Multi-source data fusion method and system based on data analysis

Abstract

The invention discloses a multi-source data fusion method and system based on data analysis, and relates to the technical field of electric digital data processing. The multi-source data fusion method based on data analysis comprises the following steps of performing fusion real-time analysis; performing dynamic fusion adaptive analysis; and interactive fusion validity analysis. According to the method, real-time analysis is carried out through real-time fusion data, whether sampling sensing frequency optimization is carried out or not is judged, then dynamic adaptability analysis is carried out according to sensing fusion data, whether sensing fusion parameter optimization is carried out or not is judged, finally interaction effectiveness analysis is carried out, and whether interaction fusion noise optimization is carried out or not is judged. Therefore, the reliability of the corresponding fire-fighting information dynamic fusion of the fire-fighting facilities in the transformer substation in the communication process of the internet of things is improved, and the problem that the reliability of the corresponding fire-fighting information dynamic fusion of the fire-fighting facilities in the transformer substation in the communication process of the internet of things is not high in the prior art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric digital data processing, and in particular to a multi-source data fusion method and system based on data analysis. BACKGROUND

[0002] The prior art mainly collects environmental parameters and equipment state data through independent front-end devices such as fire-fighting sensors, temperature detectors, smoke alarms, fire hydrant pressure monitoring devices, automatic sprinkler fire extinguishing devices, video monitoring cameras, etc., performs basic denoising processing and standardized format conversion on the raw data of each subsystem to achieve the preliminary structured goal, and then performs fusion calculation on the multi-source data based on the triggering mechanism or shallow statistical analysis rules to generate local alarm signals. The fire hydrant pressure detection device is used to detect the external pressure information of the fire hydrant, and the automatic sprinkler fire extinguishing device includes chemical agent adjusting equipment, water spray pump nozzle, etc. Then, the fire-fighting disposal scheme needs to be formulated through empirical secondary analysis of scattered alarm information. At the same time, a common data model framework is constructed by using heterogeneous data unified modeling technology to realize real-time presentation of the spatial layout state of the substation fire-fighting facilities and integration of key area monitoring images, so as to improve the fire-fighting supervision quality and operation and maintenance collaboration ability.

[0003] For example, the Chinese invention patent with publication number CN117828309B discloses a substation safety early warning method based on multi-source data fusion ranging, which includes: generating a virtual early warning space according to the dangerous distance threshold of the high-voltage equipment of the substation, obtaining first monitoring data, if the value is less than or equal to the tracking distance threshold, activating the mobile ranging early warning module to perform tracking ranging, obtaining the distance histogram time sequence diagram, combining the virtual early warning space to perform multi-source data fusion, generating the space contact probability, and if the space contact probability is not less than the contact probability threshold, performing safety early warning.

[0004] For example, the Chinese invention patent with publication number CN111209434B discloses a substation equipment inspection system and method based on multi-source heterogeneous data fusion, which includes: a multi-source heterogeneous data acquisition module, a video image data acquisition module and a sensing data acquisition module, and a multi-source heterogeneous data fusion module. The multi-source heterogeneous data acquisition module is used to convert and save the data collected by the video image data acquisition module and the sensing data acquisition module. The multi-source heterogeneous data fusion module includes a deep neural classification module and a classification result fusion module.

[0005] The above-mentioned technology at least has the following technical problems: In the prior art, in the initial stage of fire monitoring, when the combustible vapor concentration increases sharply to cause a sudden change in temperature rise rate, the temperature sensor covering the main transformer area is not combined with real-time sensing technology, and is subject to insufficient thermal inertia compensation, resulting in a lag of the measured value compared with the actual value. In addition, the diffusion of fire-fighting gas takes time, and the combustion product smoke includes smoke particles and harmful gases. In the mixed gas reaction process, the delay caused by gas diffusion is not compensated. Then, the water spray equipment arranged beside the main transformer area still maintains the conventional atomization parameters and fails to switch to high-speed flow state in time, and cannot adjust the water mist characteristics in the atomization equipment in real time according to the characteristics of the combustion product smoke. However, the existing environmental data mutation cannot be fused in real time, and the compensation adaptability of the fire spread control window period caused by response delay in the initial stage of the fire is lacking. In the high-voltage substation scene, the electromagnetic pulse caused by the action of the large-current switch causes the signal-to-noise ratio of the wireless transmission channel to drop sharply. The rapid change of the current will produce strong magnetic field changes, and such magnetic field changes will cause changes in the electric field, thereby forming an electromagnetic pulse, which is radiated to the communication line, producing transient interference, and further causing the data coverage rate to decrease, causing network jitter. There is a problem of low reliability of dynamic fusion of corresponding fire information of fire-fighting facilities in the substation in the process of Internet of Things communication. SUMMARY

[0006] The embodiment of the present application provides a multi-source data fusion method and system based on data analysis, solves the problem of low reliability of dynamic fusion of corresponding fire information of fire-fighting facilities in the substation in the process of Internet of Things communication in the prior art, and improves the reliability of dynamic fusion of corresponding fire information of fire-fighting facilities in the substation in the process of Internet of Things communication.

[0007] The embodiment of the present application provides a multi-source data fusion method based on data analysis, which comprises the following steps: a fire monitoring and management platform receives fire information data sent by an Internet of Things terminal, performs real-time analysis on the fusion process between a fire automatic alarm device and the fire monitoring and management platform according to the obtained real-time fusion data, to determine whether to perform sampling sensing frequency optimization. Sampling sensing frequency optimization means that the interval between checkpoints and node density are adjusted to improve the real-time performance of synchronous fusion of fire information data. If it is determined that the synchronous fusion is qualified, dynamic adaptability analysis is performed on the fusion process between a transformer water spray device and the fire monitoring and management platform according to the obtained sensing fusion data, to determine whether to perform sensing fusion parameter optimization. Sensing fusion parameter optimization means that the idle period caused by sensing fusion response delay is compensated to improve the sensing fusion effectiveness of fire information data. If it is determined that the sensing fusion is qualified, interactive effectiveness analysis is performed on the fusion process between a fire extinguishing device and the fire monitoring and management platform according to the obtained mixed gas stable time length, to determine whether to perform interactive fusion noise optimization. Interactive fusion noise optimization means that noise interference in the interactive fusion process is reduced to improve the interactive fusion effectiveness of fire information data.

