A real-time evaluation method and system for underwater operation safety of divers
By establishing a multivariate linear regression model, using the physiological data of divers for real-time evaluation, the problem that the existing technology cannot evaluate the safety of divers underwater operations in real time is solved, and the rapid and scientific evaluation of the divers' underwater operation status is achieved, and the divers' underwater operation status is improved. Underwater safety.
Patent Information
- Application Number
- CN202210526594.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-16
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2042-05-16
AI Technical Summary
The existing diver's underwater operation safety monitoring system cannot assess the diver's status in real time, and cannot promptly know the diver's underwater operation status.
By collecting physiological data of divers at different depths and labor intensity, a multivariate linear regression model is established to determine the optimal regression model, which is used to evaluate the safety status of divers underwater operations in real time.
It realizes rapid and scientific assessment and decision-making technical support for divers underwater operation status, and can know in real time whether the diver's status is safe, improving the diver's underwater safety.
Smart Images

Figure CN114795148B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of safety monitoring, and in particular to a method and system for real-time evaluation of underwater operation safety of divers. Background Art
[0002] Diving is a special high-risk operation. When divers work underwater, they will face a series of influences, including the mechanical effects of high underwater pressure (hydrostatic pressure), the diving environment (low temperature, water flow, underwater resistance), and the effects of various gases in the breathing gas on the body under high partial pressure.
[0003] The existing underwater operation safety monitoring system for divers can monitor the hydrological parameters of the underwater environment, the gas supply of the breathing cylinders used by divers, the breathing and heart rate of divers and other vital signs in real time through the Shearwater Perdix diving computer, HKG-07A heart rate sensor and HKH-11B breathing sensor, so as to realize real-time monitoring of the diver's status and effectively protect the diver's life safety. The existing detection system can also detect the underwater blood oxygen of divers based on the wavelet filtering algorithm. The method uses the wavelet transform filtering algorithm to filter the photoelectric volume pulse wave. The wavelet transform filtering algorithm has localization characteristics in both the time domain and the frequency domain. The window size is fixed but the shape is variable. It is adaptive to the signal, which overcomes the shortcomings of the traditional filtering algorithm. It has a good filtering effect on the photoelectric volume pulse wave that is interfered by strong underwater motion artifacts and is a weak signal, so that the blood oxygen saturation can be extracted more accurately.
[0004] The existing diver monitoring system does not involve real-time safety assessment and cannot know in real time whether the diver's status is safe. Summary of the invention
[0005] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art and to provide a method and system for real-time assessment of diver's underwater operation safety. By collecting a large amount of physiological data of divers working at different depths and different labor intensities for different periods of time, a real-time assessment model for diver's underwater operation safety is established. This provides rapid and scientific assessment and decision-making technical support for diver's underwater safety operation training and task execution, and it is possible to know in real time whether the diver's status is safe.
[0006] According to one aspect of the present invention, the present invention provides a method for real-time evaluation of underwater operation safety of divers, the method comprising the following steps:
[0007] S1: Collecting real-time evaluation data of underwater operation safety and preprocessing the data;
[0008] S2: performing multiple linear regression analysis based on the preprocessed data to establish multiple regression models;
[0009] S3: Determine the optimal regression model based on the determination coefficients of the multiple regression models;
[0010] S4: Use the optimal regression model to conduct real-time safety assessment of divers’ underwater operations.
[0011] Preferably, the underwater operation safety real-time assessment data includes at least one of the following: depth depth, work intensity power, time time, heart rate hr, respiration rr and systolic and diastolic blood pressure sysbp.
[0012] Preferably, the collecting of underwater operation safety real-time assessment data and preprocessing of the data comprises:
[0013] Through diving training experiments and water tank simulation experiments, physiological data indicator signals of divers before, during and after training at different diving depths and different work intensities are collected, and the physiological indicator signals are filtered, analyzed and processed to be converted into digital information.
[0014] Preferably, determining the optimal regression model based on the coefficients of determination of the multiple regression models comprises:
[0015] The Brog physical labor intensity score was used as the dependent variable, and depth, work intensity, time, heart rate, respiration rate, systolic blood pressure and diastolic blood pressure were used as independent variables. Multiple linear regression was performed using the stepwise screening method to obtain the regression model. Based on the determination coefficient R 2 The optimal regression model is determined as:
[0016] Y=-3.89058-
[0017] 0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp
[0018] The coefficient of determination R of the regression model 2 =0.9052.
