retained wavelet coefficients to obtain the initial filtered data. This data retains the effective signal part while removing the noise signal, providing a basis for further filtering verification and determining the multi-dimensional environment denoising data set.

[0052] Further, such as Figure 3 As shown, step S3 of the embodiment of the present application also includes:

[0053] Based on the multidimensional environmental denoising data set, correlation analysis is performed on the multiple data sources to generate multiple correlation coefficients; multiple fire indicators are determined by calculation according to the multiple correlation coefficients in combination with the multidimensional environmental denoising data set; based on the multiple fire indicators, the multiple data sources are evaluated to generate multiple fire source prediction scores; according to the multiple fire source prediction scores, the multiple data sources are traversed for comprehensive analysis to generate comprehensive fire data.

[0054] Specifically, the correlation coefficient is a coefficient obtained by performing a correlation analysis on multiple data sources based on a multidimensional environmental denoising dataset, and represents the numerical value of the degree of association between the data sources. The fire index is calculated by combining the correlation coefficient with the multidimensional environmental denoising dataset, and is an indicator used to measure the fire-related risk or status of the target area. The fire source prediction score is a score obtained by evaluating multiple data sources based on multiple fire indicators, and is used to predict the probability of the existence of a fire source. The higher the fire source prediction score of a certain area, the greater the possibility of a fire source in that area causing a fire.

[0055] Based on the multi-dimensional environmental denoising data set, statistical analysis tools are used to perform correlation analysis on multiple data sources and calculate the correlation coefficients between the data sources. For example, for the temperature data source and the smoke concentration data source, the covariance between the two is calculated and then divided by their respective standard deviations to obtain the correlation coefficient representing the relationship between the two. By performing such calculations on all data sources, multiple correlation coefficients are generated.

[0056] A series of fire protection indicators are determined by calculating multiple correlation coefficients combined with multidimensional environmental denoising data sets. These indicators can be single-type indicators such as high temperature alarm thresholds and smoke concentration monitoring values, or comprehensive indicators such as fire hazard indicators and fire spread possibility indicators. Multiple data sources are evaluated based on multiple fire protection indicators, and corresponding fire source prediction scores are generated for each data source. The evaluation process uses pre-set evaluation criteria (such as different scoring levels corresponding to the threshold range of each fire protection indicator) to evaluate each data source. If a fire protection indicator represents the fire hazard, when the indicator exceeds a certain threshold, a fire source prediction score is assigned to the data source according to the set scoring rules. By performing such an evaluation on all data sources, multiple fire source prediction scores are generated. In addition, machine learning models (such as support vector machines or random forests) can be used to evaluate data sources, and the fire source prediction score of each data source is calculated based on historical data and current monitoring values.

[0057] Finally, multiple data sources are traversed for comprehensive analysis based on multiple fire source prediction scores, and data integration and logical judgment are performed on all fire source prediction scores and data sources. For example, more attention weight is given to data sources with higher scores, and the scores, data characteristics and mutual relationships of all data sources are comprehensively considered. Comprehensive fire protection data is generated through rule-based expert system algorithms or decision tree algorithms in machine learning. This data can fully reflect the fire-related conditions in the target area.

[0058] Furthermore, step S3 of the embodiment of the present application also includes:

[0059] Feature extraction is performed based on the multiple fire source prediction scores to generate multiple comprehensive fire features, and a data fusion strategy is formulated based on the multiple comprehensive fire features; weighted calculation is performed on the multidimensional environment denoised data set according to the data fusion strategy to generate multiple weight coefficients; the multidimensional environment denoised data set is arranged in descending order based on the multiple weight coefficients to generate a denoised data sequence; the multidimensional environment denoised data set is traversed according to the denoised data sequence to perform data fusion to obtain the multidimensional environment fused data set.

[0060] Specifically, feature extraction is performed based on multiple fire source prediction scores. Feature extraction techniques, such as principal component analysis (PCA) or linear discriminant analysis (LDA), are used to process the fire source prediction score data to extract the features that can reflect the comprehensive fire situation and generate multiple comprehensive fire features, such as a combination of temperature, humidity and smoke concentration.

[0061] Next, a data fusion strategy for fusing multidimensional environmental denoising datasets is developed based on these comprehensive fire characteristics. This data fusion strategy specifies how to weight and combine data to achieve effective data fusion. It can be adjusted according to the characteristics and importance of different data sources. For example, if historical data shows that smoke concentration plays an important role in fires, it can be given a higher weight during fusion.

