Live-line work monitoring method, device, equipment and storage medium

Abstract

The invention discloses a live working monitoring method, device and equipment and a storage medium, and the method comprises the steps: obtaining a plurality of pieces of position data and a plurality of pieces of acceleration data corresponding to a plurality of parts of a working object in a live working process of the working object; performing time synchronization processing on the multiple pieces of position data and the multiple pieces of acceleration data, and performing filtering processing on the multiple pieces of processed position data and the multiple pieces of processed acceleration data by adopting different modes to obtain multiple pieces of filtered position data and multiple pieces of filtered acceleration data; determining a peak value of an acceleration amplitude based on the plurality of pieces of filtered acceleration data, and determining an action track of the operation object based on the plurality of pieces of filtered position data; and on the basis of the peak value of the acceleration amplitude and the action track, the violation behavior of the operation object in the live working process is identified, and a violation behavior identification result is obtained. By adopting the method, the violation behavior identification accuracy of the operation object in the live working process can be improved.

Description

Technical Field

[0001] The present application relates to the field of live working on transmission lines, and particularly to a live working monitoring method, device, equipment and storage medium. Background Art

[0002] Nowadays, live working has become an important way for defect elimination of transmission lines. Live working can significantly improve power supply reliability, reduce power outage time and increase power supply availability, so as to meet the high requirements of society for power supply, especially during peak power consumption periods and in important power consumption areas. And live working can reduce the operating cost of the power system, reduce the power loss caused by outage maintenance, optimize the maintenance process and improve the maintenance efficiency.

[0003] However, compared with outage working, live working has higher risks. At present, the normative monitoring of operators mainly relies on on-tower monitoring by full-time supervisors. Due to reasons such as perspective and distance limitations, it is difficult to control suddenly emerging operation risks, which will affect the safety of live working.

[0004] Therefore, how to improve the accuracy of identifying the violation behaviors of the operation object during live working has become an urgent problem to be solved. Summary of the Invention

[0005] The embodiments of the present application provide a live working monitoring method, device, equipment and storage medium, which can improve the accuracy of identifying the violation behaviors of the operation object during live working.

[0006] In a first aspect, the embodiments of the present application provide a live working monitoring method, which includes:

[0007] During the process of the operation object performing live working, obtaining a plurality of position data and a plurality of acceleration data respectively corresponding to a plurality of parts of the operation object collected by a plurality of smart wearable devices;

[0008] Using the timestamp alignment algorithm to perform time synchronization processing on the plurality of position data and the plurality of acceleration data, and obtaining the processed plurality of position data and the processed plurality of acceleration data;

[0009] Performing filtering processing on the processed plurality of position data and the processed plurality of acceleration data respectively in different ways, and obtaining the filtered plurality of position data and the filtered plurality of acceleration data;

[0010] Based on the filtered plurality of acceleration data, determining the peak value of the acceleration amplitude, and based on the filtered plurality of position data, determining the action trajectory of the operation object;

[0011] Identify the violation behavior of the operation object during live operation based on the peak value of the acceleration amplitude and the action trajectory, and obtain the identification result of the violation behavior.

[0012] In one embodiment, identifying the violation behavior of the operation object during live operation based on the peak value of the acceleration amplitude and the action trajectory, and obtaining the identification result of the violation behavior includes: determining the start time and end time corresponding to the target action of the operation object during live operation based on the peak value of the acceleration amplitude or the mutation data in the filtered multiple position data; when determining that the action trajectory is the target trajectory, determining the centripetal acceleration and the direction of the centripetal acceleration corresponding to the operation object within the time period from the start time to the end time; when determining that the centripetal acceleration corresponding to the start time indicates that the operation object is in an accelerating state, the centripetal acceleration corresponding to the end time indicates that the operation object is in a decelerating state, and the direction of the centripetal acceleration points to the center of curvature of the action trajectory, determining that the identification result of the violation behavior for the target action of the operation object is that no violation behavior occurs.

[0013] In one embodiment, the target trajectory is an arc trajectory; the method further includes: determining the curvature corresponding to the action trajectory, and when the curvature is greater than a preset curvature threshold, determining that the action trajectory is an arc; when determining that the action trajectory is an arc and the arc length corresponding to the action trajectory is greater than a preset arc length threshold, determining that the action trajectory is an arc trajectory.

