High-altitude falling accident detection method and system based on intelligent safety helmet

Abstract

The invention discloses a high-altitude falling accident detection method and system based on an intelligent safety helmet, and the method comprises the following steps: S1, installing a GPS positioner, an accelerometer, a gyroscope, a barometer and other sensors in the intelligent safety helmet in advance, and enabling a maintainer to wear the intelligent safety helmet on the head when the maintainer works; s2, monitoring the posture, the motion state and the environment condition of the wearer in real time through the sensor installed in the S1, and transmitting the collected data to a central processing unit. By monitoring the posture, the motion state and the environment condition of the wearer in real time and performing real-time processing and analysis, whether the risk of high-altitude falling exists or not can be effectively detected, and when a high-altitude falling accident possibly occurs, an alarm can be timely given to remind personnel and take emergency measures according to the danger level, so that accident injuries are reduced, and the use requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of high-altitude fall accident detection, and in particular to a high-altitude fall accident detection method and system based on a smart safety helmet. Background Art

[0002] During the power construction process, workers are required to climb high places to carry out construction. In order to improve safety, workers need to wear safety helmets when working at high altitudes. Due to the complexity of the construction environment, workers often accidentally fall from high altitudes. Among them, smart safety helmets have matured in the interaction of personnel positioning, personnel status information and management systems. How can workers automatically detect high-altitude falling accidents through the smart safety helmets worn by workers, and take timely response measures to falling accidents, has become a problem that needs to be solved. For this reason, we propose a high-altitude falling accident detection method and system based on smart safety helmets. Summary of the invention

[0003] Based on the technical problems existing in the background technology, the present invention proposes a high-altitude fall accident detection method and system based on a smart safety helmet.

[0004] The invention proposes a high-altitude fall accident detection method based on a smart safety helmet, comprising the following steps:

[0005] S1: A GPS locator, accelerometer, gyroscope, barometer and other sensors are installed in the smart helmet in advance, and the maintenance personnel wear the smart helmet on their heads when working;

[0006] S2: monitors the wearer's posture, movement status and environmental conditions in real time through the sensors installed in S1, and transmits the collected data to the central processor;

[0007] S3: The central processor processes and analyzes the data received in S2 in real time, and uses the support vector machine algorithm to determine the wearer's movement trajectory and physical condition, and detects whether there is a risk of falling from a high altitude;

[0008] S4: When it is detected that the wearer may fall from a high altitude, an alarm is triggered immediately, and an alarm signal is sent to relevant staff or the monitoring center;

[0009] S5: The control unit controls the emergency stop device to implement emergency measures, automatically cut off the power supply of the working equipment or trigger the safety rope to unlock, reducing accident injuries;

[0010] S6: The wearer's location information is transmitted to the cloud monitoring center in real time through the GPS module, and the monitoring personnel dispatch rescue personnel to the scene according to the situation;

[0011] S7: The central processor records the wearer's movement trajectory and behavior data through the data analysis and recording module for post-analysis and accident cause tracing to improve safety management level.

[0012] Preferably, in S2, the accelerometer is used to monitor the acceleration of the wearer, that is, the rate of change of velocity. When the wearer is exercising or making a sudden movement, the accelerometer will measure the change of acceleration, thereby judging the posture and motion state of the wearer. The accelerometer measures the acceleration of the wearer in three-dimensional space, which is usually expressed as a three-dimensional vector (ax, ay, az), and its mathematical expression is: [a=\sqrt{a_x^2+a_y^2+a_z^2}], where a represents the magnitude of acceleration;

[0013] The gyroscope is used to monitor the wearer's angular velocity, that is, the speed of rotation. By measuring the rotation and tilt of the wearer's head, the wearer's head position and posture changes can be determined. The mathematical expression used is: [ω=\sqrt{ω_x^2+ω_y^2+ω_z^2}], which is expressed as a three-dimensional vector (ωx, ωy, ωz), corresponding to the rotation speed around the x, y, and z axes respectively;

[0014] The barometer is used to monitor the air pressure at the wearer's location. In a high-altitude environment, the air pressure will change accordingly with the change in altitude, thereby inferring the change in altitude and altitude, and then detecting the wearer's altitude change. The mathematical expression used is: [h=\frac{(P_0-P)}{ρ\cdotg}], where h represents altitude, 0P0 represents reference air pressure, ρ represents air density, and g represents gravitational acceleration.