[0008] The embodiment of the present application provides a multi-source data fusion system based on data analysis, comprising a fusion real-time analysis module, a dynamic fusion adaptability analysis module and an interactive fusion effectiveness analysis module; the fusion real-time analysis module is used for receiving fire information data sent by an Internet of Things terminal by a fire monitoring management platform, performing real-time analysis on a fusion process between a fire automatic alarm device and the fire monitoring management platform according to obtained real-time fusion data, and determining whether to perform sampling sensing frequency optimization; the dynamic fusion adaptability analysis module is used for performing dynamic adaptability analysis on a fusion process between a transformer water spray device and the fire monitoring management platform according to obtained perception fusion data, and determining whether to perform perception fusion parameter optimization; and the interactive fusion effectiveness analysis module is used for performing interactive effectiveness analysis on a fusion process between a fire extinguishing device and the fire monitoring management platform according to obtained mixed gas stable duration, and determining whether to perform interactive fusion noise optimization.

[0009] The one or more technical solutions provided in the embodiment of the present application have at least the following technical effects or advantages: 1. By analyzing real-time fusion data, perception fusion data and mixed gas stable duration in real time, sampling sensing frequency optimization, perception fusion parameter optimization and interactive fusion noise optimization are triggered respectively, so that abnormal information found by a fire sensor can be transmitted to related fire equipment in real time, real-time fusion data is compared and corrected with a database to generate accurate scores, coupling quantization real-time is used to improve delay evaluation accuracy, perception fusion parameter optimization is implemented by using perception fusion data to dynamically compensate delay caused by response, and interactive effectiveness is evaluated by using mixed gas stable duration, so that substation fire information receiving has near-zero delay, equipment action has near-zero failure, and safety is more secure.

[0010] 2. Real-time fusion data scores are generated by comparing real-time fusion data with preset data and correcting by using correction values, data fusion real-time influence indexes are generated by coupling processing, the influence degree of data fusion real-time is accurately quantized, the accuracy of data fusion delay acquisition is improved by the processing, inherent deviation is eliminated by the correction values, so that the obtained scores are closer to the real level, coupling processing has multi-dimensional characteristics, a scientific quantization index is constructed, the index itself can reflect the time loss degree caused by receiving during data fusion, and provides a decision basis for sampling sensing frequency optimization, so as to ensure the accuracy of delay evaluation of data real-time fusion.

[0011] 3. The control precision of the fire-fighting equipment is improved by constructing a dynamic perception fusion parameter optimization system; the time synchronization error of the evaluation sensor and the fire extinguishing execution equipment is processed by using the integral method, and a perception fusion influence index is coupled to accurately quantify the time sequence matching degree of the multi-source perception data flow; the integral processing improves the accuracy of the synchronization error evaluation, smooths the random fluctuations, and makes the index closer to the real synchronization state; the index can reflect the response delay degree caused by the synchronization error before the inflection point of the flame growth, provide a decision basis for extinguishing the initial smoldering fire, ensure the rapid formation of the drug concentration advantage field, avoid the risk of re-ignition of the oil-immersed equipment, and improve the reliability of the fire extinguishing response as a whole. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 A flowchart of a multi-source data fusion method based on data analysis provided for the embodiment of the present application is provided. Figure 2 A fusion real-time analysis and judgment flowchart provided for the embodiment of the present application is provided. Figure 3 A dynamic fusion adaptability analysis and judgment flowchart provided for the embodiment of the present application is provided. Figure 4 An interactive fusion effectiveness analysis and judgment flowchart provided for the embodiment of the present application is provided. Figure 5 A structural schematic diagram of a multi-source data fusion system based on data analysis provided for the embodiment of the present application is provided. DETAILED DESCRIPTION

[0013] The embodiment of the present application provides a multi-source data fusion method and system based on data analysis, solves the problem of low dynamic fusion reliability of corresponding fire information of fire-fighting facilities in a substation in an Internet of Things communication process in the prior art, receives fire information data sent by an Internet of Things terminal through a fire monitoring and management platform, performs real-time analysis on a fusion process between a fire automatic alarm device and the fire monitoring and management platform according to obtained real-time fusion data, to determine whether to perform sampling sensing frequency optimization, if it is determined that the synchronization fusion is qualified, performs dynamic adaptability analysis on a fusion process between a transformer water spray device and the fire monitoring and management platform according to obtained perception fusion data, to determine whether to perform perception fusion parameter optimization, if it is determined that the perception fusion is qualified, performs interactive effectiveness analysis on a fusion process between a fire extinguishing device and the fire monitoring and management platform according to obtained mixed gas stable time length, to determine whether to perform interactive fusion noise optimization, and the dynamic fusion reliability of corresponding fire information of fire-fighting facilities in a substation in an Internet of Things communication process is improved.

[0014] The technical scheme in the embodiment of the present application is to solve the problem of low dynamic fusion reliability of corresponding fire information of fire-fighting facilities in a substation in an Internet of Things communication process, and the general idea is as follows: The necessity of optimizing the sampling sensing frequency is determined based on the results of real-time fusion data analysis. The dynamic adaptability is evaluated based on steel fusion data to determine the optimization requirements of perception fusion parameters. The effectiveness of interactive fusion is analyzed through the stabilization time of the mixed gas. The implementation conditions for interactive fusion noise optimization are determined, thereby achieving the effect of improving the reliability of dynamic fusion of fire information corresponding to fire protection facilities in substations during IoT communication.