[0062] The multidimensional environmental denoising data set is weighted according to the data fusion strategy. For example, for a multidimensional environmental denoising data set consisting of temperature, humidity, smoke concentration and other data, according to the weights set in the data fusion strategy (such as the weight of smoke concentration data is 0.5, the weight of temperature data is 0.3, and the weight of humidity data is 0.2), each data element is multiplied by the corresponding weight to generate multiple weight coefficients.

[0063] Based on multiple weight coefficients, a sorting algorithm is used to arrange the multidimensional environment denoising data set in descending order of weight coefficients to generate a denoised data sequence. The order of data in the sequence reflects the priority of the data in the fusion process. The data with the highest weight coefficient is placed at the front of the sequence, and the data with the lowest weight coefficient is placed at the end, ensuring that the most important data is processed first.

[0064] Finally, the multidimensional environment denoising data set is traversed according to the denoising data sequence to perform data fusion to obtain a multidimensional environment fusion data set. In this process, the data is fused from front to back according to the order of the sequence. For example, a weighted summation method can be used to multiply the first data in the sequence by its weight coefficient, add the second data multiplied by its weight coefficient, and so on, to finally obtain a multidimensional environment fusion data set.

[0065] Through feature extraction and data fusion strategy formulation, efficient data fusion is achieved, and a more accurate multi-dimensional environmental fusion data set is obtained. This process improves the comprehensiveness and practicality of the data, provides more accurate data support for fire risk assessment and early warning systems, and further enhances the ability of fire safety management.

[0066] Furthermore, step S5 of the embodiment of the present application further includes:

[0067] Based on the fire risk level and the multiple fire indicators, an expected environmental threshold is set; whether the fire risk level is greater than or equal to the expected environmental threshold is determined; if the fire risk level is greater than or equal to the expected environmental threshold, the fire risk level is extracted for risk assessment to obtain a fire risk coefficient; an impact analysis is performed based on the fire risk coefficient to generate a fire impact factor; based on the fire impact factor and the fire risk coefficient, an analysis is performed to generate the fire warning instruction.

[0068] Specifically, the expected environmental threshold is a value set based on the fire risk level and multiple fire protection indicators, which is used to determine whether the fire risk level has reached a level that requires further attention or measures. The fire risk coefficient is a coefficient obtained by conducting a risk assessment on fire risk levels greater than or equal to the expected environmental threshold, which more accurately quantifies the degree of fire risk. The fire impact factor is a factor obtained by conducting an impact analysis based on the fire risk coefficient, reflecting the relevant factors that may affect the personnel, property, environment, etc. in the target area. For example, the number of people that may be affected, the value of property, the degree of pollution to the surrounding environment, etc.

[0069] The expected environmental threshold is set based on the fire risk level and multiple fire indicators. This process needs to take into account factors such as the type of target area (such as residential areas, commercial areas, industrial areas, etc.), the configuration of fire-fighting facilities, and historical fire data.

[0070] Determine whether the fire risk level is greater than or equal to the expected environmental threshold. If the fire risk level is greater than or equal to the expected environmental threshold, extract the fire risk level for risk assessment. Otherwise, keep monitoring. Risk assessment can be done in a variety of ways, such as a probability-based risk assessment model or a hierarchical analysis method. For example, the fire risk coefficient can be calculated based on the position of the fire risk level in a specific model and the weights of different fire protection indicators.

[0071] Conduct impact analysis based on the fire risk factor. This process requires combining specific information about the target area, such as the distribution of people and property. For example, using geographic information system (GIS) technology to analyze the impact of fire risk factors on people and property in different areas, thereby generating fire impact factors.

[0072] Fire warning instructions are generated based on the analysis of fire influencing factors combined with fire risk coefficients. These instructions are customized according to the size of the fire risk and the scope of impact, such as starting the sprinkler system, sounding the alarm, and guiding personnel to evacuate. Then, these instructions are sent to the remote control terminal to achieve automatic warning of the target area.

[0073] The fire risk coefficient and influencing factor generated through fire risk assessment and impact analysis provide an important basis for the formulation of fire warning instructions, ensuring that fire risks can be comprehensively judged based on real-time data and historical data, and customized fire warning instructions can be generated to improve the accuracy and effectiveness of fire warnings and reduce the occurrence of potential fire accidents.

