Firefighter sign monitoring and early warning method based on multivariate state estimation technology

Abstract

The invention discloses a fireman physical sign monitoring and early warning method based on a multivariate state estimation technology, relates to the technical field of fireman body abnormal state monitoring and early warning, and is realized through a vital sign acquisition device and a digital individual soldier. Comprising the following steps that S1, heart rate, respiration, body temperature, perspiration and blood oxygen data of firemen in ordinary states are collected through a vital sign collecting device, and the ordinary states comprise a daily activity state, a training state and a state after continuous training for one hour; according to the method, the physical state difference between individual firemen is comprehensively considered, the vital sign state of the individual firemen can be evaluated more accurately, early warning can be given out in advance when the body of the firemen is in a potential danger state, the digital individual soldier calculates and analyzes the data, the influence caused by network abnormity on a rescue site is avoided, and the rescue efficiency is improved. At the same time, the system can send out the alarm information of the abnormal state of the firefighter at the first time, and can send the alarm information to the digital individual terminals on other teammates and the on-site headquarters.

Description

Technical Field

[0001] The present invention relates to the technical field of firefighter abnormal physical state monitoring and early warning, and in particular to a firefighter vital sign monitoring and early warning method based on multivariate state estimation technology. Background Art

[0002] According to statistics from the Ministry of Emergency Management, since its establishment in 2018, the National Comprehensive Fire and Rescue Team has made outstanding contributions and paid great sacrifices in preventing and resolving major security risks and responding to and handling various types of disasters and accidents. In the past five years, a total of 165 fire and rescue personnel have sacrificed their precious lives in fire fighting and rescue tasks, and more than 1,300 people have been gloriously injured. Faced with complex and changeable fire and rescue scenes, it is very necessary to carry out research on individual safety protection of firefighters, especially the monitoring and early warning of the vital signs data of fighters at the front-line fire and rescue sites, so as to issue early warnings and evacuation prompts in time when the firefighters are in abnormal physical condition. It is also convenient for on-site commanders to grasp the physical condition of internal attack firefighters in real time.

[0003] The equipment for monitoring the vital signs of firefighters in the "Key Emergency Communication Equipment Construction Plan for Joint Operations in Urban Complex Buildings and Major Natural Disasters" issued by the Fire Rescue Bureau in 2022 mainly includes integrated positioning terminals and heart rate detection devices. The heart rate monitoring devices are mainly smart watches. This type of terminal has poor detection accuracy and single detection parameters. There is a lack of devices for comprehensive evaluation of firefighters' vital signs through multiple parameters.

[0004] At present, some enterprises and universities have developed multi-dimensional vital signs monitoring devices based on multiple parameters such as firefighters' body temperature, heart rate, blood oxygen, blood pressure, etc., but these devices still face shortcomings. First, the device needs to process the collected vital signs parameters of firefighters and compare them with the standard thresholds to determine the current vital sign status of the firefighters. This method can only issue an alarm after detecting an abnormality in the firefighter's physical condition, and cannot perceive and judge the abnormal physical condition of the firefighter in advance. In addition, the physical condition parameters of each firefighter are different. Some firefighters have some vital sign parameters that are inconsistent with the standard after long-term training. There will be obvious differences when comparing the accuracy values. The monitoring of the physical condition of firefighters needs to be combined with a comprehensive comparison of the vital signs parameters of each individual firefighter during daily training, and a general judgment method cannot be used; second, the data collected by the existing vital signs monitoring system needs to be transmitted back from the firefighters at the rescue scene to the rear server for processing and judgment. This requires a smooth network between the front-line rescue site and the on-site command center. Firefighters may be in areas with severe wireless signal shielding such as underground and stairwells during fire rescue. The vital signs signal may not be transmitted to the rear server in the first time, and the data transmission and processing time delay is large. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a firefighter vital sign monitoring and early warning method based on multivariate state estimation technology. In the process of monitoring the vital signs of firefighters at the rescue site, the physical condition differences between individual firefighters are comprehensively considered. By collecting the daily training data of individual firefighters as a data set and combining it with the instantaneous data collected at the rescue site for comprehensive calculation, the vital sign status of individual firefighters can be evaluated more accurately, and early warning can be issued when a firefighter's body is in a potentially dangerous state.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A firefighter vital sign monitoring and early warning method based on multivariate state estimation technology is implemented through a vital sign collection device and a digital individual soldier, comprising the following steps:

[0007] S1: The heart rate, respiration, body temperature, perspiration and blood oxygen data of firefighters in their normal state are collected through the vital signs collection device. The normal state includes daily activity state, training state and the state after 1 hour of continuous training;

[0008] S2: Clean and normalize the collected daily state data to generate the daily activity state data matrix N, the training state data matrix T and the fatigue state data matrix I. The expressions are as follows:

[0009]

[0010]

[0011] Each row in each matrix represents the collected values ​​of each collection parameter at different times, and each column represents the collected values ​​of each group of collection parameters at the same time. h ,t h 、i h Indicates the heart rate value in three states, n b ,t b 、i b Indicates the breathing value in three states, n t ,t t 、i t Indicates the body temperature values ​​in three states, n s ,t s 、i s Indicates the perspiration value in three states, n o ,t o 、i o Indicates blood oxygen values ​​in three states;

[0012] S3: Firefighters wear vital signs collection devices and digital soldiers to enter the rescue site. The vital signs collection device communicates with the digital soldiers in real time via Bluetooth or WIFI to form a firefighter body area network. The vital signs collection device collects the firefighters' wartime vital signs data in real time to generate an instantaneous vector f obs , f obs The expression is:

[0013] f obs =[f h f b f t f s f o ] T

[0014] Calculate each set of acquisition vectors and f in matrix N, matrix T and matrix I respectively obs The Euclidean distance is expressed as:

[0015]

[0016]

[0017] Select m groups with the smallest calculation results to form the wartime dynamic matrices DN, DT, and DI. The expressions are as follows:

[0018]

[0019] S4: Using the instantaneous vector f of the firefighters' physical data during war obs Combined calculations are performed with the wartime dynamic matrices DN, DT, and DI to obtain a new estimated vector f estn (Daily), f estt (Motion state), f esti (Fatigue state), the calculation formula is as follows:

[0020]

[0021] S5: Calculate the estimated vector f estn 、f estt 、f esti With the instantaneous vector f obs The Euclidean distances are d(f estn ,f obs ), d(f estt ,f obs ), d(f esti ,f obs ), the calculation formula is as follows:

[0022]

[0023]

[0024] Among them, i represents five data: heart rate, respiration, body temperature, perspiration and blood oxygen.

[0025] Take d(f estn ,f obs ), d(f estt ,f obs ), d(f esti ,f obs ) The minimum value of the three vectors is d i , when d i =d(f estn ,f obs ) when the firefighters are in their daily state, d i =d(f estt ,f obs ) when the firefighter is in motion, d i =d(f esti ,f obs ), the firefighter is in a fatigue state. When the firefighter is detected in a fatigue state for 6 consecutive times, the digital individual soldier's sound and light alarm is triggered immediately, and the firefighter's instantaneous heart rate, respiration, body temperature, perspiration and blood oxygen values ​​monitored for the 6th time are compared with the standard thresholds, and the fatigue state alarm information and vital signs comparison data are sent to the on-site command center, and the firefighter's near-eye display mask prompts the firefighter that he is too tired and should rest in time.

[0026] At the same time, calculate 6 consecutive d i The mean of the data Determine d i+1 The data of the last 6 times and the average of the previous 6 times If d i+1 ≥wd i or Where w is the correction coefficient, and it is determined that the firefighter is in an abnormal state at this time. Detecting three consecutive abnormal states triggers abnormal alarm information. The digital soldier alarms with sound, light and vibration, and sends the alarm information to the near-eye display masks of other nearby firefighters. The vital signs information data and abnormal information data are transmitted back to the on-site command center.

[0027] Preferably, in step S1, each type of daily training data needs to be collected for 5 days, 1800 seconds per day, and collected every 15 seconds, and each type of daily training data is 600 groups.

[0028] Preferably, in step S2, the formula for cleaning and normalizing the collected normal state data is:

[0029]

[0030] where fnorm is the normalized acquisition vector, f is the original acquisition vector, and f max and f min are the maximum and minimum values ​​in the acquisition vector respectively.

[0031] Preferably, the instantaneous vector f obs The data is collected every 10 seconds.

[0032] The present invention provides a firefighter vital sign monitoring and early warning method based on multivariate state estimation technology, which has the following beneficial effects:

[0033] 1. In the process of monitoring the vital signs of firefighters at the rescue site, the present invention comprehensively considers the differences in physical conditions between individual firefighters, collects individual daily training data of firefighters as a data set, and combines it with the instantaneous data collected at the rescue site for comprehensive calculation, so as to more accurately evaluate the vital signs of individual firefighters and issue early warnings when firefighters are in potential dangerous conditions.

