A personnel safety state monitoring and early warning method based on a smart wearable device

Abstract

The application relates to the technical field of basic safety supervision, and discloses a personnel safety state monitoring and early warning method based on an intelligent wearing device, the intelligent wearing device is used for personnel wearing and positioning, and key index data of a human body is collected, the personnel safety state monitoring and early warning method comprises the following steps: acquiring environmental parameter data which has a negative influence on a target person in a position environment of the target person; acquiring key index data of the target person which is affected by the environmental parameter data according to the intelligent wearing device; acquiring a danger score of the position environment according to the environmental parameter data and the key index data according to a preset processing rule, and generating a corresponding data curve graph according to the environmental parameter data and the key index data; inputting the data curve graph into an identification and judgment model, and obtaining a personnel safety danger grade by combining a risk score output by the identification and judgment model with the danger score, so that the life and property safety of underground workers is timely and reliably ensured.

Description

Technical Field

[0001] This invention relates to the field of basic safety monitoring technology, specifically to a method for monitoring and early warning of personnel safety status based on a smart wearable device. Background Technology

[0002] Coal mines are areas where humans extract coal resources in coal-rich areas, generally divided into underground coal mines and open-pit coal mines. When the coal seam is far from the surface, underground tunnels are typically dug to extract the coal; this is called an underground coal mine. When the coal seam is very close to the surface, the surface soil is typically stripped away to extract the coal; this is called an open-pit coal mine. The vast majority of coal mines in my country are underground mines. A coal mine encompasses a large area, including both above-ground and underground areas, as well as related facilities.

[0003] Underground coal mines are unique working environments where harmful gases may be generated or leaked. For example, steel mills may leak carbon monoxide, while coal mines may have excessively high levels of sulfur dioxide and carbon monoxide. Exposure to harmful gases can impair bodily functions, consciousness, and health, even causing unconsciousness; if not detected promptly, it can be fatal. Therefore, in hazardous working environments, it is crucial not only to regularly monitor the levels of specific harmful gases but also to continuously monitor the vital signs and health of personnel. Any problems must be reported immediately to facilitate appropriate measures and prevent accidents. Summary of the Invention

[0004] The purpose of this invention is to provide a method for monitoring and early warning of personnel safety status based on a smart wearable device, thereby solving the following technical problems:

[0005] How to develop a personnel safety status monitoring and early warning method based on providing high-precision and timely early warnings using smart wearable devices.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A method for monitoring and early warning of personnel safety status based on a smart wearable device, wherein the smart wearable device is worn and located by personnel, and collects key human body indicator data, including:

[0008] Obtain environmental parameter data in the target person's location environment that has a negative impact on the target person;

[0009] The key indicator data of the target person's body affected by the environmental parameter data are obtained through the smart wearable device;

[0010] According to preset processing rules, the hazard score of the location environment is obtained based on the environmental parameter data and the key indicator data, and a corresponding data curve is generated based on the environmental parameter data and the key indicator data.

[0011] The data curve is input into the identification and judgment model, and the risk score output by the identification and judgment model is combined with the hazard score to obtain the personnel safety hazard level.

[0012] Execute the corresponding early warning procedure based on the personnel safety hazard level;

[0013] The identification and judgment model includes a risk identification model and a trained neural network model; the personnel safety hazard level includes: normal, abnormal, and dangerous.

[0014] As a further aspect of the present invention: the preset identification rules include:

[0015] Within a specified time period T, the location environment of the i-th target person:

[0016] The environmental parameter data are analyzed to obtain the environmental hazard score E. i (T);

[0017] The key indicator data are analyzed to obtain the personnel status score P. i (T);

[0018] The hazard score Q is obtained based on the environmental hazard score and the personnel status score. i (T);

[0019] Q i (T)=δ1*E i (T)+δ2*P i (T)

[0020] The higher the environmental hazard score, the more dangerous the environment at the location; the higher the personnel status score, the worse the physical condition of the target personnel. δ1 and δ2 are corresponding weighting coefficients.

[0021] As a further aspect of the present invention: the environmental hazard score E i The methods for obtaining (T) include:

[0022]

[0023]

[0024] Where m represents the total number of types of environmental parameter data, E i (k) represents the risk value corresponding to the kth type of environmental parameter data, C(k) represents the average concentration data of the kth type of environmental parameter data in the specified time period T; Cs(k) is the standard safe concentration value corresponding to the kth type of environmental parameter data.

[0025] As a further aspect of the present invention: the personnel status score P i The methods for obtaining (T) include:

[0026]

[0027]

[0028] Where b represents the total number of categories of the key indicator data, P i (l) represents the risk value corresponding to the key indicator data of the lth type, H(l) represents the average value of the key indicator data of the lth type during the specified time period T; Hs(l) is the optimal value corresponding to the key indicator data of the lth type.