[0015] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0016] like Figure 1 FIG. 1 is a flowchart of a multi-source data fusion method based on data analysis provided by an embodiment of the present invention. The multi-source data fusion method based on data analysis provided by an embodiment of the present invention includes the following steps: a fire monitoring and management platform receives fire information data sent by an IoT terminal, and performs a real-time analysis of the fusion process between the automatic fire alarm device and the fire monitoring and management platform based on the acquired real-time fusion data to determine whether to perform sampling sensor frequency optimization. Sampling sensor frequency optimization means adjusting the checkpoint interval and node density to improve the real-time performance of the synchronous fusion of fire information data. If the synchronous fusion is determined to be qualified, a dynamic adaptive analysis is performed on the fusion process between the transformer water spray device and the fire monitoring and management platform based on the acquired perception fusion data to determine whether to perform perception fusion parameter optimization. Perception fusion parameter optimization means compensating for the window period caused by the perception fusion response delay to improve the perception fusion effectiveness of the fire information data. If the perception fusion is determined to be qualified, an interactive effectiveness analysis is performed on the fusion process between the fire extinguishing equipment and the fire monitoring and management platform based on the acquired mixed gas stabilization time to determine whether to perform interactive fusion noise optimization. Interactive fusion noise optimization means reducing noise interference during the interactive fusion process to improve the interactive fusion effectiveness of the fire information data.

[0017] In this embodiment, key components such as fire protection facilities and fire alarm systems are connected through IoT sensing and communication technology to display the operating status of key components of substation fire protection equipment in real time: automatic fire alarm equipment, transformer water spray equipment, fire gas fire extinguishing equipment, fire hydrant water pressure monitoring, and fire pool water level monitoring. This reduces transmission delays, improves sampling coverage, ensures efficient synchronization of terminal information with the platform, and enhances the real-time decision-making capabilities of fire alarm response. Specifically, the real-time, adaptability, and interactive effectiveness of fire data fusion are optimized in stages to improve the efficiency of smart fire protection.

[0018] Further, the real-time fusion data obtained is used to analyze the real-time performance of the fusion process between the fire automatic alarm device and the fire monitoring management platform, and the specific steps include: comparing the obtained real-time fusion data with the preset real-time fusion data in the database in terms of difference, and simultaneously correcting the real-time fusion data by using the real-time fusion data correction value to obtain real-time fusion data scores, and coupling the data coverage rate score, the network jitter rate score and the electromagnetic interference intensity score to obtain a data fusion real-time performance influence index; the real-time fusion data includes data coverage rate, network jitter rate and electromagnetic interference intensity, the data coverage rate is obtained by using an electric energy quality analyzer, the network jitter rate is obtained by using one-way delay jitter calculation, and the electromagnetic interference intensity is obtained by using an oscilloscope spectrum meter; the data fusion real-time performance influence index represents the influence degree quantization data of the real-time fusion data on the real-time performance of the fusion process between the fire automatic alarm device and the fire monitoring management platform; the preset real-time fusion data includes preset data coverage rate, preset network jitter rate and preset electromagnetic interference intensity; the real-time fusion data correction value includes data coverage rate correction value, network jitter rate correction value and electromagnetic interference intensity correction value; and the real-time fusion data scores include data coverage rate score, network jitter rate score and electromagnetic interference intensity score.

[0019] The specific expression of the data coverage rate score Q1 is as follows: In the formula, Q1 represents the data coverage rate score corresponding to the end of the fusion period between the fire automatic alarm device and the fire monitoring management platform, C1 represents the data coverage rate correction value, Q C1 represents the data coverage rate corresponding to the end of the fusion process real-time performance analysis period, and Q C0 represents the preset data coverage rate.

[0020] The specific expression of the network jitter rate score Q2 is as follows: In the formula, Q2 represents the network jitter rate score corresponding to the end of the fusion period between the fire automatic alarm device and the fire monitoring management platform, C2 represents the network jitter rate correction value, Q C2 represents the network jitter rate corresponding to the end of the fusion process real-time performance analysis period, and Q N0 represents the preset network jitter rate.

[0021] The specific expression of the electromagnetic interference intensity score Q3 is as follows: In the formula, Q3 represents the electromagnetic interference intensity score corresponding to the end of the fusion period between the fire automatic alarm device and the fire monitoring management platform, C3 represents the electromagnetic interference intensity correction value, Q C3 represents the electromagnetic interference intensity corresponding to the end of the fusion process real-time performance analysis period, and Q E0 represents the preset electromagnetic interference intensity.

[0022] Data fusion real-time influence index R DF The specific expression is: , wherein R DF represents the data fusion real-time influence index corresponding to the end of the fusion period between the fire automatic alarm equipment and the fire monitoring and management platform.

[0023] In this embodiment, the preset real-time fusion data is represented by the sum and average of the real-time fusion data corresponding to the end of the historical fusion period between the historical fire automatic alarm equipment and the fire monitoring and management platform, the real-time fusion data is obtained by the real-time fusion data corresponding to the end of the fusion period between the fire automatic alarm equipment and the fire monitoring and management platform, and the data coverage rate correction value, the network jitter rate correction value, and the electromagnetic interference intensity correction value are values preset in the database for measuring the influence degree of data coverage rate, network jitter rate, and electromagnetic interference intensity on the data fusion real-time influence index. The corresponding correction values are stored in the database for each parameter, and there is a preset mapping relationship between them, which can be many-to-one or one-to-one. In actual application, the real-time data coverage rate, network jitter rate, and electromagnetic interference intensity can be input to accurately obtain the corresponding correction value, providing a quantitative basis for evaluating the influence of the data fusion real-time influence index on the fusion degree, and assisting in accurately calculating the data fusion real-time influence index. The value range of the three correction values is 0-1, and the sum is equal to 1.

[0024] It should be noted that the data fusion real-time influence index increases with the increase of data coverage rate, network jitter rate, and electromagnetic interference intensity. The decrease of data coverage rate, i.e. when multiple nodes in the same area concurrently transmit data, leads to increased channel competition, increased network transmission delay volatility, i.e. increased network jitter rate. If there is high electromagnetic interference in the environment at this time, the superimposed interference signal will increase the wireless communication error rate, further expand the data packet retransmission probability, and force the communication stability to be maintained by reducing the sampling frequency or reducing the coverage range. Although low-frequency sampling can reduce network jitter rate, it will cause the data coverage rate to rise, weakening the state monitoring capability of key areas.

