Multi-source monitoring platform for fire-fighting simulation training

Abstract

The invention, which relates to the technical field of multi-source monitoring, discloses a fire-fighting simulation training multi-source monitoring platform comprising a data conversion module and a data integration module. The data conversion module receives fire-fighting simulation training data from different sources of the monitoring platform; then data generated by sensors or monitoring devices of different brands and models are converted into a unified XML format, meanwhile, data under different communication protocols are converted into a unified TCP / IP protocol data packet, and the data integration module carries out unified integration processing on fire-fighting simulation training data of different sources; the multi-source data is accessed, inquired and called in a unified mode, abnormal data can be automatically identified and calibrated through the quality verification module, and necessary manual adjustment can be performed on corresponding reference data in a database through the feedback calibration module, so that the accuracy and reliability of the data are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-source monitoring, and in particular to a multi-source monitoring platform for firefighting simulation training. Background Art

[0002] The multi-source monitoring platform for fire simulation training is a highly integrated system that integrates a variety of advanced monitoring technologies. It aims to implement comprehensive and detailed management and monitoring of the firefighters' training process by realistically simulating fire scenes and training environments. This platform can aggregate data from a variety of sensors, such as smoke detectors, temperature sensors, and flame detectors, to achieve three-dimensional and multi-dimensional monitoring of the training environment.

[0003] However, in actual applications, since fire simulation training environments often involve many different brands and models of sensors and monitoring equipment, these devices have significant differences in data formats and communication protocols. This difference not only hinders the smooth integration of data, but also easily leads to the emergence of information islands, thereby weakening the integrity and accuracy of the monitoring platform. More seriously, if the real-time processing of data is not sufficient, it may cause alarm delays, causing firefighters to miss the best time for rescue; and if the data accuracy is not high, it may cause false alarms or missed alarms, which will have an adverse impact on the training effect of firefighters. Summary of the invention

[0004] In response to the above situation, the present invention performs unified integrated processing of fire simulation training data from different sources, so that multi-source data can be accessed and queried in a unified manner, and can automatically identify and calibrate abnormal data, and can manually calibrate the monitoring platform effect through the summary stage after training.

[0005] The technical solution includes a data conversion module and a data integration module. The data conversion module receives fire simulation training data from different sources of the monitoring platform, and then converts the data generated by sensors or monitoring equipment of different brands and models into a unified XML format, and converts the data under different communication protocols into a unified TCP / IP protocol data packet. The data integration module integrates the converted data into a unified database, which is the data storage area of ​​the monitoring platform and is used to store all the fire simulation training data from different sources of the monitoring platform. The data is then cleaned and Kalman filtering is used to reduce random errors in the data and improve the stability of the data. At the same time, each record of the data integration is converted into a unique hash value through a hash algorithm, and data with the same hash value is regarded as duplicate data, and finally the duplicate data is deleted; The data integration module further processes the data integration. The specific steps are as follows: S1, collect the data with the same measurement parameter characteristics together, and number the collected data with the same measurement parameter characteristics in sequence X1, X2, X3...Xn; S2, calculate the mean of the data in a group , and then calculate the standard deviation of the data ; S3, when When it is greater than 0.3, locate the median of the group of data, calculate the difference between X1, X2, X3...Xn and the median in turn, filter out the data with the largest absolute difference, mark it as abnormal data, and remove this abnormal data from the group of data to form a new data group, and then repeat steps S1-S3 until Until it is less than 0.36; S4, when When it is less than 0.3, the processed data will be integrated into the buffer repository built into the data integration module. The processed data can be accessed and queried in a unified manner regardless of the source from which the data originally came.

[0006] Furthermore, it also includes a quality verification module, and the specific steps are as follows: d. Extract the time stamps t1, t2, t3...tn of the data groups X1, X2, X3...Xn, and simultaneously extract the corresponding reference data XC and the predetermined measurement time stamp tc in the database; e, calculate the error rate , and then calculate the error rates X21, X31...Xn1 in turn according to this formula. When X11, X21, X31...Xn1 are greater than 0.2, it means that the corresponding data is abnormal and marked as abnormal data. Otherwise, it is normal data and proceed to the next step; f, calculate the time error rate Then, the time error rates t21, t31...tn1 are calculated in sequence according to this formula. When t11, t21, t31...tn1 are greater than 0.5s, it indicates that the measurement time is abnormal and is marked as a timestamp abnormality. Otherwise, it indicates a normal timestamp.