[0019] Preferably, the use of the optimal regression model to perform real-time evaluation of diver underwater operation safety includes:
[0020] During diving, the Y value is obtained by real-time monitoring of the diver's working depth, work intensity, and vital signs. According to the range of the Y value, the safe working time under the working depth and labor intensity is evaluated.
[0021] According to another aspect of the present invention, the present invention also provides a real-time evaluation system for underwater operation safety of divers, the system comprising:
[0022] A collection module, used to collect real-time evaluation data of underwater operation safety and pre-process the data;
[0023] Establishing a module for performing multiple linear regression analysis based on the preprocessed data to establish multiple regression models;
[0024] A determination module, used for determining an optimal regression model based on the determination coefficients of the multiple regression models;
[0025] An evaluation module is used to use the optimal regression model to perform real-time evaluation of the safety of divers' underwater operations.
[0026] Preferably, the underwater operation safety real-time assessment data includes at least one of the following: depth depth, work intensity power, time time, heart rate hr, respiration rr and systolic and diastolic blood pressure sysbp.
[0027] Preferably, the acquisition module acquires real-time evaluation data of underwater operation safety, and preprocesses the data including:
[0028] Through diving training experiments and water tank simulation experiments, physiological data index signals of divers before, during and after training at different diving depths and different work intensities are collected, and the physiological index signals are filtered, analyzed and processed to be converted into digital information.
[0029] Preferably, the determining module determines the optimal regression model based on the coefficients of determination of the multiple regression models, including:
[0030] The Brog physical labor intensity score was used as the dependent variable, and depth, work intensity, time, heart rate, respiration rate, systolic blood pressure and diastolic blood pressure were used as independent variables. Multiple linear regression was performed using the stepwise screening method to obtain the regression model. Based on the determination coefficient R 2 The optimal regression model is determined as:
[0031] Y=-3.89058-
[0032] 0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp
[0033] The coefficient of determination R of the regression model 2 =0.9052.
[0034] Preferably, the evaluation module uses the optimal regression model to perform real-time evaluation of diver's underwater operation safety, including:
[0035] During diving, the Y value is obtained by real-time monitoring of the diver's working depth, work intensity, and vital signs. According to the range of the Y value, the safe working time under the working depth and labor intensity is evaluated.
[0036] Beneficial effects: The present invention collects a large amount of physiological data of divers working at different depths and different labor intensities for different periods of time, and establishes a real-time evaluation model for divers' underwater operation safety. This provides rapid and scientific evaluation and decision-making technical support for divers' underwater safety operation training and task execution, and can determine in real time whether the diver's status is safe.
[0037] The features and advantages of the present invention will become clear through reference to the following drawings and detailed description of specific embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a flow chart of the real-time evaluation method for underwater operation safety of divers of the present invention;
[0039] Figure 2 It is a schematic diagram of the real-time evaluation system for underwater operation safety of divers of the present invention. DETAILED DESCRIPTION
[0040] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings 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.
[0041] Example 1
[0042] Figure 1 1 is a flow chart of the real-time evaluation method for underwater operation safety of divers of the present invention. Figure 1 As shown, the present invention provides a method for real-time evaluation of underwater operation safety of divers, the method comprising the following steps:
[0043] S1: Collect real-time evaluation data on underwater operation safety and pre-process the data.
[0044] Preferably, the data collected for real-time evaluation of underwater operation safety and preprocessing of the data include: collecting physiological data indicator signals at different diving depths and different operation intensities, before, during and after diver training through diving training experiments and water tank simulation experiments, and filtering, analyzing and converting the physiological indicator signals into digital information.
[0045] Preferably, the underwater operation safety real-time assessment data includes at least one of the following: depth depth, work intensity power, time time, heart rate hr, respiration rr and systolic and diastolic blood pressure sysbp.