[0025] By considering the above mutual influence mechanism, the relationship between the data fusion real-time influence index and each variable can be more comprehensively understood. These relationships are crucial for real-time evaluation in the data fusion real-time influence index acquisition process. By optimizing data coverage rate, network jitter rate, and electromagnetic interference intensity, the fusion between the fire automatic alarm equipment and the fire monitoring and management platform is improved, effectively solving the problem of low dynamic fusion reliability of corresponding fire information in the process of Internet of Things communication of fire facilities in the substation.

[0026] As Figure 2As shown, the fusion real-time analysis and judgment flowchart provided by the embodiment of the application judges whether the obtained data fusion real-time influence index is greater than a preset value, and if greater than the preset value, the optimization flow is started. The first step is to check and adjust the checkpoint interval, and then the index value is reacquired and it is judged whether the index is not greater than the preset index in the database; if not greater than, dynamic adaptability analysis is performed, and if greater than, the sampling sensing frequency optimization is performed to reacquire the index value; when the finally obtained index value is not greater than the preset value, the flow ends; otherwise, the adjustment process will continue to be looped, and the whole optimization loop must be completed within a specified number of times, and if the limit is exceeded, the sampling sensing frequency warning is triggered.

[0027] It is further understood that whether to perform the sampling sensing frequency optimization is judged by comparing the obtained data fusion real-time influence index with the preset data fusion real-time influence index in the database: if the obtained data fusion real-time influence index is greater than the preset data fusion real-time influence index in the database, it is recorded as unqualified data synchronization and the sampling sensing frequency optimization is performed; if the obtained data fusion real-time influence index is not greater than the preset data fusion real-time influence index in the database, it is recorded as qualified data synchronization and the dynamic adaptability analysis is performed.

[0028] The specific steps of the sampling sensing frequency optimization are as follows: the first step is to perform checkpoint interval optimization: the data fusion real-time influence index deviation and the alarm response time length deviation are acquired, which are respectively proportionally processed with the preset data fusion real-time influence index deviation and the alarm response time length deviation in the database, the results of the proportional processing are summed and averaged to obtain a checkpoint interval preliminary value, which is used to prompt the scheduler to adjust the checkpoint interval based on the obtained checkpoint interval preliminary value to suppress the occurrence of in-band spurs of signal transmission; after the sampling sensing frequency optimization, it is judged whether the reacquired data fusion real-time influence index deviation is not greater than the preset data fusion real-time influence index deviation in the database, if yes, the first step is completed and the dynamic adaptability analysis is performed, otherwise, the second step is performed. The second step is to optimize the node density: based on the re-acquired node density reserve value, the topology self-organizing engine is prompted to adjust the node density based on the obtained node density reserve value to reduce the probability of phase distortion. The node density reserve value represents the re-acquired data fusion real-time impact index deviation and alarm response time deviation after the sampling sensing frequency is optimized. After proportional processing with the data fusion real-time impact index deviation and alarm response time deviation preset in the database, the sum and average processing results are calculated; after the sampling sensing frequency is optimized, if the re-acquired data fusion real-time impact index is not greater than the data fusion real-time impact index preset in the database, the second step is completed and dynamic adaptive analysis is performed, otherwise the sampling sensing frequency optimization times are judged; the specific steps for judging the sampling sensing frequency optimization times are: if the sampling sensing frequency optimization times are within the specified sampling sensing frequency optimization times, return to the first step, otherwise a sampling sensing frequency warning is performed.

[0029] In this embodiment, the checkpoint interval parameters are adjusted in real time based on the obtained checkpoint interval through an adaptive adjustment algorithm to achieve smooth signal transmission. At the same time, the historical checkpoint interval reserve value is used as sample data and input into the autoregressive model of the historical load data time series prediction model. The checkpoint interval-node density time series prediction model is trained based on the adaptive adjustment algorithm. The currently obtained checkpoint interval reserve value and node density reserve value are input into the checkpoint interval-node density time series prediction model, and the corresponding checkpoint interval adjustment value and node density adjustment value are output; the data fusion real-time impact index deviation represents the difference between the obtained data fusion real-time impact index and the data fusion real-time impact index preset in the database, and the alarm response time deviation represents the difference between the obtained alarm response time and the alarm response time preset in the database.

[0030] This example establishes a hierarchical and progressive sampling sensor frequency optimization mechanism to achieve intelligent tuning of the fire data synchronization fusion process, suppress high-frequency glitches in the transmission signal, and make the real-time data stream present a smoother transmission characteristic. Data integrity is maintained by reducing the probability of phase distortion caused by multipath effects. At the same time, a closed-loop convergence mechanism for data fusion errors is established within a preset number of optimizations, forming a dynamic balance between fire alarm response delay and data packet loss rate, achieving a reduction in the average fusion delay, a relative decrease in the incidence of phase distortion, and an improvement in the stability of concurrent transmission.

[0031] Further, the fusion process between the transformer water spray device and the fire monitoring management platform is dynamically adaptive analyzed according to the obtained perception fusion data, and the specific steps include: integrating the obtained perception fusion data in the divided perception fusion time interval to obtain a perception fusion data area, and coupling the perception fusion data area to obtain a perception fusion influence index; the perception fusion time interval represents a unit time period corresponding to the analysis of the perception fusion efficiency (corresponding to the rapidly changing fire environment, the unit time period is usually set to several seconds), the integration processing represents the cumulative change of the perception fusion data in the perception fusion time interval, the perception fusion data includes the temperature rise rate change, the combustion product smoke concentration change and the smoke diffusion speed change, the greater the three changes, the more complex the fire environment, which will intensify the data interference and conflict, and then reduce the accuracy and real-time of the perception fusion between the device and the platform, and the perception fusion data area includes the temperature rise rate change area, the combustion product smoke concentration change area and the smoke diffusion speed change area.