[0029] As a further aspect of the present invention: the method for obtaining a personnel safety hazard level by combining the risk score output by the identification and judgment model with the hazard score includes:

[0030] F i (T)=α1*Q i (T)+α2*M i

[0031] Where α1 and α2 are the corresponding weighting coefficients, M i For the aforementioned risk score, F i (T) represents the final score;

[0032] When F i (T)≤Thr F The personnel safety hazard level is normal;

[0033] When Thr F <F i (T)<γ*Thr F The personnel safety hazard level is abnormal;

[0034] When F i (T)≥γ*Thr F The personnel safety hazard level is dangerous;

[0035] Among them, Thr F γ is the preset warning threshold, and γ is the preset coefficient.

[0036] As a further aspect of the present invention: the early warning program includes:

[0037] If the safety hazard level of the personnel is normal, no alarm will be triggered.

[0038] If the safety risk level of the personnel is abnormal, initiate risk tracing.

[0039] If the safety hazard level of the personnel is deemed dangerous, initiate risk tracing and issue an alarm.

[0040] As a further aspect of the present invention: the risk tracing includes:

[0041] Determine the underground ventilation path based on the location of the target personnel who have triggered an anomaly or danger warning.

[0042] For the underground ventilation path of the target, environmental parameter data of n locations of the target personnel along the underground ventilation path are obtained in reverse ventilation direction, and a gradient sequence E is established; E = (E1, E2) i ,...E j ,...E n ), n>j>i>1;

[0043] Calculate the diffusion trend direction coefficient β and diffusion trend intensity coefficient Z based on the gradient sequence E;

[0044]

[0045]

[0046]

[0047] Among them, E i For the concentration data of a single environmental parameter at the location of the i-th target person, the Median function is the median function for the gradient sequence E; r i This indicates that in the gradient sequence E under the corresponding conditions, E satisfies j >E i The number of counts.

[0048] As a further aspect of the present invention: the risk tracing includes:

[0049] If β < 0, then reconstruct the underground ventilation path and the gradient sequence E;

[0050] If β>0, Z≤Thr Z After setting the corresponding underground ventilation path as a suspicious area, the underground ventilation path and the gradient sequence E are reconstructed, and c of the suspicious areas are broadcast as suspicious danger areas.

[0051] If β>0, Z>Thr Z Obtain the largest E in the gradient sequence E. i The corresponding location of the target personnel is designated as a dangerous location, and a broadcast is made to notify personnel near the dangerous location to evacuate.

[0052] Among them, Thr ZThis is a preset threshold for the intensity of the diffusion trend.

[0053] The beneficial effects of this invention are as follows: This invention requires underground workers to wear intelligent wearable devices capable of locating and monitoring key bodily indicators. Through sensors pre-installed at designated locations underground, environmental parameters such as carbon dioxide, carbon monoxide, and sulfur monoxide concentrations can be monitored in real time. Key indicators can include heart rate and blood oxygen concentration. By comparing environmental parameter data and key indicator data with corresponding standard values, a hazard score can be obtained. Considering the fluctuations in environmental parameter data and key indicator data over a certain period, future hazards can be predicted based on data curves and identification and judgment models. A risk score is given, representing the potential for a hazardous gas leak at a designated location that could affect the personal safety of the target personnel. Then, based on the hazard score and risk score, the safety hazard level of the designated target personnel and their location is determined, and corresponding early warning procedures are executed accordingly to ensure the timely and reliable safety of the lives and property of underground workers. Attached Figure Description

[0054] The invention will now be further described with reference to the accompanying drawings.

[0055] Figure 1 This is a flowchart illustrating the personnel safety status monitoring and early warning method of the present invention. Detailed Implementation

[0056] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0057] Please see Figure 1 As shown, this invention is a method for monitoring and early warning of personnel safety status based on a smart wearable device. The smart wearable device is used for personnel to wear and locate themselves, and collects key human body indicator data, including:

[0058] Obtain environmental parameter data in the target person's location environment that has a negative impact on the target person;

[0059] The key indicator data of the target person's body affected by the environmental parameter data are obtained through the smart wearable device;

[0060] According to preset processing rules, the hazard score of the location environment is obtained based on the environmental parameter data and the key indicator data, and a corresponding data curve is generated based on the environmental parameter data and the key indicator data.

[0061] The data curve is input into the identification and judgment model, and the risk score output by the identification and judgment model is combined with the hazard score to obtain the personnel safety hazard level.

[0062] Execute the corresponding early warning procedure based on the personnel safety hazard level;

[0063] The identification and judgment model includes a risk identification model and a trained neural network model; the personnel safety hazard level includes: normal, abnormal, and dangerous.