[0015] Preferably, in S3, a support vector machine algorithm is used to determine the movement trajectory and physical state of the wearer to detect whether there is a risk of falling from a high altitude. The specific judgment logic steps are as follows:

[0016] S301: extracting features from the data received by the central processor, including the wearer's posture, movement speed, rotation angle, and height change, as input to the support vector machine algorithm;

[0017] S302: Mark samples in the received data set according to pre-defined labels, for example, a normal motion state is 0, and a high-altitude fall risk is 1;

[0018] S303: Divide the data set marked in S302 into a training set and a test set, train a support vector machine model on the training set, and verify the model performance on the test set;

[0019] S304: Input the feature data extracted in S301 into the trained support vector machine model, and perform a risk assessment on the wearer's current state based on the output result of the support vector machine model to determine whether the wearer's current motion state has a risk of falling from a height.

[0020] Preferably, in S5, before the emergency stop device automatically cuts off the power supply of the working equipment or triggers the unlocking of the safety rope, it is necessary to judge the danger level of falling from a height, and the judgment logic steps are as follows:

[0021] S501: transmitting data indicating the risk of falling from a height to a central processor for analysis and processing, and evaluating the data according to threshold algorithms and rules to determine the danger;

[0022] S502: Classify the danger signals into different levels of risk, including low risk, medium risk or high risk, according to the results of data analysis and pre-set danger level standards;

[0023] S503: For each danger level, the central processor sets a trigger condition to determine whether immediate measures need to be taken, and the trigger condition includes the duration and degree of the danger signal, etc.;

[0024] S504: Based on the danger level analyzed in S502 and the triggering conditions set in S503, the central processing unit evaluates the urgency of the dangerous situation and determines whether it is necessary to immediately trigger the emergency stop device to execute safety measures.

[0025] Preferably, in S502, the low risk standard is: there may be potential danger, but the impact on the safety of the wearer is small, and no emergency measures need to be taken immediately, for example, the low-speed posture change or altitude change is within an acceptable range;

[0026] The standard for medium risk is: there is an obvious danger that requires close attention and timely response, for example, the wearer's acceleration and posture change greatly, the height changes quickly, and there may be a risk of falling from a height;

[0027] The standard for high risk is: there is a serious danger and emergency measures need to be taken immediately to protect the wearer's safety, such as a sudden sharp drop in height, the wearer shows signs of losing control, and there is a clear risk of falling.

[0028] Preferably, in S7, the central processing unit can visualize the recorded motion trajectory and behavior data, such as drawing a trajectory graph, a curve graph, etc., to help the user intuitively understand the wearer's motion situation, wherein the least squares method can be used to fit a smooth trajectory curve graph to show the trend and change of the motion path. The least squares method is given a set of n data points (xi, yi), and fits an m-order polynomial function f(x) = a0 + a1x + a2x2 + ... + amxm. The goal of the least squares method is to minimize the residual sum of squares, that is, to minimize the sum of squares of the errors between the fitting function and the actual data points;

[0029] Its mathematical expression is: [\min_{a_0,a_1,\ldots,a_m}\sum_{i=1}^{n}(y_i-f(x_i))^2];

[0030] Where mina0,a1,…,am means minimizing the parameters 0,1,…,a0,a1,…,am. It means to sum the index i of the data point from 1 to n, that is, to accumulate all the data points. y_i-f(x_i))^2: It means the square of the residual of each data point (xi,yi), that is, the square of the difference between the actual observed value yi and the value given by the fitting function f(xi).

[0031] The present invention also proposes a high-altitude fall accident detection system based on a smart helmet, comprising a smart helmet, a cloud monitoring center and a central processor;

[0032] The smart helmet includes a sensor monitoring and acquisition module;

[0033] The cloud monitoring center includes real-time monitoring and rescue modules;

[0034] The central processing unit includes a data processing and analysis module, a control unit, a high-altitude fall warning module, an emergency stop module and a data recording and analysis module.