[0032] The temperature rise rate change is used to reflect the temperature change in the combustion process in the perception fusion time interval, the combustion product smoke concentration change is used to reflect the smoke concentration change in the combustion process in the perception fusion time interval, and the smoke diffusion speed change is used to reflect the smoke diffusion in the combustion process in the perception fusion time interval, the temperature rise rate change area represents the area under the integral curve corresponding to the temperature rise rate change with time in the perception fusion time interval, which is used to quantify the cumulative effect of temperature change, the combustion product smoke concentration change area represents the area under the integral curve corresponding to the smoke concentration change with time in the perception fusion time interval, which is used to quantify the cumulative effect of smoke generation, and the smoke diffusion speed change area represents the area under the integral curve corresponding to the smoke diffusion speed change with time in the perception fusion time interval, which is used to quantify the cumulative effect of smoke diffusion, and the perception fusion influence index represents the quantitative data of the dynamic adaptability influence degree of the perception fusion data on the fusion process between the transformer water spray device and the fire monitoring management platform.

[0033] In the embodiment, by constructing a perception fusion effectiveness evaluation method based on multi-parameter space-time integral modeling, the dynamic coordination efficiency of the fire monitoring platform and the fire extinguishing device is improved: the multi-dimensional data integral calculation of the temperature rise rate, the smoke concentration and the diffusion speed is adopted, the fire characteristic parameters in the second time window are converted into quantifiable area indexes, the linkage coupling strength of the multi-sensing data in the fire development process is accurately represented, and then the response parameter matrix of the water spray device is optimized based on the area proportion weight of each parameter, the early fire extinguishing agent delivery precision is improved and the mis-spray rate is reduced, and the transformer oil pillow explosion chain reaction is blocked.

[0034] As Figure 3As shown, the dynamic fusion adaptive analysis and judgment flowchart provided by the embodiment of the present application judges whether the obtained perception fusion influence index is greater than the preset value. If it is higher than the preset value, optimization is started: first, the data alignment degree is corrected to adjust the perception fusion response delay, and then the index value is re-evaluated. If the corrected index does not meet the preset value requirement, it enters the flow adjustment stage, updates the parameters through the perception fusion delay compensation mechanism, and detects the index again. If the index value is not greater than the preset value, the optimization instruction is completed. If the index value is greater than the preset value, it is first judged whether it is within the specified number of optimizations. If it is within the specified number of optimizations, the flow is restarted. If it is not within the specified number of optimizations, the perception fusion early warning is performed.

[0035] It is further understood that the specific steps of judging whether to perform perception fusion parameter optimization are: comparing the obtained perception fusion influence index with the preset perception fusion influence index in the database: if the obtained perception fusion influence index is not greater than the preset perception fusion influence index in the database, it is recorded as perception fusion qualified and interactive effectiveness analysis is performed; if the obtained perception fusion influence index is greater than the preset perception fusion influence index in the database, it is recorded as perception fusion unqualified and perception fusion parameter optimization is performed.

[0036] Among them, the specific steps of perception fusion parameter optimization are: first, data alignment correction: obtain the perception fusion influence index deviation and the inference delay time deviation, respectively, and perform proportional processing with the preset perception fusion influence index deviation and the inference delay time deviation in the database. The sum average processing of the proportional processed results obtains the data alignment correction value, which is used to prompt the time loss of the injection controller caused by the perception fusion response delay. The inference delay time length represents the delay time length of the smoke sensor in the combustion process. After data alignment correction, it is judged whether the re-obtained perception fusion influence index deviation is not greater than the preset perception fusion influence index deviation in the database. If yes, the first step is completed and interactive effectiveness analysis is performed. Otherwise, it indicates that the response delay is overloaded and the second step is performed. The second step is perception fusion delay compensation: based on the re-obtained medicament injection flow adjustment value, the medicament injection flow is increased to improve the control effectiveness of the fire at the initial stage of the fire. The medicament injection flow adjustment value represents the harmonic average result of the perception fusion influence index deviation and the data alignment deviation re-obtained after data alignment correction. After perception fusion parameter optimization, if the re-obtained perception fusion influence index is not greater than the preset perception fusion influence index in the database, the second step is completed and interactive effectiveness analysis is performed. Otherwise, the perception fusion parameter optimization frequency judgment is performed: the specific steps of the perception fusion parameter optimization frequency judgment are: if the perception fusion parameter optimization frequency is within the specified perception fusion parameter optimization frequency, return to the first step. Otherwise, the perception fusion early warning is performed.

[0037] In the embodiment, the perception fusion influence index deviation represents the difference between the obtained perception fusion influence index and the preset perception fusion influence index, the data alignment degree deviation represents the difference between the obtained data alignment degree and the preset data alignment degree in the database, the inference delay time length deviation represents the difference between the obtained inference delay time length and the preset inference delay time length in the database, the data alignment degree is timely adjusted based on the obtained current data alignment correction value by the timestamp synchronization algorithm to compensate for the time delay of the fusion process, and the historical data alignment correction value and the flow value are input into the multivariate linear regression model in the linear regression model as sample data, the data alignment-flow adjustment linear regression model is obtained based on the training of the timestamp synchronization algorithm, and the obtained data alignment correction value and the flow value are input into the data alignment-flow adjustment linear regression model to output corresponding data alignment correction adjustment value and flow adjustment value.

[0038] The example improves the control accuracy of the fire-fighting equipment by constructing an optimization system of dynamic perception fusion parameters, dynamically corrects the time synchronization error of the sensor data and the fire extinguishing execution equipment, improves the time sequence matching degree of the multi-source perception data stream, ensures that the concentration advantage field of the extinguishing agent is quickly formed before the inflection point of the flame growth, improves the timeliness of extinguishing the initial smoldering fire, avoids the risk of re-ignition of the oil-immersed equipment, and overall improves the reliability of the fire extinguishing response.