[0064] In this embodiment of the invention, underground workers need to wear smart wearable devices capable of locating and monitoring key bodily indicators. Sensors pre-installed at designated locations underground can monitor environmental parameters in real time, such as concentrations of carbon dioxide, carbon monoxide, and sulfur monoxide. Key indicators can include heart rate and blood oxygen concentration. By comparing environmental parameter data and key indicator data with corresponding standard values, a hazard score can be obtained. Considering the fluctuations in environmental parameter data and key indicator data over a certain period, future hazards can be predicted based on data curves and identification models. A risk score is given, representing a potential leak of hazardous gas at a designated location that could affect the personal safety of the target personnel. Then, based on the hazard score and risk score, the safety hazard level of the designated target personnel and their location is determined, and corresponding early warning procedures are executed accordingly to ensure the timely and reliable safety of the lives and property of underground workers.

[0065] As a further aspect of the present invention: the preset identification rules include:

[0066] Within a specified time period T, the location environment of the i-th target person:

[0067] The environmental parameter data are analyzed to obtain the environmental hazard score E. i (T);

[0068] The key indicator data are analyzed to obtain the personnel status score P. i (T);

[0069] The hazard score Q is obtained based on the environmental hazard score and the personnel status score. i (T);

[0070] Q i (T)=δ1*E i (T)+δ2*P i (T)

[0071] The higher the environmental hazard score, the more dangerous the environment at the location; the higher the personnel status score, the worse the physical condition of the target personnel. δ1 and δ2 are corresponding weighting coefficients.

[0072] As a further aspect of the present invention: the environmental hazard score E i The methods for obtaining (T) include:

[0073]

[0074]

[0075] Where m represents the total number of types of environmental parameter data, E i (k) represents the risk value corresponding to the kth type of environmental parameter data, C(k) represents the average concentration data of the kth type of environmental parameter data in the specified time period T; Cs(k) is the standard safe concentration value corresponding to the kth type of environmental parameter data.

[0076] As a further aspect of the present invention: the personnel status score P i The methods for obtaining (T) include:

[0077]

[0078]

[0079] Where b represents the total number of categories of the key indicator data, P i (l) represents the risk value corresponding to the key indicator data of the lth type, H(l) represents the average value of the key indicator data of the lth type during the specified time period T; Hs(l) is the optimal value corresponding to the key indicator data of the lth type.

[0080] As a further aspect of the present invention: the method for obtaining a personnel safety hazard level by combining the risk score output by the identification and judgment model with the hazard score includes:

[0081] F i (T)=α1*Q i (T)+α2*M i

[0082] Where α1 and α2 are the corresponding weighting coefficients, M i For the aforementioned risk score, F i (T) represents the final score;

[0083] When F i (T)≤Thr F The personnel safety hazard level is normal;

[0084] When Thr F <F i (T)<γ*Thr F The personnel safety hazard level is abnormal;

[0085] When F i (T)≥γ*Thr F The personnel safety hazard level is dangerous;

[0086] Among them, Thr F γ is the preset warning threshold, and γ is the preset coefficient.

[0087] As a further aspect of the present invention: the early warning program includes:

[0088] If the safety hazard level of the personnel is normal, no alarm will be triggered.

[0089] If the safety risk level of the personnel is abnormal, initiate risk tracing.

[0090] If the safety hazard level of the personnel is deemed dangerous, initiate risk tracing and issue an alarm.

[0091] As a further aspect of the present invention: the risk tracing includes:

[0092] Determine the underground ventilation path based on the location of the target personnel who have triggered an anomaly or danger warning.

[0093] For the underground ventilation path of the target, environmental parameter data of n locations of the target personnel along the underground ventilation path are obtained in reverse ventilation direction, and a gradient sequence E is established; E = (E1, E2) i ,...E j ,...E n ), n>j>i>1;

[0094] Calculate the diffusion trend direction coefficient β and diffusion trend intensity coefficient Z based on the gradient sequence E;

[0095]

[0096]

[0097]

[0098] Among them, E i For the location of the i-th target person, a single environmental parameter data point is provided. Taking carbon monoxide (CO) as an example, this single environmental parameter data represents the concentration of CO. The Median function is the median function for the gradient sequence E. iThis indicates that in the gradient sequence E under the corresponding conditions, E satisfies j >E i The number of counts.

[0099] As a further aspect of the present invention: the risk tracing includes:

[0100] If β < 0, then reconstruct the underground ventilation path and the gradient sequence E;

[0101] If β>0, Z≤Thr Z After setting the corresponding underground ventilation path as a suspicious area, the underground ventilation path and the gradient sequence E are reconstructed, and c of the suspicious areas are broadcast as suspicious danger areas.

[0102] If β>0, Z>Thr Z Obtain the largest E in the gradient sequence E. i The corresponding location of the target personnel is designated as a dangerous location, and a broadcast is made to notify personnel near the dangerous location to evacuate.