[0046] Specific experimental methods include:
[0047] 1) Installation and debugging of experimental equipment
[0048] ①Build an extravehicular signal receiving platform;
[0049] ② Debug telemetry equipment and N-one equipment outside the cabin;
[0050] ③ Empty cabin debugging telemetry equipment and N-one equipment in the cabin and signal reception outside the cabin;
[0051] 2) Physical examination of divers and basic exercise load test
[0052] ①Physical examination: record the diver's age, accurately measure height and weight to 0.1cm, weight to 0.01kg, and calculate body mass index (BMI);
[0053] ②Extravehicular maximum exercise load test
[0054] The subjects first used a power bicycle, K4b2 cardiopulmonary function tester, and real-time electrocardiogram monitoring to determine the ventilation threshold (VT), maximum oxygen uptake (VO2 peak), and maximum heart rate. After two minutes of warm-up, the subjects pedaled on a power bicycle, with the workload starting at 25w and increasing by 25w per minute, maintaining the pedal speed at 60rpm until exhaustion. The total exercise time varied from person to person, approximately 8-12 minutes. During the period, VT, VO2max, and maximum heart rate were measured, and the labor intensity level was divided according to oxygen consumption, and the heart rate corresponding to each labor intensity was recorded;
[0055] 3) Monitoring of life indicators at different depths and labor intensities in the cabin
[0056] ① 30 minutes before entering the cabin, test the diver's basic heart rate, body temperature, respiratory rate, and lung function indicators;
[0057] ② The diver wears N-one's breathing, heart rate, blood pressure, blood oxygen and body temperature detection probes and rests in the cabin for 10 minutes;
[0058] ③ Slowly and evenly pressurize (pressurization speed 3m / min) to the corresponding depth (10, 20, 30m). When the predetermined depth is reached and the detection signal is stable, the subject starts pedaling the bicycle, and the bicycle speed is maintained at 60rpm. The workload starts at 25w and increases by 25w per minute, maintaining the pedal speed at 60rpm. The intensity of exercise is defined based on each person's estimated heart rate, using heart rate combined with the labor intensity table: low intensity: heart rate at 35-40% of maximum oxygen consumption, medium intensity: heart rate at 41-70% of maximum oxygen consumption, high intensity: heart rate greater than 70% of maximum oxygen consumption. Each labor intensity is maintained for 5 minutes, during which the vital indicators of each labor intensity are monitored in real time: heart rate, body temperature, respiratory rate, blood oxygen, and blood pressure (randomly select 10 time points and calculate the average value).
[0059] 4) Calculation method: Determine the average value of the vital indicators and heart rate of the diver to reach a stable state under each load. Perform correlation analysis and regression analysis on the HR, blood pressure, blood oxygen, respiratory rate, and body temperature collected under different dynamic intensities, using the brogs scale as an indicator of labor intensity, and establish regression relationship equations to calculate and analyze the mutual relationship. Take the heart rate as the variable and the vital indicators as the independent variable to find the linear regression equation. The closer the r value is to 1, the stronger the linear correlation is.
[0060] S2: Perform multiple linear regression analysis based on the preprocessed data to establish multiple regression models.
[0061] Specifically, SAS software was used to perform regression analysis on the experimental data in step 2, where depth 1 represents 5 meters, 2 represents 10 meters, 3 represents 15 meters, 4 represents 20 meters, 5 represents 25 meters, and 6 represents 30 meters. The working intensity is 1 represents 30W, 2 represents 60W, and 3 represents 90W.
[0062] The multiple regression models established are as follows:
[0063] (1) Regression model 1
[0064] Y=-0.32511-0.08306depth+1.22294power+0.00858time
[0065] Among them, Y is the score, the score is the dependent variable, depth, work intensity and time are the independent variables, and multiple linear regression is performed. The regression model is shown in the above formula.
[0066] R 2 =0.7062
[0067] (2) Regression Model 2
[0068] Y=-2.52279-0.05096depth+0.84722power+0.00647time+0.02788hr
[0069] Y is the score, with the score as the dependent variable, depth, work intensity, time and heart rate as the independent variables, and multiple linear regression is performed. The regression model is shown in the above formula
[0070] R 2 =0.7858
[0071] (3) Regression Model 3
[0072] Y=-2.59510+0.05081depth+0.82918power+0.00632time+0.02668hr+0.01002rr
[0073] Y is the score, with the score as the dependent variable, depth, work intensity, time, heart rate, and respiration as the independent variables, and multiple linear regression was performed;
[0074] R 2 =0.7882
[0075] (4) Regression Model 4
[0076] Y=-3.89058-0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp
[0077] Y is the score, with the score as the dependent variable, depth, work intensity (power), time (time), heart rate (hr), respiration (rr), systolic blood pressure and diastolic blood pressure (sysbp) as independent variables. Multiple linear regression was performed using the stepwise screening method. The regression model is shown above. Respiration and systolic blood pressure were not included in the model.