[0035] Preferably, the sensor monitoring and acquisition module uses a GPS locator, an accelerometer, a gyroscope and a barometer to monitor and collect data on the wearer's position, posture, motion state and environmental conditions, and transmits the collected data to the data processing and analysis module;

[0036] The real-time monitoring and rescue module is used to monitor the wearer's condition, and the monitoring personnel dispatch rescue personnel to the scene according to the situation;

[0037] The data processing and analysis module is used to process and analyze the received data in real time, and use the support vector machine algorithm to determine the wearer's movement trajectory and physical condition, and detect whether there is a risk of falling from a high altitude;

[0038] The control unit is used to control the emergency stop module, and the high-altitude fall warning module is used to send an alarm signal to relevant staff or a monitoring center;

[0039] The emergency stop module is used to automatically cut off the power supply of the working equipment or trigger the unlocking of the safety rope to reduce accident injuries;

[0040] The data recording and analysis module is used to record the wearer's movement trajectory and behavior data, and present them visually to help the user intuitively understand the wearer's movement status.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention can effectively detect whether there is a risk of falling from a height by monitoring the wearer's posture, movement status and environmental conditions in real time and performing real-time processing and analysis. When a high-altitude fall accident may occur, the present invention can promptly alarm and remind personnel and implement emergency measures according to the danger level, thereby reducing accident injuries and meeting usage requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flow chart of a high-altitude fall accident detection method based on a smart safety helmet proposed by the present invention;

[0044] Figure 2 This is a block diagram of a high-altitude fall accident detection system based on a smart safety helmet proposed by the present invention. DETAILED DESCRIPTION

[0045] The present invention will be further explained below in conjunction with specific embodiments.

[0046] Embodiment 1

[0047] Reference Figure 1 This embodiment proposes a high-altitude fall accident detection method based on a smart safety helmet, comprising the following steps:

[0048] S1: A GPS locator, accelerometer, gyroscope, barometer and other sensors are installed in the smart helmet in advance, and the maintenance personnel wear the smart helmet on their heads when working;

[0049] S2: The wearer's posture, motion state and environmental conditions are monitored in real time through the sensors installed in S1, and the collected data is transmitted to the central processor. The accelerometer is used to monitor the wearer's acceleration, that is, the rate of change of velocity. When the wearer exercises or makes a sudden movement, the accelerometer will measure the change in acceleration, thereby judging the wearer's posture and motion state. The accelerometer measures the wearer's acceleration in three-dimensional space, which is usually expressed as a three-dimensional vector (ax, ay, az), and its mathematical expression is: [a=\sqrt{a_x^2+a_y^2+a_z^2}], where a represents the magnitude of acceleration;

[0050] The gyroscope is used to monitor the wearer's angular velocity, that is, the speed of rotation. By measuring the rotation and tilt of the wearer's head, the wearer's head position and posture changes can be determined. The mathematical expression used is: [ω=\sqrt{ω_x^2+ω_y^2+ω_z^2}], which is expressed as a three-dimensional vector (ωx, ωy, ωz), corresponding to the rotation speed around the x, y, and z axes respectively;

[0051] The barometer is used to monitor the air pressure at the wearer's location. In a high-altitude environment, the air pressure will change accordingly with the change of altitude, thereby inferring the change of altitude and altitude, and then detecting the wearer's altitude change. The mathematical expression used is: [h=\frac{(P_0-P)}{ρ\cdotg}], where h represents the altitude, 0P0 represents the reference air pressure, ρ represents the air density, and g represents the acceleration of gravity;

[0052] S3: The central processor processes and analyzes the data received in S2 in real time, and uses the support vector machine algorithm to determine the wearer's movement trajectory and physical condition, and detects whether there is a risk of falling from a high altitude. The logical steps of using the support vector machine algorithm for judgment are as follows:

[0053] S301: extracting features from the data received by the central processor, including the wearer's posture, movement speed, rotation angle, and height change, as input to the support vector machine algorithm;

[0054] S302: Mark samples in the received data set according to pre-defined labels, for example, a normal motion state is 0, and a high-altitude fall risk is 1;

[0055] S303: Divide the data set marked in S302 into a training set and a test set, train a support vector machine model on the training set, and verify the model performance on the test set;