[0039] As shown in Figure 4 The interactive fusion effectiveness analysis and judgment flowchart provided by the embodiment of the application is shown in the figure, whether the obtained mixed gas stable time length is greater than the preset value is judged, if yes, optimization is started: first, the interactive fusion delay is corrected, and then the time length is re-detected; if the re-obtained index is not greater than the preset value in the database, optimization is completed, otherwise, the fusion noise suppression value is improved and the time length is re-evaluated; the index is re-obtained, if the index is not greater than the preset value, interactive effectiveness analysis is performed, if it is not within the specified number of optimizations, an interactive fusion warning is sent.

[0040] It is further understood that the fusion process between the fire-fighting equipment and the fire-fighting monitoring and management platform is analyzed for interactive effectiveness according to the obtained mixed gas stable time length, and the specific steps of determining whether to perform interactive fusion noise optimization are: comparing the obtained mixed gas stable time length with the preset mixed gas stable time length in the database: if the obtained mixed gas stable time length is greater than the preset mixed gas stable time length in the database, it is recorded as unstable adjustment and interactive fusion parameter optimization is performed; if the obtained mixed gas stable time length is not greater than the preset mixed gas stable time length in the database, it is recorded as stable adjustment and interactive effectiveness analysis is completed.

[0041] The specific steps of the interactive fusion parameter optimization are as follows: first, interactive fusion delay optimization is performed: the mixed gas stable duration deviation and the fire gas release speed deviation are obtained, and proportional processing is performed on the mixed gas stable duration deviation and the fire gas release speed deviation in the database respectively, summation average processing is performed on the proportional processing results, and an interactive fusion delay correction value is obtained, which is used to correct the delay generated by the gas diffusion device, promote the uniform distribution of the fire gas, and improve the response speed of the gas diffusion device. After the interactive fusion delay correction, it is judged whether the newly obtained mixed gas stable duration is not greater than the preset mixed gas stable duration in the database. If yes, the first step is completed and the interactive effectiveness analysis is performed. Otherwise, the second step is performed; second, fusion noise optimization is performed: based on the mixed gas stable duration deviation obtained after the interactive fusion delay correction, a fusion noise improvement value is obtained by mapping in the database, which is used to improve the noise amplitude suppression effect of the corresponding noise covariance matrix in the Kalman filter algorithm; after the interactive fusion parameter optimization, if the newly obtained mixed gas stable duration is not greater than the preset mixed gas stable duration in the database, the second step is completed and the interactive effectiveness analysis is completed. Otherwise, the number of interactive fusion parameter optimization times is judged; the specific steps of the number of interactive fusion parameter optimization times are as follows: if the number of interactive fusion parameter optimization times is within the specified number of interactive fusion parameter optimization times, return to the first step. Otherwise, the interactive fusion warning is performed.

[0042] The mixed gas stable duration represents the time required for the mixed gas to reach stability after the fire gas reacts with the combustion product, the mixed gas stable duration deviation represents the difference between the obtained mixed gas stable duration and the preset mixed gas stable duration, the mixed gas stable duration is obtained by monitoring with a built-in timer, the preset mixed gas stable duration is represented by the result of summation average of the historical mixed gas stable duration in the fusion process between the historical fire extinguishing equipment and the fire monitoring and management platform, and the fire gas release speed deviation represents the difference between the obtained fire gas release speed and the preset fire gas release speed.

[0043] In the embodiment, the current interactive fusion delay is obtained based on the parameter adaptive algorithm to compensate the interactive fusion delay in real time, the length of the window period caused by the need for gas diffusion is reduced, the fusion noise improvement value is input into the Bayesian network model as sample data, the interactive fusion-noise suppression Bayesian network model is obtained based on the parameter adaptive algorithm, the obtained interactive fusion delay correction value and the fusion noise improvement value are input into the interactive fusion-noise suppression Bayesian network model, and the corresponding interactive fusion delay correction adjustment value and the fusion noise improvement adjustment value are output.

[0044] The example realizes the quality and efficiency improvement of the dynamic fusion control ability of the fire extinguishing system by constructing a verification and optimization mechanism of mixed gas diffusion stability, increases the gas cloud uniform distribution speed of the gas diffusion device in the high temperature pyrolysis scene of the oil immersed transformer, drives the Kalman filter to implement multi-dimensional noise suppression reinforcement operation, optimizes the dynamic monitoring signal to noise ratio of the oil mist-fire extinguishing gas mixing process, realizes the error convergence rate improvement of the gas stability time length, avoids the risk of afterburning caused by the settlement delay of the fire extinguishing agent, and links the monitoring module to establish a gas concentration distribution thermodynamic diagram to realize real-time correction feedback link.

[0045] As Figure 5 shown, a structure diagram of a multi-source data fusion system based on data analysis provided by the embodiment of the application, the multi-source data fusion system based on data analysis provided by the embodiment of the application comprises a fusion real-time analysis module, a dynamic fusion adaptability analysis module and an interactive fusion effectiveness analysis module; the fusion real-time analysis module is used for receiving fire information data sent by an Internet of Things terminal by a fire monitoring and management platform, performing real-time analysis on a fusion process between a fire automatic alarm device and the fire monitoring and management platform according to obtained real-time fusion data, and determining whether to perform sampling sensing frequency optimization; the dynamic fusion adaptability analysis module is used for performing dynamic adaptability analysis on a fusion process between a transformer water spray device and the fire monitoring and management platform according to obtained sensing fusion data, and determining whether to perform sensing fusion parameter optimization; and the interactive fusion effectiveness analysis module is used for performing interactive effectiveness analysis on a fusion process between a fire extinguishing device and the fire monitoring and management platform according to obtained mixed gas stability time length, and determining whether to perform interactive fusion noise optimization.