[0078] R 2 =0.9052
[0079] (5) Regression model 5
[0080] Y=78.82547-1.15102*depth+13.47619*power+0.07577*time;
[0081] Y is heart rate, with heart rate as the dependent variable, depth, work intensity, and time as independent variables, and multiple linear regression is performed. The regression model is shown in the above formula.
[0082] R 2 =0.4201.
[0083] S3: Determine the optimal regression model based on the determination coefficients of the multiple regression models.
[0084] Specifically, Brog physical labor intensity score was used as the dependent variable, depth, work intensity, time, heart rate, respiration, systolic and diastolic blood pressure as independent variables, and multiple linear regression was performed using the stepwise screening method to obtain the regression model. 2 Determine the optimal regression model. 2 The value is closest to 1, and regression model 4 is the optimal regression model:
[0085] Y=-3.89058-0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp
[0086] The coefficient of determination R of the regression model 2 =0.9052.
[0087] S4: Use the optimal regression model to conduct real-time safety assessment of divers’ underwater operations.
[0088] Specifically, during diving, the working depth, work intensity, and vital signs of the diver are monitored in real time to obtain a Y value, and according to the range of the Y value, the safe working time under the working depth and labor intensity is evaluated.
[0089] Among them, safety assessment and decision support: based on the monitoring of core body temperature, heart rate, respiration and oxygen concentration before, during and after diving operations, and based on the factors affecting diving safety and safety thresholds of various physiological parameters, automatically produce safety assessment index conclusions and operational safety decision support recommendations.
[0090] This embodiment collects a large amount of physiological data of divers working at different depths and different labor intensities for different periods of time, and establishes a real-time assessment model for divers' underwater operation safety. This provides rapid and scientific assessment and decision-making technical support for divers' underwater safety operation training and task execution, and can determine in real time whether the diver's status is safe.
[0091] Example 2
[0092] Figure 2 Schematic diagram of the real-time evaluation system for underwater operation safety of divers of the present invention. Figure 2As shown, the present invention also provides a real-time evaluation system for underwater operation safety of divers, the system comprising:
[0093] The acquisition module 201 is used to acquire real-time evaluation data of underwater operation safety and pre-process the data;
[0094] Establishing module 202, for performing multiple linear regression analysis based on the preprocessed data to establish multiple regression models;
[0095] A determination module 203, configured to determine an optimal regression model based on the coefficients of determination of the multiple regression models;
[0096] The evaluation module 204 is used to use the optimal regression model to perform real-time evaluation of the safety of divers' underwater operations.
[0097] Preferably, the underwater operation safety real-time assessment data includes at least one of the following: depth depth, work intensity power, time time, heart rate hr, respiration rr and systolic and diastolic blood pressure sysbp.
[0098] Preferably, the acquisition module 201 acquires real-time evaluation data of underwater operation safety, and preprocesses the data including:
[0099] Through diving training experiments and water tank simulation experiments, physiological data index signals of divers before, during and after training at different diving depths and different work intensities are collected, and the physiological index signals are filtered, analyzed and processed to be converted into digital information.
[0100] Preferably, the determining module 203 determines the optimal regression model based on the coefficients of determination of the multiple regression models, including:
[0101] The Brog physical labor intensity score was used as the dependent variable, and depth, work intensity, time, heart rate, respiration rate, systolic blood pressure and diastolic blood pressure were used as independent variables. Multiple linear regression was performed using the stepwise screening method to obtain the regression model. Based on the determination coefficient R 2 The optimal regression model is determined as:
[0102] Y=-3.89058-0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp
[0103] The coefficient of determination R of the regression model 2 =0.9052.
[0104] Preferably, the evaluation module 204 uses the optimal regression model to perform real-time evaluation of diver's underwater operation safety, including:
[0105] During diving, the Y value is obtained by real-time monitoring of the diver's working depth, work intensity, and vital signs. According to the range of the Y value, the safe working time under the working depth and labor intensity is evaluated.