[0056] S304: Input the feature data extracted in S301 into the trained support vector machine model, and perform risk assessment on the wearer's current state according to the output result of the support vector machine model to determine whether the wearer's current motion state has a risk of falling from a high altitude;

[0057] S4: When it is detected that the wearer may fall from a high altitude, an alarm is triggered immediately, and an alarm signal is sent to relevant staff or the monitoring center;

[0058] S5: The control unit controls the emergency stop device to implement emergency measures, automatically cut off the power supply of the working equipment or trigger the safety rope to unlock, reducing accident injuries;

[0059] Before the emergency stop device automatically cuts off the power supply of the working equipment or triggers the unlocking of the safety rope, it is necessary to judge the danger level of falling from a height. The judgment logic steps are as follows:

[0060] S501: transmitting data indicating the risk of falling from a height to a central processor for analysis and processing, and evaluating the data according to threshold algorithms and rules to determine the danger;

[0061] S502: According to the results of data analysis and the pre-set danger level standards, the danger signals are classified into different levels of risk, including low risk, medium risk or high risk, where the low risk standard is: potential danger may exist, but the impact on the wearer's safety is small and no emergency measures need to be taken immediately, for example, low-speed posture changes or altitude changes are within an acceptable range;

[0062] The standard for medium risk is: there is an obvious danger that requires close attention and timely response, for example, the wearer's acceleration and posture change greatly, the height changes quickly, and there may be a risk of falling from a height;

[0063] The standard for high risk is: there is a serious danger and emergency measures need to be taken immediately to protect the wearer's safety, such as a sudden drop in height, the wearer shows signs of losing control, and there is an obvious risk of falling;

[0064] S503: For each danger level, the central processor sets a trigger condition to determine whether immediate measures need to be taken, and the trigger condition includes the duration and degree of the danger signal, etc.;

[0065] S504: Based on the danger level analyzed in S502 and the triggering condition set in S503, the central processor evaluates the urgency of the dangerous situation and determines whether it is necessary to immediately trigger the emergency stop device to execute safety measures;

[0066] S6: The wearer's location information is transmitted to the cloud monitoring center in real time through the GPS module, and the monitoring personnel dispatch rescue personnel to the scene according to the situation;

[0067] S7: The central processor records the wearer's movement trajectory and behavior data through the data analysis and recording module for post-analysis and accident cause tracing to improve safety management level;

[0068] The central processing unit can visualize the recorded motion trajectory and behavior data, such as drawing trajectory graphs, curve graphs, etc., to help users intuitively understand the wearer's motion situation. The least squares method can be used to fit a smooth trajectory curve graph to show the trend and change of the motion path. The least squares method is given a set of n data points (xi, yi), and fits an m-order polynomial function f(x) = a0+a1x+a2x2+…+amxm. The goal of the least squares method is to minimize the residual sum of squares, that is, to minimize the sum of squares of the errors between the fitting function and the actual data points;

[0069] Its mathematical expression is: [\min_{a_0,a_1,\ldots,a_m}\sum_{i=1}^{n}(y_i-f(x_i))^2];

[0070] Where mina0,a1,…,am means minimizing the parameters 0,1,…,a0,a1,…,am. Indicates the summation operation of the index i of the data point from 1 to n, that is, the accumulation of all data points, y_i-f(x_i))^2: represents the square of the residual of each data point (xi,yi), that is, the square of the difference between the actual observed value yi and the value given by the fitting function f(xi);

[0071] This embodiment can effectively detect whether there is a risk of falling from a height by real-time monitoring of the wearer's posture, movement status and environmental conditions and performing real-time processing and analysis. When a high-altitude fall accident may occur, it can promptly alarm and remind personnel and implement emergency measures according to the level of danger to reduce accident injuries and meet usage requirements.

[0072] Embodiment 2

[0073] Reference Figure 2 ,This embodiment proposes a high altitude fall accident detection system based on a smart helmet, including a smart helmet, a cloud monitoring center and a central processor;

[0074] The smart helmet includes a sensor monitoring and acquisition module, wherein the sensor monitoring and acquisition module uses a GPS locator, an accelerometer, a gyroscope and a barometer to monitor and collect data on the wearer's position, posture, motion state and environmental conditions respectively;

[0075] The cloud monitoring center includes real-time monitoring and rescue modules, which are used to monitor the wearer's condition. The monitoring personnel dispatch rescue personnel to the scene according to the situation.