[0074] In summary, the multi-data fusion fire warning method provided in the embodiment of the present application has the following technical effects:

[0075] The target area is collected by multiple data sensing devices to obtain a multidimensional environmental data set. The multidimensional environmental data set covers various information related to the fire risk in the target area, such as temperature, smoke concentration, humidity and other environmental parameters, providing comprehensive raw data for subsequent analysis. The multidimensional environmental data set is combined with the fire equipment layout data of the target area to remove noise and obtain a multidimensional environmental denoising data set. This step improves the quality and accuracy of the data by cleaning up irrelevant or interfering data, making subsequent analysis more reliable. Based on the multidimensional environmental denoising data set, a comprehensive analysis of multiple data sources is performed to generate fire comprehensive data, and the multidimensional environmental denoising data set is fused according to the fire comprehensive data to obtain a multidimensional environmental fusion data set. This step integrates information from different sources to make the data more comprehensive and representative, forming a comprehensive environmental view, thereby more accurately reflecting the fire risk status. Training and learning are performed based on the fire comprehensive data to build a fire risk model. According to the multiple data sources, the multidimensional environmental fusion data set is synchronized to the fire risk model for evaluation, and the fire risk level of the target area is quantified, providing a key basis for subsequent early warning decisions. This step can dynamically adapt to different environmental changes and optimize the accuracy of fire risk prediction through machine learning. Based on the fire risk level, a fire warning instruction is generated, and the fire warning instruction is sent to the remote control terminal for automatic warning of the target area. This step realizes a rapid response mechanism to ensure that relevant personnel can receive fire risk information in time when a fire occurs and take corresponding prevention or rescue measures.

[0076] In general, the embodiment of the present application collects environmental data through multi-data sensing equipment, builds a fire risk model for evaluation after noise filtering, comprehensive analysis and data fusion, and finally generates warning instructions to realize automatic fire warning. This multi-data fusion method overcomes the limitations of traditional single data warning, comprehensively considers multiple environmental factors and eliminates data noise interference, making fire risk assessment more accurate. At the same time, automatic warning ensures timely notification of relevant personnel, effectively improving the accuracy, timeliness and reliability of fire warning, thereby improving the effectiveness of the entire fire warning system and ensuring fire safety in the target area.

[0077] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a multi-data fusion fire warning platform, the platform comprising:

[0078] The environment data collection module 10 is used to collect the environment of the target area through multiple data sensing devices to obtain a multi-dimensional environment data set.

[0079] The data denoising module 20 is used to filter out noise from the multidimensional environmental data set combined with the firefighting equipment layout data of the target area to obtain a multidimensional environmental denoised data set.

[0080] The data fusion module 30 is used to perform a comprehensive analysis on multiple data sources based on the multidimensional environmental denoising data set to generate comprehensive fire protection data, and fuse the multidimensional environmental denoising data set according to the comprehensive fire protection data to obtain a multidimensional environmental fusion data set.

[0081] The fire risk assessment module 40 is used to perform training and learning based on the comprehensive fire protection data, construct a fire risk model, synchronize the multi-dimensional environment fusion data set to the fire risk model for evaluation according to the multiple data sources, and obtain the fire risk level of the target area.

[0082] The fire warning module 50 is used to make a determination based on the fire risk level, generate a fire warning instruction, and send the fire warning instruction to the remote control terminal to automatically warn the target area.

[0083] Furthermore, the environmental data collection module 10 of the embodiment of the present application is also used to perform the following steps:

[0084] Retrieve historical environmental data archives for sensor analysis, and select and determine multiple data sensing devices; determine multiple data sources based on the historical environmental data archives, perform collection and analysis based on the multiple data sources, and determine multiple collection points; obtain data collection demand information, and deploy the multiple data sensing devices in accordance with the data collection demand information and the multiple collection points to construct a data sensing network; perform environmental traversal of the multiple data sources in the target area through the data sensing network to obtain the multidimensional environmental data set.

[0085] Furthermore, the data denoising module 20 in the embodiment of the present application is also used to perform the following steps:

[0086] Download a fire map of the target area, mark the target area according to the fire map, and determine the fire equipment layout data of the target area; integrate the multidimensional environmental data set in combination with the fire equipment layout data to obtain comprehensive fire environment data; perform noise identification based on the comprehensive fire environment data, determine multiple noise sources, perform feature analysis according to the multiple noise sources, and obtain multiple noise feature data; use a filtering algorithm in combination with the multiple noise feature data to filter out noise and generate initial filtered data; perform filtering verification on the initial filtered data to obtain a filtering effect, perform denoising analysis based on the filtering effect, and determine the multidimensional environmental denoising data set.