[0014] In one embodiment, the processed multiple position data and the processed multiple acceleration data are respectively filtered in different ways to obtain the filtered multiple position data and the filtered multiple acceleration data, including: using a Kalman filter to filter the processed multiple position data to obtain the filtered multiple position data; and using a Butterworth low-pass filter to filter the high-frequency noise in the processed multiple acceleration data to obtain the filtered multiple acceleration data.

[0015] In one embodiment, the method further includes: obtaining point cloud data of the transmission line where the live working is located; outputting an alarm message when it is determined that the working object is currently at the ground potential position and the minimum distance between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the electrical part in the transmission line where the live working is located is less than the first preset distance threshold; outputting an alarm message when it is determined that the working object is currently at the intermediate potential position and the sum of the first minimum distance and the second minimum distance is less than the second preset distance threshold; the first minimum distance is the minimum distance between the position data of multiple parts at the current moment and the point cloud data corresponding to the electrical part; the second minimum distance is the minimum distance between the position data of multiple parts at the current moment and the point cloud data corresponding to the non-electrical part in the transmission line where the live working is located; outputting an alarm message when it is determined that the working object is currently at the equipotential position and the minimum distance between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the non-electrical part is less than the third preset distance threshold.

[0016] In one embodiment, the multiple parts include the left foot, right foot, left hand, and right hand of the working object; the method further includes: when it is determined that the working object enters the equipotential position along the strain insulator string, determining the first distance between the left foot and the right foot of the working object, and the second distance between the left hand and the right hand; when it is determined that both the first distance and the second distance are less than or equal to N times the structural height of the strain insulator string, determining that the working normality detection result of the working object is normal; N is a positive integer greater than 1.

[0017] In one embodiment, the method further includes: based on the multiple position data corresponding to any part, determining the standard deviation of the duration and displacement magnitude corresponding to multiple action stages of the working object; the multiple action stages include the stage of climbing the tower included in the transmission line where the live working is located, the stage of entering the equipotential, the stage of live working, and the stage of descending the tower; for each action stage, based on the duration corresponding to the targeted action stage and the standard duration corresponding to the targeted action stage, determining the operation efficiency evaluation result of the working object under the targeted action stage; based on the standard deviation of the displacement magnitude corresponding to the targeted action stage and the standard deviation of the standard displacement magnitude corresponding to the targeted action stage, determining the action trajectory stability evaluation result of the working object under the targeted action stage; based on the average value of the deviation between each position data of the working object corresponding to the targeted action stage and the standard position data corresponding to each position data, determining the spatial accuracy evaluation result of the working object under the targeted action stage.

[0018] In a second aspect, the present application provides a live working monitoring device, and the device includes:

[0019] An acquisition module, configured to acquire multiple position data and multiple acceleration data respectively corresponding to multiple parts of a job object collected by multiple intelligent wearable devices during the live working process of the job object;

[0020] A processing module, configured to perform time synchronization processing on the multiple position data and the multiple acceleration data by using a timestamp alignment algorithm, to obtain the processed multiple position data and the processed multiple acceleration data;

[0021] The processing module is further configured to perform filtering processing on the processed multiple position data and the processed multiple acceleration data respectively in different ways, to obtain the filtered multiple position data and the filtered multiple acceleration data;

[0022] A determination module, configured to determine the peak value of the acceleration amplitude based on the filtered multiple acceleration data, and to determine the action trajectory of the job object based on the filtered multiple position data;

[0023] The determination module is configured to identify the violation behavior of the job object during the live working process based on the peak value of the acceleration amplitude and the action trajectory, to obtain a violation behavior identification result.

[0024] In a third aspect, the present application provides a computer device, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0025] During the live working process of the job object, acquire multiple position data and multiple acceleration data respectively corresponding to multiple parts of the job object collected by multiple intelligent wearable devices;

[0026] Use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and the multiple acceleration data, to obtain the processed multiple position data and the processed multiple acceleration data;

[0027] Perform filtering processing on the processed multiple position data and the processed multiple acceleration data respectively in different ways, to obtain the filtered multiple position data and the filtered multiple acceleration data;

[0028] Based on the filtered multiple acceleration data, determine the peak value of the acceleration amplitude, and based on the filtered multiple position data, determine the action trajectory of the job object;

[0029] Based on the peak value of the acceleration amplitude and the action trajectory, identify the violation behavior of the job object during the live working process, to obtain a violation behavior identification result.