[0046] In the embodiment, the real-time analysis module dynamically adjusts the transmission efficiency of the alarm device, optimizes the sampling frequency, shortens the time delay, ensures that the fire signal and the platform are immediately linked, the dynamic fusion adaptability analysis module calibrates the water spray device parameters according to the environmental variables, improves the cooling accuracy of the fire scene, the interactive fusion effectiveness analysis module optimizes the cooperative noise suppression through gas diffusion characteristics analysis, and the modules cooperate with each other to improve the fire data fusion efficiency.

[0047] In summary, the embodiment of the application analyzes the real-time fusion data, the sensing fusion data and the mixed gas stability time length in real time, respectively triggers the sampling sensing frequency optimization, the sensing fusion parameter optimization and the interactive fusion noise optimization, makes the abnormal information found by the fire sensor be transmitted to the related fire equipment in real time, generates a precise score by comparing and correcting the real-time fusion data and the database, improves the delay evaluation accuracy by coupling the quantified real-time performance, dynamically compensates the delay caused by the response by using the sensing fusion data to implement the sensing fusion parameter optimization, and evaluates the interactive effectiveness by using the mixed gas stability time length, so that the substation fire information receiving is near zero delay, the equipment action is near zero failure, and the safety is more secure.

[0048] Those skilled in the art will appreciate that embodiments of the present application can be devised for a variety of applications. It is intended that the present application be limited only by the scope of the appended claims, and it is intended that various modifications and alterations made by those skilled in the art be considered as within the scope of the present application. The embodiments of the present application will be described with reference to the attached drawings, wherein:

[0049] The present application is described in reference to the drawings using a flowchart and / or a block diagram of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0050] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0052] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the embodiments by those skilled in the art once they learn of the basic inventive concepts. Therefore, the appended claims are intended to cover all such modifications and variations as fall within the scope of the present application.

[0053] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A multi-source data fusion method based on data analysis, characterized in that: The following steps are involved: A1. The fire monitoring and management platform receives fire information data sent by IoT terminals and, based on the acquired real-time fusion data, performs real-time analysis of the fusion process between the automatic fire alarm equipment and the fire monitoring and management platform to determine whether to optimize the sampling and sensing frequency. This optimization involves adjusting the checkpoint interval and node density to improve the real-time synchronization and fusion of fire information data. A2: If the synchronous fusion is determined to be qualified, a dynamic adaptive analysis of the fusion process between the transformer water spray equipment and the fire monitoring and management platform is performed based on the acquired perception fusion data to determine whether to optimize the perception fusion parameters. The perception fusion parameter optimization method improves the effectiveness of the perception fusion of fire information data by compensating for the window period caused by the perception fusion response delay. A3. If the perception fusion is determined to be qualified, the interactive effectiveness analysis of the fusion process between the fire-fighting equipment and the fire monitoring and management platform is performed based on the obtained mixed gas stabilization time to determine whether interactive fusion noise optimization is performed. The interactive fusion noise optimization means improving the interactive fusion effectiveness of fire information data by reducing noise interference during the interactive fusion process.

2. The multi-source data fusion method based on data analysis according to claim 1, characterized in that: The real-time analysis of the fusion process between the fire automatic alarm equipment and the fire monitoring management platform based on the acquired real-time fusion data includes the following specific steps: The acquired real-time fusion data is compared with the preset real-time fusion data in the database for difference, and correction processing is performed based on the real-time fusion data correction value to obtain the real-time fusion data score. The data coverage rate score, network jitter rate score and electromagnetic interference intensity score are coupled to obtain the data fusion real-time impact index; The real-time fusion data includes data coverage rate, network jitter rate and electromagnetic interference intensity. The data fusion real-time impact index represents the quantitative data of the impact of real-time fusion data on the real-time fusion between fire automatic alarm equipment and fire monitoring management platform.

3. The multi-source data fusion method based on data analysis as claimed in claim 2, characterized in that: The specific steps of determining whether to optimize the sampling sensing frequency are as follows: Compare the acquired data fusion real-time impact index with the preset data fusion real-time impact index in the database: If the acquired data fusion real-time impact index is greater than the data fusion real-time impact index preset in the database, it is recorded as data synchronization failure and the sampling sensing frequency optimization is performed; If the obtained data fusion real-time impact index is not greater than the data fusion real-time impact index preset in the database, the data synchronization is considered qualified and dynamic adaptability analysis is performed.

4. The multi-source data fusion method based on data analysis as claimed in claim 3, characterized in that: The specific steps of optimizing the sampling sensing frequency are as follows: The first step is to optimize the checkpoint interval: the obtained data fusion real-time impact indicator deviation and alarm response time deviation are proportionally processed with the data fusion real-time impact indicator deviation and alarm response time deviation preset in the database. The results of the proportional processing are summed and averaged to obtain the checkpoint interval reserve value. This is used to prompt the scheduler to adjust the checkpoint interval based on the obtained checkpoint interval reserve value to suppress the occurrence of burrs in the signal transmission band. After the sampling sensing frequency is optimized, it is determined whether the deviation of the re-acquired data fusion real-time impact index is no greater than the deviation of the data fusion real-time impact index preset in the database. If so, the first step is completed and dynamic adaptability analysis is performed; otherwise, the second step is performed. The second step is to optimize the node density: based on the newly obtained node density reserve value, the topology self-organizing engine is prompted to adjust the node density based on the obtained node density reserve value to reduce the probability of phase distortion; After the sampling sensing frequency is optimized, if the reacquired data fusion real-time impact index is not greater than the data fusion real-time impact index preset in the database, the second step is completed and dynamic adaptability analysis is performed; otherwise, the sampling sensing frequency optimization times are determined; The specific steps of judging the sampling sensing frequency optimization times are as follows: if the sampling sensing frequency optimization times are within the prescribed sampling sensing frequency optimization times, then returning to the first step; otherwise, performing a sampling sensing frequency warning.