[0007] Furthermore, it also includes a monitoring control module and a data visualization module. When the monitoring control module receives data marked as abnormal, it controls the data visualization module to display the IP address of the abnormal data, and notifies relevant personnel to inspect the corresponding sensor or monitoring equipment by flashing or marking the location of the abnormal data in red. The data visualization module will not cancel the flashing or red reminder mode until the detection is normal. When the monitoring control module receives data with abnormal timestamps, it will quickly replace those abnormal timestamps with tc timestamps, and immediately send out an alarm to relevant personnel through the data visualization module, prompting them to accurately calibrate the time of the sensors or monitoring equipment with problems; The monitoring control module uses the corrected timestamp data and the detected normal data as valid data for fire simulation training monitoring, and then displays them in real time and intuitively through the data visualization module. The monitoring personnel can understand the information and effects of the fire simulation training in real time and intuitively through the data visualization module.

[0008] Furthermore, it also includes a feedback calibration module. During the fire simulation training process or the summary stage after the training, once it is found that the results reflected by the monitoring data deviate from the actual training situation, the relevant technical personnel can accurately locate the abnormal data through the feedback calibration module, and use the function of the feedback calibration module to make necessary manual adjustments to the corresponding reference data in the database to ensure the accuracy and reliability of the data.

[0009] Furthermore, the wireless information transmission method involved in the multi-source monitoring platform uses 5G communication transmission; The reference data that the quality verification module relies on all come from the unified database established by the data integration module. This database not only bears the responsibility of data integration and management, but also serves as the benchmark for data calibration by the feedback calibration module.

[0010] Due to the adoption of the above technical solution, the present invention has the following advantages compared with the prior art: 1. The data integration module integrates the fire simulation training data from different sources in a unified way, so that multi-source data can be accessed and queried in a unified manner. The quality verification module can automatically identify and calibrate abnormal data, and the feedback calibration module can make necessary manual adjustments to the corresponding reference data in the database to ensure the accuracy and reliability of the data. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 The present invention is a flow chart of a multi-source monitoring platform for fire simulation training. DETAILED DESCRIPTION

[0012] The above and other technical contents, features and effects of the present invention are described in detail below with reference to the attached Figure 1 The detailed description of the embodiments will clearly show that the structural contents mentioned in the following embodiments are all based on the drawings in the specification.

[0013] In order to solve the phenomenon of information islands and improve the accuracy and real-time performance of data, based on the existing technology, a data conversion module and a data integration module are included. The data conversion module receives fire simulation training data from different sources of the monitoring platform, and then converts the data generated by sensors or monitoring equipment of different brands and models into a unified XML format, and converts the data under different communication protocols into a unified TCP / IP protocol data packet; The existence of the data integration module enables the monitoring platform to provide a global data view, which is convenient for users to analyze and mine data. At the same time, it also provides a reliable data foundation for subsequent quality verification, storage and advanced data analysis functions.

[0014] The data integration module integrates the converted data into a unified database, which is the data storage area of ​​the monitoring platform and is used to store all the fire simulation training data from different sources of the monitoring platform. The data is then cleaned and Kalman filtering is used to reduce random errors in the data and improve the stability of the data. At the same time, each record of the data integration is converted into a unique hash value through a hash algorithm, and data with the same hash value is regarded as duplicate data, and finally the duplicate data is deleted; The data integration module further processes the data integration. The specific steps are as follows: S1, collect the data with the same measurement parameter characteristics together, and number the collected data with the same measurement parameter characteristics in sequence X1, X2, X3...Xn; S2, calculate the mean of the data in a group , and then calculate the standard deviation of the data ; S3, when When it is greater than 0.3, locate the median of the group of data, calculate the difference between X1, X2, X3...Xn and the median in turn, filter out the data with the largest absolute difference, mark it as abnormal data, and remove this abnormal data from the group of data to form a new data group, and then repeat steps S1-S3 until Until it is less than 0.36; S4, when When it is less than 0.3, the processed data will be integrated into the buffer repository built into the data integration module. The processed data can be accessed and queried in a unified manner regardless of the source from which the data originally came.

[0015] Through the strict control of data by the quality verification module, the platform failure rate caused by data errors or anomalies can be effectively reduced, and the stability and reliability of the platform can be improved. The quality verification module plays an indispensable role in the multi-source monitoring platform for fire simulation training. It ensures the accuracy of data, improves data quality, guarantees training results, and promotes the stable operation of the platform.