[0076] The central processing unit includes a data processing and analysis module, a control unit, a high-altitude fall warning module, an emergency stop module, and a data recording and analysis module;

[0077] The data processing and analysis module is used to process and analyze the received data in real time, and use the support vector machine algorithm to determine the wearer's movement trajectory and physical condition, and detect whether there is a risk of falling from a height. The control unit is used to control the emergency stop module. The high-altitude fall warning module is used to send an alarm signal to relevant staff or the monitoring center. The emergency stop module is used to automatically cut off the power supply of the working equipment or trigger the unlocking of the safety rope to reduce accident injuries; the data recording and analysis module is used to record the wearer's movement trajectory and behavior data, and present it visually to help users intuitively understand the wearer's movement status.

[0078] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A high-altitude fall accident detection method based on a smart safety helmet, characterized in that: The following steps are involved: S1: A GPS locator, an accelerometer, a gyroscope and a barometer are pre-installed in the smart helmet, and the maintenance personnel wear the smart helmet on their heads when working; S2: monitors the wearer's posture, movement status and environmental conditions in real time through the sensors installed in S1, and transmits the collected data to the central processor; S3: The central processor processes and analyzes the data received in S2 in real time, and uses the support vector machine algorithm to determine the wearer's movement trajectory and physical condition, and detects whether there is a risk of falling from a high altitude; S4: When it is detected that the wearer may fall from a high altitude, an alarm is triggered immediately, and an alarm signal is sent to relevant staff or the monitoring center; S5: The control unit controls the emergency stop device to implement emergency measures, automatically cut off the power supply of the working equipment or trigger the safety rope to unlock, reducing accident injuries; S6: The wearer's location information is transmitted to the cloud monitoring center in real time through the GPS module, and the monitoring personnel dispatch rescue personnel to the scene according to the situation; S7: The central processor records the wearer's movement trajectory and behavior data through the data analysis and recording module for post-analysis and accident cause tracing to improve safety management level.

2. The high-altitude fall accident detection method based on the smart safety helmet according to claim 1 is characterized in that: In S2, the accelerometer is used to monitor the acceleration of the wearer, that is, the rate of change of velocity. When the wearer is exercising or making a sudden movement, the accelerometer will measure the change of acceleration, thereby judging the posture and motion state of the wearer. The accelerometer measures the acceleration of the wearer in three-dimensional space, which is usually expressed as a three-dimensional vector (ax, ay, az), and its mathematical expression is: [a=\sqrt{a_x^2+a_y^2+a_z^2}], where a represents the magnitude of acceleration; The gyroscope is used to monitor the wearer's angular velocity, that is, the speed of rotation. By measuring the rotation and tilt of the wearer's head, the wearer's head position and posture changes can be determined. The mathematical expression used is: [ω=\sqrt{ω_x^2+ω_y^2+ω_z^2}], which is expressed as a three-dimensional vector (ωx, ωy, ωz), corresponding to the rotation speed around the x, y, and z axes respectively; The barometer is used to monitor the air pressure at the wearer's location. In a high-altitude environment, the air pressure will change accordingly with the change in altitude, thereby inferring the change in altitude and altitude, and then detecting the wearer's altitude change. The mathematical expression used is: [h=\frac{(P_0-P)}{ρ\cdotg}], where h represents altitude, 0P0 represents reference air pressure, ρ represents air density, and g represents gravitational acceleration.

3. The high-altitude fall accident detection method based on the smart safety helmet according to claim 1 is characterized in that: In S3, the support vector machine algorithm is used to judge the movement trajectory and physical state of the wearer to detect whether there is a risk of falling from a high altitude. The specific judgment logic steps are as follows: S301: extracting features from the data received by the central processor, including the wearer's posture, movement speed, rotation angle and height change features, as input to the support vector machine algorithm; S302: Label samples in the received data set according to pre-defined labels; S303: Divide the data set marked in S302 into a training set and a test set, train a support vector machine model on the training set, and verify the model performance on the test set; S304: Input the feature data extracted in S301 into the trained support vector machine model, and perform a risk assessment on the wearer's current state based on the output result of the support vector machine model to determine whether the wearer's current motion state has a risk of falling from a height.