[0030] Fourthly, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0031] During the live working process of the operation object, obtain multiple position data and multiple acceleration data respectively corresponding to multiple parts of the operation object collected by multiple intelligent wearable devices;

[0032] Use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and the multiple acceleration data to obtain the processed multiple position data and the processed multiple acceleration data;

[0033] Perform filtering processing on the processed multiple position data and the processed multiple acceleration data in different ways respectively to obtain the filtered multiple position data and the filtered multiple acceleration data;

[0034] Based on the filtered multiple acceleration data, determine the peak value of the acceleration amplitude, and based on the filtered multiple position data, determine the action trajectory of the operation object;

[0035] Based on the peak value of the acceleration amplitude and the action trajectory, identify the violation behavior of the operation object during the live working process to obtain the violation behavior identification result.

[0036] Fifthly, the present application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented:

[0037] During the live working process of the operation object, obtain multiple position data and multiple acceleration data respectively corresponding to multiple parts of the operation object collected by multiple intelligent wearable devices;

[0038] Use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and the multiple acceleration data to obtain the processed multiple position data and the processed multiple acceleration data;

[0039] Perform filtering processing on the processed multiple position data and the processed multiple acceleration data in different ways respectively to obtain the filtered multiple position data and the filtered multiple acceleration data;

[0040] Based on the filtered multiple acceleration data, determine the peak value of the acceleration amplitude, and based on the filtered multiple position data, determine the action trajectory of the operation object;

[0041] Based on the peak value of the acceleration amplitude and the action trajectory, identify the violation behavior of the operation object during the live working process to obtain the violation behavior identification result.

[0042] The above-mentioned live working monitoring method, device, equipment and storage medium. The computer device can, during the live working process of the working object, obtain multiple position data and multiple acceleration data respectively corresponding to multiple parts of the working object collected by multiple intelligent wearable devices; use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and multiple acceleration data to obtain the processed multiple position data and the processed multiple acceleration data; perform filtering processing on the processed multiple position data and the processed multiple acceleration data respectively in different ways to obtain the filtered multiple position data and the filtered multiple acceleration data; based on the filtered multiple acceleration data, determine the peak value of the acceleration amplitude, and based on the filtered multiple position data, determine the movement trajectory of the working object; based on the peak value of the acceleration amplitude and the movement trajectory, identify the violation behavior of the working object during the live working process to obtain the violation behavior identification result. By adopting this method, the computer device can perform time synchronization processing and filtering processing on the position data and acceleration data of the high-precision working object collected in real time by multiple intelligent wearable devices to obtain more accurate position data and acceleration data (i.e., the filtered multiple position data and the filtered multiple acceleration data). Then, based on the more accurate position data and acceleration data, identify the violation behavior of the working object during the live working process, and a more accurate violation behavior identification result can be obtained, that is, the accuracy of identifying the violation behavior of the working object during the live working process is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0044] Figure 1 FIG. is a schematic diagram of an application scenario of a live working monitoring method provided by an embodiment of the present application;

[0045] Figure 2 FIG. is a schematic flowchart of a live working monitoring method provided by an embodiment of the present application;

[0046] Figure 3 FIG. is a schematic flowchart of another live working monitoring method provided by an embodiment of the present application;

[0047] Figure 4 FIG. is a schematic structural diagram of a live working monitoring device provided by an embodiment of the present application;

[0048] Figure 5It is a schematic structural diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0049] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0050] The application scenarios of the live working monitoring method provided by the embodiments of the present application will be introduced below.

[0051] Please refer to Figure 1 , Figure 1 which is a schematic diagram of an application scenario of a live working monitoring method provided by an embodiment of the present application. As Figure 1 shown, it includes a computer device 101 and multiple intelligent wearable devices ( Figure 1 in the figure, intelligent wearable device 102, intelligent wearable device 103, intelligent wearable device 104, intelligent wearable device 105 and intelligent wearable device 106 are taken as examples for illustration). Among them, data transmission is carried out between the computer device 101 and each intelligent wearable device through a network.