[0016] Furthermore, it also includes a quality verification module, and the specific steps are as follows: a, extracting the time stamps t1, t2, t3...tn of the data groups X1, X2, X3...Xn, and at the same time extracting the corresponding reference data XC and the predetermined measurement time stamp tc in the database; b. Calculate the error rate , and then calculate the error rates X21, X31...Xn1 in turn according to this formula. When X11, X21, X31...Xn1 are greater than 0.2, it means that the corresponding data is abnormal and marked as abnormal data. Otherwise, it is normal data and proceed to the next step; c. Calculate the time error rate Then, the time error rates t21, t31...tn1 are calculated in sequence according to this formula. When t11, t21, t31...tn1 are greater than 0.5s, it indicates that the measurement time is abnormal and is marked as a timestamp abnormality. Otherwise, it indicates a normal timestamp.

[0017] Furthermore, it also includes a monitoring control module and a data visualization module. When the monitoring control module receives data marked as abnormal, it controls the data visualization module to display the IP address of the abnormal data, and notifies relevant personnel to inspect the corresponding sensor or monitoring equipment by flashing or marking the location of the abnormal data in red. The data visualization module will not cancel the flashing or red reminder mode until the detection is normal. When the monitoring control module receives data with abnormal timestamps, it will quickly replace those abnormal timestamps with tc timestamps, and immediately send out an alarm to relevant personnel through the data visualization module, prompting them to accurately calibrate the time of the sensors or monitoring equipment with problems; The monitoring control module uses the corrected timestamp data and the detected normal data as valid data for fire simulation training monitoring, and then displays them in real time and intuitively through the data visualization module. The monitoring personnel can understand the information and effects of the fire simulation training in real time and intuitively through the data visualization module.

[0018] The feedback calibration module can perform real-time manual verification of various fire simulation training data collected on the platform to ensure the accuracy and reliability of the data. Once deviations or errors are found in the data, the feedback calibration module can make manual corrections in a timely manner to avoid the negative impact of erroneous data on training results and decision-making analysis.

[0019] Furthermore, it also includes a feedback calibration module. During the fire simulation training process or the summary stage after the training, once it is found that the results reflected by the monitoring data deviate from the actual training situation, the relevant technical personnel can accurately locate the abnormal data through the feedback calibration module, and use the function of the feedback calibration module to make necessary manual adjustments to the corresponding reference data in the database to ensure the accuracy and reliability of the data.

[0020] Furthermore, the wireless information transmission method involved in the multi-source monitoring platform uses 5G communication transmission; The reference data that the quality verification module relies on all come from the unified database established by the data integration module. This database not only bears the responsibility of data integration and management, but also serves as the benchmark for data calibration by the feedback calibration module.

[0021] When the present invention is used specifically, on the basis of the prior art, the data conversion module receives the fire simulation training data from different sources of the monitoring platform, and then converts the data generated by sensors or monitoring equipment of different brands and models into a unified XML format, and at the same time converts the data under different communication protocols into a unified TCP / IP protocol data packet; The data integration module integrates the converted data into a unified database, which is the data storage area of ​​the monitoring platform and is used to store all the fire simulation training data from different sources of the monitoring platform. The data is then cleaned and Kalman filtering is used to reduce random errors in the data and improve data stability. At the same time, each record of the data integration is converted into a unique hash value through a hash algorithm, and data with the same hash value is regarded as duplicate data, and finally the duplicate data is deleted; the data integration module further processes the data integration.

[0022] The quality verification module extracts the time stamps t1, t2, t3...tn of the data groups X1, X2, X3...Xn, and simultaneously extracts the corresponding reference data XC and the predetermined measurement time stamp tc in the database; Calculate the error rate , and then calculate the error rates X21, X31...Xn1 in turn according to this formula. When X11, X21, X31...Xn1 are greater than 0.2, it means that the corresponding data is abnormal and marked as abnormal data. Otherwise, it is normal data and proceed to the next step; Calculate time error rate Then, the time error rates t21, t31...tn1 are calculated in sequence according to this formula. When t11, t21, t31...tn1 are greater than 0.5s, it indicates that the measurement time is abnormal and is marked as a timestamp abnormality. Otherwise, it indicates a normal timestamp.

[0023] The monitoring control module uses the corrected timestamp data and the detected normal data as valid data for fire simulation training monitoring, and then displays them in real time and intuitively through the data visualization module. The monitoring personnel can understand the information and effects of the fire simulation training in real time and intuitively through the data visualization module.

[0024] During the fire simulation training process or the summary stage after training, once it is found that the results reflected by the monitoring data deviate from the actual training situation, the relevant technical personnel will accurately locate the abnormal data through the feedback calibration module, and use the function of the feedback calibration module to make necessary manual adjustments to the corresponding reference data in the database to ensure the accuracy and reliability of the data. By adopting the above method, the fire simulation training data from different sources are uniformly integrated and processed, so that multi-source data can be accessed and queried in a unified manner, and abnormal data can be automatically identified and calibrated, and the monitoring platform effect can be manually calibrated through the summary stage after training.