4. The high-altitude fall accident detection method based on the smart safety helmet according to claim 1 is characterized in that: In S5, before the emergency stop device automatically cuts off the power supply of the working equipment or triggers the unlocking of the safety rope, it is necessary to judge the danger level of falling from a height, and the judgment logic steps are as follows: S501: transmitting data indicating the risk of falling from a height to a central processor for analysis and processing, and evaluating the data according to threshold algorithms and rules to determine the danger; S502: Classify the danger signals into different levels of risk, including low risk, medium risk or high risk, according to the results of data analysis and pre-set danger level standards; S503: For each danger level, the central processor sets a trigger condition to determine whether immediate action is required, and the trigger condition includes the duration and degree of the danger signal; S504: Based on the danger level analyzed in S502 and the triggering conditions set in S503, the central processing unit evaluates the urgency of the dangerous situation and determines whether it is necessary to immediately trigger the emergency stop device to execute safety measures.

5. The high-altitude fall accident detection method based on the smart safety helmet according to claim 4 is characterized in that: In S502, the low risk standard is: there may be potential danger, but the impact on the safety of the wearer is small, and no emergency measures need to be taken immediately; The criteria for medium risk are: there is an obvious danger that requires close attention and timely response; The high-risk standard is: there is a serious danger and emergency measures need to be taken immediately to protect the wearer's safety.

6. The high-altitude fall accident detection method based on the smart safety helmet according to claim 1 is characterized in that: In the S7, the central processor can visualize the recorded motion trajectory and behavior data to help the user intuitively understand the wearer's motion situation, wherein the least squares method can be used to fit a smooth trajectory curve graph to show the trend and change of the motion path. The least squares method is given a set of n data points (xi, yi), and fits an m-order polynomial function f(x) = a0 + a1x + a2x2 + ... + amxm. The goal of the least squares method is to minimize the residual sum of squares, that is, to minimize the sum of squares of the errors between the fitting function and the actual data points; Its mathematical expression is: [\min_{a_0,a_1,\ldots,a_m}\sum_{i=1}^{n}(y_i-f(x_i))^2]; Where mina0,a1,…,am means minimizing the parameters 0,1,…,a0,a1,…,am. It means to sum the index i of the data point from 1 to n, that is, to accumulate all the data points. y_i-f(x_i))^2: It means the square of the residual of each data point (xi,yi), that is, the square of the difference between the actual observed value yi and the value given by the fitting function f(xi).

7. A high-altitude fall accident detection system based on a smart safety helmet, used to implement the method described in any one of claims 1 to 6, characterized in that: Includes smart helmet, cloud monitoring center and central processing unit; The smart helmet includes a sensor monitoring and acquisition module; The cloud monitoring center includes real-time monitoring and rescue modules; The central processing unit includes a data processing and analysis module, a control unit, a high-altitude fall warning module, an emergency stop module and a data recording and analysis module.

8. The high-altitude fall accident detection system based on the smart safety helmet according to claim 7 is characterized in that: The sensor monitoring and acquisition module uses a GPS locator, an accelerometer, a gyroscope and a barometer to monitor and collect data on the wearer's position, posture, motion state and environmental conditions, and transmits the collected data to the data processing and analysis module; The real-time monitoring and rescue module is used to monitor the wearer's condition, and the monitoring personnel dispatch rescue personnel to the scene according to the situation; The data processing and analysis module is used to process and analyze the received data in real time, and use the support vector machine algorithm to determine the wearer's movement trajectory and physical condition, and detect whether there is a risk of falling from a high altitude; The control unit is used to control the emergency stop module, and the high-altitude fall warning module is used to send an alarm signal to relevant staff or a monitoring center; The emergency stop module is used to automatically cut off the power supply of the working equipment or trigger the unlocking of the safety rope to reduce accident injuries; The data recording and analysis module is used to record the wearer's movement trajectory and behavior data, and present them visually to help the user intuitively understand the wearer's movement status.

Images