[0052] Optionally, the intelligent wearable device 102 can be an intelligent device worn on the head of the operation object, such as an intelligent safety helmet; the intelligent wearable devices 103 and 104 can be intelligent devices worn on the left and right wrists of the operation object respectively; the intelligent wearable devices 105 and 106 can be intelligent devices worn on the left and right ankle joints of the operation object respectively.

[0053] Optionally, the intelligent wearable devices 102 to 106 can be devices integrated with real-time kinematic (RTK) high-precision positioning sensors, accelerometers, gyroscopes and other devices, which can not only be used to transmit the action trajectory and status of the operation object in real time, but also receive warning information sent by the background (such as the computer device 101).

[0054] Among them, the intelligent wearable device 102 can collect multiple position data and multiple acceleration data corresponding to the head of the operation object; the intelligent wearable device 103 can collect multiple position data and multiple acceleration data corresponding to the left hand of the operation object; the intelligent wearable device 104 can collect multiple position data and multiple acceleration data corresponding to the right hand of the operation object; the intelligent wearable device 105 can collect multiple position data and multiple acceleration data corresponding to the left foot of the operation object; the intelligent wearable device 106 can collect multiple position data and multiple acceleration data corresponding to the right foot of the operation object.

[0055] Among them, during the live working of the job object, the computer device 101 can obtain multiple position data and multiple acceleration data corresponding to multiple parts of the job object collected by the intelligent wearable devices 102 to 106; then, the computer device 101 can perform time synchronization processing on the multiple position data and multiple acceleration data, and perform filtering processing on the processed multiple position data and processed multiple acceleration data in different ways respectively to obtain the filtered multiple position data and filtered multiple acceleration data; after that, the computer device 101 can identify the violation behavior of the job object during the live working based on the filtered multiple position data and filtered multiple acceleration data to obtain the violation behavior identification result. By adopting this method, the computer device 101 can perform time synchronization processing and filtering processing on the position data and acceleration data of the high-precision job object collected by multiple intelligent wearable devices in real time to obtain more accurate position data and acceleration data (i.e., the filtered multiple position data and filtered multiple acceleration data), and then, based on the more accurate position data and acceleration data, identify the violation behavior of the job object during the live working, and can obtain a more accurate violation behavior identification result, that is, improve the accuracy of identifying the violation behavior of the job object during the live working.

[0056] Optionally, the computer device 101 integrates data such as three-dimensional point clouds and models of the transmission line (including tower equipment and power lines) where the live working is located. It can not only obtain the coordinates of any point on the transmission line where the live working is located, but also receive various data transmitted back by the intelligent wearable devices 102 to 106 in real time, calculate whether there is an abnormality through intelligent algorithms, and can send the abnormality information to the intelligent wearable devices for real-time warning.

[0057] Optionally, the computer device 101 can be a terminal device or a server. Among them, the terminal device mentioned here can include but is not limited to: smart phones, tablet computers, laptop computers, desktop computers, smart watches, smart TVs, intelligent vehicle terminals, etc. The server mentioned here can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, etc.

[0058] Please refer to Figure 2 , Figure 2 is a schematic flowchart of a live working monitoring method provided by an embodiment of the present application. This method can be executed by a computer device (such as the above computer device 101). As Figure 2 shown, the live working monitoring method can include but is not limited to the following steps:

[0059] S201. During the live working of the work object, obtain multiple position data and multiple acceleration data respectively corresponding to multiple parts of the work object collected by multiple intelligent wearable devices.

[0060] Among them, the position data is, for example, P(x, y, z), where x represents the longitude of the point where the intelligent wearable device is located, y represents the latitude of the point where the intelligent wearable device is located, and z represents the elevation of the point where the intelligent wearable device is located. Optionally, for the convenience of later calculation, the coordinate system corresponding to the transmitted coordinates can be the Cartesian coordinate system.

[0061] Among them, the acceleration data is, for example, A(a x , a y , a z ), where a x represents the acceleration in the front - back direction of the intelligent wearable device, a y represents the acceleration in the left - right direction of the intelligent wearable device, and a z represents the acceleration in the up - down direction of the intelligent wearable device.