5. The multi-source data fusion method based on data analysis according to claim 1, characterized in that: The dynamic adaptive analysis of the fusion process between the transformer water spray equipment and the fire monitoring management platform based on the acquired perception fusion data includes the following specific steps: Integrate the acquired perception fusion data within the divided perception fusion time interval to obtain the perception fusion data area, and simultaneously couple the perception fusion data area to obtain the perception fusion impact index; The perception fusion time interval represents a unit time period for analyzing the perception fusion efficiency. The integration processing represents a process for quantifying the cumulative change of the perception fusion data within the perception fusion time interval. The perception fusion data includes the change in the temperature rise rate, the change in the concentration of the combustion product smoke, and the change in the smoke diffusion speed. The perception fusion data area includes the area of ​​temperature rise rate change, the area of ​​combustion product smoke concentration change, and the area of ​​smoke diffusion speed change. The perception fusion impact index represents quantitative data on the degree of dynamic adaptive impact of the perception fusion data on the fusion process between the transformer water spray equipment and the fire monitoring and management platform.

6. The multi-source data fusion method based on data analysis according to claim 5, characterized in that: The specific steps of determining whether to perform perception fusion parameter optimization are as follows: Compare the acquired perception fusion impact index with the perception fusion impact index preset in the database: If the acquired perception fusion impact index is not greater than the perception fusion impact index preset in the database, the perception fusion is considered qualified and the interaction effectiveness analysis is performed; If the obtained perception fusion impact index is greater than the perception fusion impact index preset in the database, it is recorded as perception fusion failure and perception fusion parameter optimization is performed.

7. The multi-source data fusion method based on data analysis according to claim 6, characterized in that: The specific steps of optimizing the perception fusion parameters are as follows: The first step is to correct data alignment: obtain the perception fusion influence index deviation and the inference delay time deviation, and then perform proportional processing on them with the perception fusion influence index deviation and inference delay time deviation preset in the database. The results of the proportional processing are summed and averaged to obtain the data alignment correction value, which is used to inform the injection controller of the time loss caused by the perception fusion response delay. The inference delay time represents the delay in smoke sensor recognition during the combustion process. After the data alignment is corrected, it is determined whether the re-acquired perception fusion impact index is no greater than the perception fusion impact index preset in the database. If so, the first step is completed and the interaction validity analysis is performed. Otherwise, it indicates that the response delay is overloaded and the second step is performed. The second step is to compensate for the perception fusion delay: the agent injection flow rate is increased based on the re-acquired agent injection flow rate adjustment value to improve the effectiveness of fire control in the early stage of the fire; After the perception fusion parameters are optimized, if the re-acquired perception fusion impact index is not greater than the perception fusion impact index preset in the database, the second step is completed and the interaction effectiveness analysis is performed; otherwise, the number of perception fusion parameter optimizations is determined; The specific steps of judging the number of perception fusion parameter optimizations are: if the number of perception fusion parameter optimizations is within the prescribed number of perception fusion parameter optimizations, return to the first step; otherwise, perform a perception fusion warning.

8. The multi-source data fusion method based on data analysis according to claim 1, characterized in that: The specific steps of performing interactive effectiveness analysis on the fusion process between the fire extinguishing equipment and the fire monitoring management platform based on the obtained mixed gas stabilization time to determine whether to perform interactive fusion noise optimization are as follows: Compare the obtained mixed gas stabilization time with the mixed gas stabilization time preset in the database: If the obtained mixed gas stabilization time is longer than the mixed gas stabilization time preset in the database, it is recorded as unstable adjustment and interactive fusion parameter optimization is performed; If the obtained mixed gas stabilization time is not greater than the mixed gas stabilization time preset in the database, it is recorded as stable and the interaction effectiveness analysis is completed; The specific steps of optimizing the interactive fusion parameters are as follows: The first step is to optimize the interactive fusion delay: the obtained mixed gas stabilization time deviation and fire gas release rate deviation are proportionally processed with the mixed gas stabilization time deviation and fire gas release rate deviation preset in the database. The results of the proportional processing are summed and averaged to obtain the interactive fusion delay correction value. This is used to correct the delay caused by the gas diffusion device, promote faster and more uniform distribution of fire gas, and improve the response speed of the gas diffusion device. After the interactive fusion delay is corrected, it is determined whether the re-acquired mixed gas stabilization time is not greater than the mixed gas stabilization time preset in the database. If so, the first step is completed and the interactive validity analysis is performed; otherwise, the second step is performed.

9. The multi-source data fusion method based on data analysis as claimed in claim 8, characterized in that: The second step is to perform fusion noise optimization: The mixed gas stabilization time deviation obtained after interactive fusion delay correction is mapped in the database to obtain the fusion noise improvement value, which is used to improve the noise amplitude suppression effect of the corresponding noise covariance matrix in the Kalman filter algorithm; After the interactive fusion parameter optimization, if the re-acquired mixed gas stabilization time is not greater than the mixed gas stabilization time preset in the database, the second step and the interactive effectiveness analysis are completed; otherwise, the interactive fusion parameter optimization times are determined; The specific steps of judging the interactive fusion parameter optimization times are as follows: if the interactive fusion parameter optimization times are within the prescribed interactive fusion parameter optimization times, returning to the first step; otherwise, performing interactive fusion warning.

10. A system using the multi-source data fusion method based on data analysis according to any one of claims 1 to 9, characterized in that: Including fusion real-time analysis module, dynamic fusion adaptability analysis module and interactive fusion effectiveness analysis module; The fusion real-time analysis module is used for the fire monitoring and management platform to receive fire information data sent by the Internet of Things terminal, and to perform real-time analysis on the fusion process between the fire automatic alarm equipment and the fire monitoring and management platform based on the acquired real-time fusion data to determine whether to optimize the sampling sensor frequency; The dynamic fusion adaptability analysis module is used to perform dynamic adaptability analysis on the fusion process between the transformer water spray equipment and the fire monitoring management platform based on the acquired perception fusion data to determine whether to optimize the perception fusion parameters; The interactive fusion effectiveness analysis module is used to perform interactive effectiveness analysis on the fusion process between the fire extinguishing equipment and the fire monitoring management platform according to the obtained mixed gas stabilization time, so as to determine whether to perform interactive fusion noise optimization.

Images