[0034] 2. The present invention sets the data calculation and analysis process on the digital single soldier carried by the firefighter, and there is no need to transmit the data back to the rear for calculation, thus avoiding the impact of network abnormalities at the rescue site. At the same time, it can issue an alarm message of the firefighter's abnormal physical condition in the first time, and the alarm message can be sent to the digital single soldier terminals of other teammates and the on-site command center. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of equipment connection of a firefighter vital sign monitoring and early warning method based on multivariate state estimation technology of the present invention;

[0036] Figure 2 The present invention is a flow chart of a firefighter vital sign monitoring and early warning method based on multivariate state estimation technology. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] See also Figure 1-2 The present invention provides a technical solution: a firefighter vital sign monitoring and early warning method based on multivariate state estimation technology, which is implemented by a vital sign collection device and a digital soldier. The digital soldier integrates a multivariate state estimation monitoring and early warning algorithm, and uses the algorithm to process the firefighter vital sign data in real time, including the following steps:

[0039] S1: The heart rate, respiration, body temperature, perspiration and blood oxygen data of firefighters in their normal state are collected through the vital signs collection device. The normal state includes daily activity state, training state and the state after 1 hour of continuous training;

[0040] Daily activity status data refers to data when walking, sitting, and still. Training status data refers to data generated during daily training. At this time, firefighters are in a state of intense activity, and various data will change significantly compared to usual. After continuous training for 1 hour, the status data changes are more obvious and the firefighters are in a state of physical fatigue.

[0041] S2: Clean and normalize the collected daily state data to remove useless data and data seriously affected by interference, and generate daily activity state data matrix N, training state data matrix T and fatigue state data matrix I. The expressions are as follows:

[0042]

[0043] Each row in each matrix represents the collected values ​​of each collection parameter at different times, and each column represents the collected values ​​of each group of collection parameters at the same time. h ,t h 、i h Indicates the heart rate value in three states, n b ,t b 、i b Indicates the breathing value in three states, n t ,t t 、i t Indicates the body temperature values ​​in three states, n s ,t s 、i s Indicates the perspiration value in three states, n o ,t o 、i o Indicates blood oxygen values ​​in three states;

[0044] S3: Firefighters wear vital signs collection devices and digital soldiers to enter the rescue site. The vital signs collection device communicates with the digital soldiers in real time via Bluetooth or WIFI to form a firefighter body area network. The vital signs collection device collects the firefighters' wartime vital signs data in real time to generate an instantaneous vector f obs , f obs The expression is:

[0045] f obs =[f h f b f t f s f o ] T

[0046] Calculate each set of acquisition vectors and f in matrix N, matrix T and matrix I respectively obs The Euclidean distance is expressed as:

[0047]

[0048] Select m groups with the smallest calculation results to form the wartime dynamic matrices DN, DT, and DI. The expressions are as follows:

[0049]

[0050]

[0051] S4: Using the instantaneous vector f of the firefighters' physical data during war obs Combined calculations are performed with the wartime dynamic matrices DN, DT, and DI to obtain a new estimated vector f estn (Daily), f estt (Motion state), f esti (Fatigue state), the calculation formula is as follows:

[0052]

[0053] S5: Calculate the estimated vector f estn 、f estt 、f esti With the instantaneous vector f obs The Euclidean distances are d(f estn ,f obs ), d(f estt ,f obs ), d(f esti ,f obs ), the calculation formula is as follows:

[0054]

[0055] Among them, i represents five data: heart rate, respiration, body temperature, perspiration and blood oxygen.

[0056] Take d(f estn ,f obs ), d(f estt ,f obs ), d(f esti ,f obs ) The minimum value of the three vectors is d i , when d i =d(f estn ,f obs ) when the firefighters are in their daily state, d i =d(f estt ,f obs) when the firefighter is in motion, d i =d(f esti ,f obs ), the firefighter is in a fatigue state. When the firefighter is detected in a fatigue state for 6 consecutive times, the digital individual soldier's sound and light alarm is triggered immediately, and the firefighter's instantaneous heart rate, respiration, body temperature, perspiration and blood oxygen values ​​monitored for the 6th time are compared with the standard thresholds, and the fatigue state alarm information and vital signs comparison data are sent to the on-site command center, and the firefighter's near-eye display mask prompts the firefighter that he is too tired and should rest in time.

[0057] At the same time, calculate 6 consecutive d i The mean of the data Determine d i+1 The data of the last 6 times and the average of the previous 6 times If d i+1 ≥wd i or Where w is the correction coefficient, and it is determined that the firefighter is in an abnormal state at this time. Detecting three consecutive abnormal states triggers abnormal alarm information. The digital soldier alarms with sound, light and vibration, and sends the alarm information to the near-eye display masks of other nearby firefighters. The vital signs information data and abnormal information data are transmitted back to the on-site command center.

[0058] As an embodiment of the present invention, in step S1, each type of daily training data needs to be collected for 5 days, 1800 seconds per day, and collected every 15 seconds. Each type of daily training data is 600 groups. After output cleaning, the valid data is less than 600 groups.