[0062] In an optional implementation manner, when the computer device obtains multiple position data and multiple acceleration data respectively corresponding to multiple parts of the work object collected by multiple intelligent wearable devices during the live working of the work object, it can be that during the live working of the work object, receive the position data and acceleration data of the corresponding parts of the work object sent by multiple intelligent wearable devices respectively. Correspondingly, multiple intelligent wearable devices respectively send the position data and acceleration data of the corresponding parts of the work object to the computer device.

[0063] Optionally, before multiple intelligent wearable devices respectively send the position data and acceleration data of the corresponding parts of the work object to the computer device, each intelligent wearable device among the multiple intelligent wearable devices can sample the position data of the corresponding part of the work object through RTK, where the sampling frequency is, for example, 30HZ; each intelligent wearable device can also sample the acceleration data of the corresponding part of the work object through an accelerometer, where the sampling frequency is, for example, 30HZ.

[0064] S202. Use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and multiple acceleration data to obtain the processed multiple position data and the processed multiple acceleration data.

[0065] In an optional implementation manner, the computer device can also perform time synchronization processing on the multiple position data and multiple acceleration data through its own clock synchronization function to obtain the processed multiple position data and the processed multiple acceleration data.

[0066] S203. Filter the processed multiple position data and the processed multiple acceleration data in different ways respectively to obtain the filtered multiple position data and the filtered multiple acceleration data.

[0067] In an optional implementation, when the computer device filters the processed multiple position data, it can filter the fluctuating data in the processed multiple position data. In this way, the fluctuation of the position data can be reduced, making the filtered multiple position data smoother.

[0068] In an optional implementation, when the computer device filters the processed multiple acceleration data, it can filter the high-frequency noise in the processed multiple acceleration data. In this way, the high-frequency noise in the multiple processed acceleration data can be removed, so as to obtain smoother acceleration data and avoid the interference of noise on the subsequent identification of illegal behaviors.

[0069] S204. Based on the filtered multiple acceleration data, determine the peak value of the acceleration amplitude, and based on the filtered multiple position data, determine the action trajectory of the operation object.

[0070] In an optional implementation, when the computer device determines the peak value of the acceleration amplitude based on the filtered multiple acceleration data, it may include: determining the resultant acceleration amplitude of each filtered acceleration data; and determining the peak value of the acceleration amplitude from the multiple resultant acceleration amplitudes.

[0071] Optionally, the resultant acceleration amplitude of each filtered acceleration data can be determined by the computer device through the following formula (1).

[0072] (1)

[0073] In formula (1), a represents the resultant acceleration amplitude of each filtered acceleration data; a x represents the acceleration in the front-back direction in each filtered acceleration data; a y represents the acceleration in the left-right direction in each filtered acceleration data; a z represents the acceleration in the up-down direction in each filtered acceleration data.

[0074] Optionally, the peak value of the acceleration amplitude can be the maximum value in the resultant acceleration amplitudes, or the minimum value in the resultant acceleration amplitudes, etc., which is not limited here.

[0075] In an alternative embodiment, the computer device may determine the action trajectory of the operation object based on the filtered multiple position data, which may include: determining the displacement vector at adjacent moments based on the filtered multiple position data; and accumulating the displacement vectors at multiple adjacent moments to obtain the action trajectory of the operation object.

[0076] Optionally, the computer device may use the following formula (2) to determine the displacement vector at adjacent moments .

[0077] (2)

[0078] In formula (2), (x(t), y(t), z(t)) represents the position data at time t in the filtered multiple position data; (x(t + 1), y(t + 1), z(t + 1)) represents the position data at time t + 1 in the filtered multiple position data.

[0079] S205. Identify the violation behavior of the operation object during live working based on the peak value of the acceleration amplitude and the action trajectory, and obtain the violation behavior identification result.