[0087] Furthermore, the data denoising module 20 in the embodiment of the present application is also used to perform the following steps:

[0088] Based on the multiple noise characteristic data, analysis is performed to obtain a fire environment noise signal; wavelet decomposition is performed on the fire environment noise signal to obtain noise signal wavelet coefficients; threshold quantization is performed based on the noise signal wavelet coefficients to determine the noise signal wavelet selection threshold; the noise signal wavelet coefficients are truncated according to the noise signal wavelet selection threshold, and noise signals less than the noise signal wavelet selection threshold are set to zero to obtain valid signal information greater than the noise signal wavelet selection threshold; filtering and reconstructing the valid signal information to obtain the initial filtering data.

[0089] Furthermore, the data fusion module 30 in the embodiment of the present application is also used to perform the following steps:

[0090] Based on the multidimensional environmental denoising data set, correlation analysis is performed on the multiple data sources to generate multiple correlation coefficients; multiple fire indicators are determined by calculation according to the multiple correlation coefficients in combination with the multidimensional environmental denoising data set; based on the multiple fire indicators, the multiple data sources are evaluated to generate multiple fire source prediction scores; according to the multiple fire source prediction scores, the multiple data sources are traversed for comprehensive analysis to generate comprehensive fire data.

[0091] Furthermore, the data fusion module 30 in the embodiment of the present application is also used to perform the following steps:

[0092] Feature extraction is performed based on the multiple fire source prediction scores to generate multiple comprehensive fire features, and a data fusion strategy is formulated based on the multiple comprehensive fire features; weighted calculation is performed on the multidimensional environment denoised data set according to the data fusion strategy to generate multiple weight coefficients; the multidimensional environment denoised data set is arranged in descending order based on the multiple weight coefficients to generate a denoised data sequence; the multidimensional environment denoised data set is traversed according to the denoised data sequence to perform data fusion to obtain the multidimensional environment fused data set.

[0093] Furthermore, the fire warning module 50 of the embodiment of the present application is also used to perform the following steps:

[0094] Based on the fire risk level and the multiple fire indicators, an expected environmental threshold is set; whether the fire risk level is greater than or equal to the expected environmental threshold is determined; if the fire risk level is greater than or equal to the expected environmental threshold, the fire risk level is extracted for risk assessment to obtain a fire risk coefficient; an impact analysis is performed based on the fire risk coefficient to generate a fire impact factor; based on the fire impact factor and the fire risk coefficient, an analysis is performed to generate the fire warning instruction.

[0095] Through the above detailed description of the fire warning method of multi-data fusion in this specification, those skilled in the art can clearly understand the fire warning platform of multi-data fusion in this embodiment. For the platform disclosed in Example 2, since it corresponds to the method disclosed in Example 1, it has corresponding functional modules and beneficial effects. For relevant matters, please refer to the description of the method part.

[0096] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fire warning method based on multi-data fusion, characterized in that: The method comprises: Collect the environment of the target area through multiple data sensing devices to obtain a multi-dimensional environmental data set; Performing noise filtering on the multidimensional environment data set in combination with the firefighting equipment layout data of the target area to obtain a multidimensional environment denoised data set; Comprehensively analyzing multiple data sources based on the multidimensional environment denoising data set to generate comprehensive fire protection data, and fusing the multidimensional environment denoising data set according to the comprehensive fire protection data to obtain a multidimensional environment fused data set; Conduct training and learning based on the comprehensive fire protection data to build a fire risk model, synchronize the multi-dimensional environment fusion data set to the fire risk model for evaluation according to the multiple data sources, and obtain the fire risk level of the target area; A determination is made based on the fire risk level, a fire warning instruction is generated, and the fire warning instruction is sent to a remote control terminal for automatic warning of the target area.

2. The multi-data fusion fire warning method according to claim 1, characterized in that: The environment of the target area is collected by multiple data sensing devices to obtain a multi-dimensional environmental data set, and the method includes: Retrieve historical environmental data archives for sensor analysis and select and determine multiple data sensor devices; Determine multiple data sources according to the historical environmental data archive, perform collection and analysis according to the multiple data sources, and determine multiple collection points; Obtaining data collection requirement information, and deploying the plurality of data sensing devices according to the data collection requirement information and the plurality of collection points to construct a data sensing network; The multi-dimensional environmental data set is obtained by performing an environmental traversal on the multiple data sources in the target area through the data sensor network.