[0059] As an embodiment of the present invention, in step S2, the formula for cleaning and normalizing the collected normal state data is:

[0060]

[0061] where f norm is the normalized acquisition vector, f is the original acquisition vector, and f max and f min are the maximum and minimum values ​​in the collected vector respectively. Since the collected data such as heart rate and body temperature have different dimensions and the data variation range is also quite different, normalization processing is required to retain the variation and distribution law of the original data.

[0062] As an embodiment of the present invention, when firefighters are performing tasks at a fire scene / rescue scene, considering the computing power of a digital soldier and in order to timely detect the physical fatigue and abnormal information of the firefighters, the instantaneous vector f obs The data is collected every 10 seconds.

[0063] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A firefighter vital sign monitoring and early warning method based on multivariate state estimation technology, characterized in that: This is achieved through a vital signs collection device and a digital soldier, including the following steps: S1: The heart rate, respiration, body temperature, perspiration and blood oxygen data of firefighters in their normal state are collected through the vital signs collection device. The normal state includes daily activity state, training state and the state after 1 hour of continuous training; S2: Clean and normalize the collected daily state data to generate the daily activity state data matrix N, the training state data matrix T and the fatigue state data matrix I. The expressions are as follows: Each row in each matrix represents the collection value of each collection parameter at different times, k is the time, and each column represents the collection value of each group of collection parameters at the same time, n h ,t h 、i h Indicates the heart rate value in three states, n b ,t b 、i b Indicates the breathing value in three states, n t ,t t 、i t Indicates the body temperature values ​​in three states, n s ,t s 、i s Indicates the perspiration value in three states, n o ,t o 、i o Indicates blood oxygen values ​​in three states; S3: Firefighters wear vital signs collection devices and digital soldiers to enter the rescue site. The vital signs collection device communicates with the digital soldiers in real time via Bluetooth or WIFI to form a firefighter body area network. The vital signs collection device collects the firefighters' wartime vital signs data in real time to generate an instantaneous vector f obs , f obs The expression is: f obs =[f h f b f t f s f o ] T Calculate each set of acquisition vectors and f in matrix N, matrix T and matrix I respectively obs The Euclidean distance is expressed as: Select m groups of data with the smallest calculation results to form the wartime dynamic matrices DN, DT, and DI. The expressions are as follows: S4: Using the instantaneous vector f of the firefighters' physical data during war obs Combined calculations are performed with the wartime dynamic matrices DN, DT, and DI to obtain a new estimation vector f estn (Daily), f estt (Motion state), f esti (Fatigue state), the calculation formula is as follows: S5: Calculate the estimated vector f estn 、f estt 、f esti With the instantaneous vector f obs The Euclidean distances are d(f estn ,f obs ), d(f estt ,f obs ), d(f esti ,f obs ), the calculation formula is as follows: Among them, i represents five data: heart rate, respiration, body temperature, perspiration and blood oxygen. Take d(f estn ,f obs ), d(f estt ,f obs ), d(f esti ,f obs ) The minimum value of the three vectors is d i , when d i =d(f estn ,f obs ) when the firefighters are in their daily state, d i =d(f estt ,f obs ) when the firefighter is in motion, d i =d(f esti ,f obs ), the firefighter is in a fatigue state. When the firefighter is detected in a fatigue state for 6 consecutive times, the digital individual soldier's sound and light alarm is triggered immediately, and the firefighter's instantaneous heart rate, respiration, body temperature, perspiration and blood oxygen values ​​monitored for the 6th time are compared with the standard thresholds, and the fatigue state alarm information and vital signs comparison data are sent to the on-site command center, and the firefighter's near-eye display mask prompts the firefighter that he is too tired and should rest in time. At the same time, calculate 6 consecutive d i The mean of the data Determine d i+1 The data of the last 6 times and the average of the previous 6 times If d i+1 ≥wd i or Where w is the correction coefficient, and it is determined that the firefighter is in an abnormal state at this time. Detecting three consecutive abnormal states triggers abnormal alarm information. The digital soldier alarms with sound, light and vibration, and sends the alarm information to the near-eye display masks of other nearby firefighters. The vital signs information data and abnormal information data are transmitted back to the on-site command center.

2. The firefighter vital sign monitoring and early warning method based on multivariate state estimation technology according to claim 1 is characterized in that: In step S1, each type of daily training data needs to be collected for 5 days, 1800 seconds per day, and collected every 15 seconds. Each type of daily training data is 600 groups.

3. The firefighter vital sign monitoring and early warning method based on multivariate state estimation technology according to claim 1 is characterized in that: In step S2, the formula for cleaning and normalizing the collected normal state data is: where f norm is the normalized acquisition vector, f is the original acquisition vector, and f max and f min are the maximum and minimum values ​​in the acquisition vector respectively.

4. The firefighter vital sign monitoring and early warning method based on multivariate state estimation technology according to claim 1 is characterized in that: Instantaneous vector f obs The data is collected every 10 seconds.

Images