[0080] In the embodiment of the present application, the computer device may, during the live working of the operation object, acquire multiple position data and multiple acceleration data respectively corresponding to multiple parts of the operation object collected by multiple intelligent wearable devices; use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and the multiple acceleration data to obtain the processed multiple position data and the processed multiple acceleration data; perform filtering processing on the processed multiple position data and the processed multiple acceleration data respectively in different ways to obtain the filtered multiple position data and the filtered multiple acceleration data; determine the peak value of the acceleration amplitude based on the filtered multiple acceleration data, and determine the action trajectory of the operation object based on the filtered multiple position data; identify the violation behavior of the operation object during live working based on the peak value of the acceleration amplitude and the action trajectory, and obtain the violation behavior identification result. By adopting this method, the computer device can perform time synchronization processing and filtering processing on the position data and acceleration data of the high-precision operation object collected in real time by multiple intelligent wearable devices to obtain more accurate position data and acceleration data (i.e., the filtered multiple position data and the filtered multiple acceleration data). Then, based on the more accurate position data and acceleration data, the violation behavior of the operation object during live working is identified, and a more accurate violation behavior identification result can be obtained, that is, the accuracy of identifying the violation behavior of the operation object during live working is improved.

[0081] Please refer to Figure 3 , Figure 3It is a schematic flowchart of another live working monitoring method provided by an embodiment of the present application. Different from the live working monitoring method shown in Figure 2 , the difference lies in that Figure 3 in the live working monitoring method shown in, it specifically elaborates on how a computer device identifies the violation behavior of an operation object during live working based on the peak value of the acceleration amplitude and the movement trajectory, and obtains the identification result of the violation behavior. As shown in Figure 3 , the live working monitoring method may include but is not limited to the following steps:

[0082] S301. During the live working process of the operation object, obtain multiple position data and multiple acceleration data respectively corresponding to multiple parts of the operation object collected by multiple intelligent wearable devices.

[0083] S302. Use the timestamp alignment algorithm to perform time synchronization processing on the multiple position data and the multiple acceleration data, and obtain the processed multiple position data and the processed multiple acceleration data.

[0084] In an optional implementation manner, the relevant descriptions of steps S301 and S302 can be respectively referred to the descriptions in the foregoing steps S201 and S202, and will not be elaborated here.

[0085] S303. Use a Kalman filter to perform filtering processing on the processed multiple position data to obtain the filtered multiple position data; and use a Butterworth low-pass filter to perform filtering processing on the high-frequency noise in the processed multiple acceleration data to obtain the filtered multiple acceleration data.

[0086] S304. Based on the filtered multiple acceleration data, determine the peak value of the acceleration amplitude, and based on the filtered multiple position data, determine the movement trajectory of the operation object.

[0087] In an optional implementation manner, the relevant description of step S304 can be referred to the description in the foregoing step S204, and will not be elaborated here.

[0088] S305. Based on the peak value of the acceleration amplitude or the mutation data in the filtered multiple position data, determine the start time and end time corresponding to the target action of the operation object during the live working process.

[0089] S306. In the case where the movement trajectory is determined to be the target trajectory, determine the centripetal acceleration and the direction of the centripetal acceleration corresponding to the operation object during the time period from the start time to the end time.

[0090] In an alternative embodiment, the target trajectory is an arc trajectory; the computer device can also determine the curvature corresponding to the action trajectory, and determine that the action trajectory is an arc when the curvature is greater than a preset curvature threshold; when it is determined that the action trajectory is an arc and the arc length corresponding to the action trajectory is greater than a preset arc length threshold, it is determined that the action trajectory is an arc trajectory. In this way, by ensuring that the arc length satisfies a certain range, some minor local curvature changes can be excluded.

[0091] Optionally, when the computer device determines the curvature corresponding to the action trajectory, the following formula (3) can be used.

[0092] (3)

[0093] In formula (2), k represents the curvature corresponding to the action trajectory; are the displacement vectors at adjacent times the first-order derivative and the second-order derivative of (which can be obtained using formula (2)).

[0094] Optionally, the arc length corresponding to the action trajectory can be determined by the computer device using the following formula (4).

[0095] (4)

[0096] In formula (4), L represents the arc length corresponding to the action trajectory; represents the displacement vector at adjacent times.

[0097] S307. When it is determined that the centripetal acceleration corresponding to the starting moment indicates that the operation object is in an accelerating state, the centripetal acceleration corresponding to the ending moment indicates that the operation object is in a decelerating state, and the direction of the centripetal acceleration points to the center of curvature of the action trajectory, it is determined that the recognition result of the illegal behavior of the target action for the operation object is that no illegal behavior has occurred.