[0106] The specific implementation process of the functions realized by each module in Example 2 of the present invention is the same as the implementation process of each step in Example 1, and will not be repeated here.
[0107] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. All equivalent structural changes made by using the contents of the present invention specification and drawings under the concept of the present invention, or directly / indirectly applied in other related technical fields are included in the patent protection scope of the present invention.
Claims
1. A real-time evaluation method for underwater operation safety of divers, characterized in that: The method comprises the following steps: S1: Collecting real-time evaluation data of underwater operation safety and preprocessing the data; S2: performing multiple linear regression analysis based on the preprocessed data to establish multiple regression models; S3: Determine the optimal regression model based on the determination coefficients of the multiple regression models; S4: using the optimal regression model to perform real-time evaluation of diver's underwater operation safety; the real-time evaluation data of underwater operation safety includes at least one of the following: depth depth, work intensity power, time time, heart rate hr, respiration rr, systolic blood pressure and diastolic blood pressure sysbp; the determination coefficient based on the multiple regression models, determining the optimal regression model includes: The Brog physical labor intensity score was used as the dependent variable, and depth, work intensity, time, heart rate, respiration, systolic blood pressure, and diastolic blood pressure were used as independent variables. Multiple linear regression was performed using the stepwise screening method to obtain the regression model. Based on the determination coefficient R 2 The optimal regression model is determined as: Y=-3.89058-0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp The coefficient of determination R of the regression model 2 =0.9052.
2. The method according to claim 1, characterized in that The collecting of underwater operation safety real-time assessment data and preprocessing of the data include: Through diving training experiments and water tank simulation experiments, physiological data indicator signals of divers before, during and after training at different diving depths and different work intensities are collected, and the physiological data indicator signals are filtered, analyzed and processed to be converted into digital information.
3. The method according to claim 1, characterized in that The method of using the optimal regression model to conduct real-time evaluation of diver's underwater operation safety includes: During diving, the Y value is obtained by real-time monitoring of the diver's working depth, work intensity, and vital signs. According to the range of the Y value, the safe working time under the working depth and labor intensity is evaluated.
4. A real-time evaluation system for underwater operation safety of divers, characterized in that: The system comprises: A collection module, used to collect real-time evaluation data of underwater operation safety and pre-process the data; Establishing a module for performing multiple linear regression analysis based on the preprocessed data to establish multiple regression models; A determination module, used to determine an optimal regression model based on the determination coefficients of the multiple regression models; The evaluation module is used to use the optimal regression model to perform a real-time evaluation of the underwater operation safety of the diver; the real-time evaluation data of the underwater operation safety includes at least one of the following: depth depth, work intensity power, time time, heart rate hr, respiration rr, systolic blood pressure and diastolic blood pressure sysbp; the determination module determines the optimal regression model based on the determination coefficients of the multiple regression models, including: The Brog physical labor intensity score was used as the dependent variable, and depth, work intensity, time, heart rate, respiration, systolic blood pressure, and diastolic blood pressure were used as independent variables. Multiple linear regression was performed using the stepwise screening method to obtain the regression model. Based on the determination coefficient R 2 The optimal regression model is determined as: Y=-3.89058-0.06511depth+0.99994power+0.00351time+0.01954hr+0.02018sysbp The coefficient of determination R of the regression model 2 =0.9052.
5. The system according to claim 4, characterized in that The acquisition module acquires real-time evaluation data of underwater operation safety, and preprocesses the data including: Through diving training experiments and water tank simulation experiments, physiological data indicator signals of divers before, during and after training at different diving depths and different work intensities are collected, and the physiological data indicator signals are filtered, analyzed and processed to be converted into digital information.
6. The system according to claim 5, characterized in that The evaluation module uses the optimal regression model to perform real-time evaluation of diver underwater operation safety, including: During diving, the Y value is obtained by real-time monitoring of the diver's working depth, work intensity, and vital signs. According to the range of the Y value, the safe working time under the working depth and labor intensity is evaluated.
Citation Information
Patent Citations
Diving garment based on safety assessment method
CN108372918A
Marine salvage operation marine environment risk assessment system
CN112434948A