3. The multi-data fusion fire warning method according to claim 1, characterized in that: The multidimensional environment data set is combined with the fire equipment layout data of the target area to remove noise to obtain a multidimensional environment denoised data set, the method comprising: Downloading a fire map of the target area, marking the target area according to the fire map, and determining the fire equipment layout data of the target area; Based on the multi-dimensional environment data set and the fire equipment layout data, the fire environment comprehensive data is obtained by integration; Perform noise identification based on the comprehensive fire environment data, determine multiple noise sources, perform feature analysis according to the multiple noise sources, and obtain multiple noise feature data; Using a filtering algorithm to combine the plurality of noise feature data to perform noise filtering to generate initial filtering data; The initial filtering data is filtered and verified to obtain a filtering effect, and a denoising analysis is performed according to the filtering effect to determine the multi-dimensional environment denoising data set.

4. The multi-data fusion fire warning method according to claim 3, characterized in that: The method comprises: using a filtering algorithm to combine the plurality of noise characteristic data to filter out noise and generate initial filtering data; Analyze the multiple noise characteristic data to obtain a fire environment noise signal; Performing wavelet decomposition on the fire environment noise signal to obtain wavelet coefficients of the noise signal; Perform threshold quantization according to the noise signal wavelet coefficients to determine the noise signal wavelet selection threshold; According to the noise signal wavelet selection threshold, the noise signal wavelet coefficients are intercepted, the noise signal smaller than the noise signal wavelet selection threshold is set to zero, and the effective signal information larger than the noise signal wavelet selection threshold is obtained; The effective signal information is filtered and reconstructed to obtain the initial filtering data.

5. The multi-data fusion fire warning method according to claim 1, characterized in that: Comprehensively analyzing multiple data sources based on the multi-dimensional environment denoising data set to generate comprehensive fire protection data, the method includes: Performing correlation analysis on the multiple data sources based on the multidimensional environmental denoising data set to generate multiple correlation coefficients; Determine multiple fire protection indicators by calculating according to the multiple correlation coefficients combined with the multi-dimensional environment denoised data set; Evaluating the plurality of data sources based on the plurality of fire indicators to generate a plurality of fire source prediction scores; The multiple data sources are traversed for comprehensive analysis based on the multiple fire source prediction scores to generate comprehensive fire protection data.

6. The multi-data fusion fire warning method according to claim 5, characterized in that: The multidimensional environment denoising data set is fused according to the fire protection comprehensive data to obtain a multidimensional environment fused data set, the method comprising: Extracting features based on the multiple fire source prediction scores to generate multiple fire protection comprehensive features, and formulating a data fusion strategy based on the multiple fire protection comprehensive features; Performing weighted calculation on the multi-dimensional environment denoising data set according to the data fusion strategy to generate a plurality of weight coefficients; Arrange the multidimensional environment denoising data set in descending order based on the multiple weight coefficients to generate a denoising data sequence; The multidimensional environment denoising data set is traversed according to the denoising data sequence to perform data fusion to obtain the multidimensional environment fusion data set.

7. The multi-data fusion fire warning method according to claim 5, characterized in that: Based on the fire risk level, a determination is made to generate a fire warning instruction, the method comprising: Setting a desired environmental threshold based on the fire risk level in combination with the plurality of fire protection indicators; Determining whether the fire risk level is greater than or equal to the expected environmental threshold; If the fire risk level is greater than or equal to the expected environmental threshold, extracting the fire risk level for risk assessment to obtain a fire risk coefficient; Performing an impact analysis based on the fire risk coefficient to generate a fire impact factor; The fire warning instruction is generated based on the analysis of the fire impact factor combined with the fire risk coefficient.

8. The multi-data fusion fire warning platform is characterized by: The platform is used to execute the method according to any one of claims 1 to 7, including: An environmental data collection module, which is used to collect environmental data of a target area through multiple data sensing devices to obtain a multi-dimensional environmental data set; A data denoising module, the data denoising module is used to filter out noise from the multidimensional environmental data set combined with the firefighting equipment layout data of the target area to obtain a multidimensional environmental denoised data set; A data fusion module, the data fusion module is used to perform a comprehensive analysis on multiple data sources based on the multidimensional environment denoising data set to generate comprehensive fire protection data, and fuse the multidimensional environment denoising data set according to the comprehensive fire protection data to obtain a multidimensional environment fused data set; A fire risk assessment module, wherein the fire risk assessment module is used to perform training and learning based on the comprehensive fire protection data, construct a fire risk model, synchronize the multi-dimensional environment fusion data set to the fire risk model for assessment according to the multiple data sources, and obtain the fire risk level of the target area; A fire warning module is used to make a determination based on the fire risk level, generate a fire warning instruction, and send the fire warning instruction to a remote control terminal to automatically warn the target area.

Images