[0025] The above is a further detailed description of the present invention in combination with a specific implementation method, and it cannot be determined that the specific implementation of the present invention is limited to this; for technical personnel in the technical field to which the present invention belongs and related technical fields, based on the technical solution of the present invention, the expansion and replacement of operating methods and data should all fall within the protection scope of the present invention.

Claims

1. A multi-source monitoring platform for fire simulation training, characterized in that: It includes a data conversion module and a data integration module. The data conversion module receives fire simulation training data from different sources of the monitoring platform, and then converts the data generated by sensors or monitoring equipment of different brands and models into a unified XML format, and converts the data under different communication protocols into a unified TCP / IP protocol data packet; The data integration module integrates the converted data into a unified database, which is the data storage area of ​​the monitoring platform and is used to store all the fire simulation training data from different sources of the monitoring platform. The data is then cleaned and Kalman filtering is used to reduce random errors in the data and improve the stability of the data. At the same time, each record of the data integration is converted into a unique hash value through a hash algorithm, and data with the same hash value is regarded as duplicate data, and finally the duplicate data is deleted; The data integration module further processes the data integration, and the specific steps are as follows: S1, collect the data with the same measurement parameter characteristics together, and number the collected data with the same measurement parameter characteristics in sequence X1, X2, X3...Xn; S2, calculate the mean of the data in a group , and then calculate the standard deviation of the data ; S3, when When it is greater than 0.3, locate the median of the group of data, calculate the difference between X1, X2, X3...Xn and the median in turn, filter out the data with the largest absolute difference, mark it as abnormal data, and remove this abnormal data from the group of data to form a new data group, and then repeat steps S1-S3 until Until it is less than 0.36; S4, when When it is less than 0.3, the processed data will be integrated into the buffer repository built into the data integration module. The processed data can be accessed and queried in a unified manner regardless of the source from which the data originally came.

2. According to claim 1, a multi-source monitoring platform for fire simulation training is characterized in that: It also includes a quality verification module. The specific steps are as follows: a, extracting the time stamps t1, t2, t3...tn of the data groups X1, X2, X3...Xn, and at the same time extracting the corresponding reference data XC and the predetermined measurement time stamp tc in the database; b. Calculate the error rate , and then calculate the error rates X21, X31...Xn1 in turn according to this formula. When X11, X21, X31...Xn1 are greater than 0.2, it means that the corresponding data is abnormal and marked as abnormal data. Otherwise, it is normal data and proceed to the next step; c. Calculate the time error rate Then, the time error rates t21, t31...tn1 are calculated in sequence according to this formula. When t11, t21, t31...tn1 are greater than 0.5s, it indicates that the measurement time is abnormal and is marked as a timestamp abnormality. Otherwise, it indicates a normal timestamp.

3. According to claim 2, a multi-source monitoring platform for fire simulation training is characterized in that: It also includes a monitoring control module and a data visualization module. When the monitoring control module receives data marked as abnormal, it controls the data visualization module to display the IP address of the abnormal data, and notifies relevant personnel to inspect the corresponding sensor or monitoring equipment by flashing or marking the location of the abnormal data in red. The data visualization module will not cancel the flashing or red reminder until the detection is normal; When the monitoring control module receives data with abnormal timestamps, it will quickly replace those abnormal timestamps with tc timestamps, and immediately send out an alarm to relevant personnel through the data visualization module, prompting them to accurately calibrate the time of the sensors or monitoring equipment with problems; The monitoring control module uses the corrected timestamp data and the detected normal data as valid data for fire simulation training monitoring, and then displays them in real time and intuitively through the data visualization module. The monitoring personnel can understand the information and effects of the fire simulation training in real time and intuitively through the data visualization module.

4. According to claim 3, a multi-source monitoring platform for fire simulation training is characterized in that: It also includes a feedback calibration module. During the fire simulation training process or the summary stage after the training, once it is found that the results reflected by the monitoring data deviate from the actual training situation, the relevant technical personnel can accurately locate the abnormal data through the feedback calibration module, and use the function of the feedback calibration module to make necessary manual adjustments to the corresponding reference data in the database to ensure the accuracy and reliability of the data.

5. A multi-source monitoring platform for fire simulation training according to any one of claims 1 to 4, characterized in that: The wireless information transmission method involved in this multi-source monitoring platform uses 5G communication transmission; The reference data that the quality verification module relies on all come from the unified database established by the data integration module. This database not only bears the responsibility of data integration and management, but also serves as the benchmark for data calibration by the feedback calibration module.

Images