[0103] Among them, Thr Z The preset diffusion trend intensity threshold is used; in this embodiment, if β>0, Z≤Thr Z This satisfies the requirement, indicating that E is in the direction of reverse ventilation. j >E i In most cases, the differences are not significant, making it difficult to trace the source. In such cases, the only option is to broadcast notifications about the c suspicious areas as suspicious danger areas.

[0104] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A method for monitoring and early warning of personnel safety status based on a smart wearable device, wherein the smart wearable device is used for personnel to wear and locate, and to collect key human body indicator data, characterized in that, include: Obtain environmental parameter data in the target person's location environment that has a negative impact on the target person; The key indicator data of the target person's body affected by the environmental parameter data are obtained through the smart wearable device; According to preset processing rules, the hazard score of the location environment is obtained based on the environmental parameter data and the key indicator data, and a corresponding data curve is generated based on the environmental parameter data and the key indicator data. The data curve is input into the identification and judgment model, and the risk score output by the identification and judgment model is combined with the hazard score to obtain the personnel safety hazard level. Execute the corresponding early warning procedure based on the personnel safety hazard level; The identification and judgment model includes a risk identification model and a trained neural network model; the personnel safety hazard level includes: normal, abnormal, and dangerous. The preset processing rules include: Within a specified time period T, the location environment of the i-th target person: The environmental parameter data are analyzed to obtain an environmental hazard score. ; The key indicator data are analyzed to obtain personnel status scores. ; The hazard score is obtained based on the environmental hazard score and the personnel status score. ; ； The higher the environmental hazard score, the more dangerous the environment at the location; and the higher the personnel condition score, the worse the physical condition of the target personnel. and All of these are corresponding weighting coefficients.

2. The method for monitoring and early warning of personnel safety status based on a smart wearable device according to claim 1, characterized in that, The environmental hazard rating The methods for obtaining it include: ； ； Where m represents the total number of types of environmental parameter data. This represents the risk value corresponding to the kth type of environmental parameter data. This represents the average concentration data of the k-th environmental parameter during the specified time period T. The standard safe concentration value corresponding to the kth type of environmental parameter data.

3. The method for monitoring and early warning of personnel safety status based on a smart wearable device according to claim 1, characterized in that, Personnel status score The methods for obtaining it include: ； ； Where b represents the total number of categories of the key indicator data. Indicates the first The corresponding risk values ​​of the aforementioned key indicator data, Indicates that in the specified time period T, the first The average value of the key indicator data mentioned above; No. The optimal values ​​corresponding to the key indicator data mentioned above.

4. The method for monitoring and early warning of personnel safety status based on a smart wearable device according to claim 1, characterized in that, The method for obtaining a person's safety hazard level by combining the risk score output by the identification and judgment model with the hazard score includes: ； in, and For the corresponding weighting coefficients, For the aforementioned risk score, For the final score; when The personnel safety hazard level is normal; when The personnel safety hazard level is abnormal; when The personnel safety hazard level is dangerous; in, To preset the warning threshold, These are preset coefficients.

5. The method for monitoring and early warning of personnel safety status based on a smart wearable device according to claim 4, characterized in that, The early warning procedure includes: If the safety hazard level of the personnel is normal, no alarm will be triggered. If the safety risk level of the personnel is abnormal, initiate risk tracing. If the safety hazard level of the personnel is deemed dangerous, initiate risk tracing and issue an alarm.

6. The method for monitoring and early warning of personnel safety status based on a smart wearable device according to claim 5, characterized in that, The risk tracing includes: Determine the underground ventilation path based on the location of the target personnel who have triggered an anomaly or danger warning. For the underground ventilation path of the target, the environmental parameter data of the n locations of the target personnel on the underground ventilation path are obtained in the order of reverse ventilation direction, and a gradient sequence E is established; , ; Calculate the diffusion trend direction coefficient based on the gradient sequence E. and diffusion trend intensity coefficient Z; ； ； ； in, The concentration data of a single environmental parameter at the location of the i-th target person. The function is the median function for the gradient sequence E; This indicates that, under the corresponding conditions, the gradient sequence E satisfies... The number of counts.

7. The method for monitoring and early warning of personnel safety status based on a smart wearable device according to claim 6, characterized in that, The risk tracing includes: like Then, the underground ventilation path and the gradient sequence E are reconstructed; like , After setting the corresponding underground ventilation path as a suspicious area, the underground ventilation path and the gradient sequence E are reconstructed, and c of the suspicious areas are broadcast as suspicious danger areas. like , Obtain the largest gradient sequence E. The corresponding location of the target personnel is designated as a dangerous location, and a broadcast is made to notify personnel near the dangerous location to evacuate. in, This is a preset threshold for the intensity of the diffusion trend.

Images