[0098] Exemplarily, when the operation object's arm moves around the transmission line (such as a tower component) where live working is being carried out, the acceleration will change periodically. For example, the centripetal acceleration a c = v 2 / r, where v represents the speed and r represents the radius of the arc trajectory. Among them, the speed can be obtained by the computer device through differential approximation calculation of the position data. For example, , where represents the displacement vector at adjacent times, represents the time interval between adjacent times.

[0099] In the embodiments of the present application, the computer device can determine the start time and end time corresponding to the target action of the operation object during live working based on the peak value of the acceleration amplitude or the mutation data in the filtered multiple position data; in the case of determining that the action trajectory is the target trajectory, determine the centripetal acceleration and the direction of the centripetal acceleration corresponding to the operation object within the time period from the start time to the end time; in the case of determining that the centripetal acceleration corresponding to the start time indicates that the operation object is in an accelerating state, the centripetal acceleration corresponding to the end time indicates that the operation object is in a decelerating state, and the direction of the centripetal acceleration points to the center of curvature of the action trajectory, determine that the recognition result of the violation behavior of the target action for the operation object is that no violation behavior occurs. In this way, by associating and verifying the acceleration data and the position data, the data validity can be ensured, thereby improving the accuracy of the recognition of violation behaviors of the operation object during live working.

[0100] In an alternative embodiment, Figure 2 and Figure 3 in the live working monitoring method shown, the computer device can also acquire the point cloud data of the transmission line where the live working is located; in the case of determining that the operation object is currently at the ground potential position and the minimum distance between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the electrical part in the transmission line where the live working is located is less than the first preset distance threshold, output an alarm message; in the case of determining that the operation object is currently at the intermediate potential position and the sum of the first minimum distance and the second minimum distance is less than the second preset distance threshold, output an alarm message; the first minimum distance is the minimum distance between the position data of multiple parts at the current moment and the point cloud data corresponding to the electrical part; the second minimum distance is the minimum distance between the position data of multiple parts at the current moment and the point cloud data corresponding to the non-electrical part in the transmission line where the live working is located; in the case of determining that the operation object is currently at the equipotential position and the minimum distance between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the non-electrical part is less than the third preset distance threshold, output an alarm message.

[0101] Optionally, the transmission line where the live working is located may include transmission towers and power lines, etc.

[0102] Optionally, the minimum distances between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the electrical part in the transmission line where live working is carried out, the first minimum distance, the second minimum distance, and the minimum distances between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the non-electrical part can all be determined by the computer device using the k-dimensional tree (KD-Tree) algorithm. In this way, the calculation efficiency can be improved. Among them, the KD-Tree is a data structure that divides the k-dimensional data space and is mainly applied to the search for key data in the multi-dimensional space.

[0103] The following is an example to illustrate the calculation process of the KD-Tree.

[0104] Suppose the coordinate set of the live part of the transmission line where live working is carried out (which can be directly extracted after the computer device has completed point cloud classification) is (x i , y i , z i ), where i = 1, 2, 3,..., n. Then, the mean and variance of each dimension are calculated as follows:

[0105] Mean of longitude (x dimension) ; Variance of longitude (x dimension) ;

[0106] Mean of latitude (y dimension) ; Variance of latitude (y dimension) ;

[0107] Mean of elevation (z dimension) ; Variance of elevation (z dimension) .

[0108] Compare and select the dimension with the largest variance as the splitting axis for this division.

[0109] ② Divide the data set (calculate the median)

[0110] Through calculation, assume that a certain dimension (such as longitude, that is, the x dimension) is selected as the splitting axis, and the median on this dimension needs to be found to divide the data set. That is, sort the values of all points on the selected splitting axis (x dimension), and set the sorted array as x 1 ≤ x 2 ≤... ≤ x n .

[0111] If n is odd, the median m is the value at the middle position, that is ;

[0112] If n is even, the median m is usually taken as the average of the two middle numbers, that is 。

[0113] Divide the data set into two subsets through the median m. The points in the left subset satisfy x i ≤m, and the points in the right subset satisfy x i >m. Then recursively perform the same operation on these two subsets to construct a KD-Tree.

[0114] ③ Query the nearest point

[0115] Start searching from the root node of the KD-Tree:

[0116] Compare the coordinates P(x 0 , y 0 , z 0 ) transmitted back by the smart wearable device with the value of the splitting axis represented by the current node, and decide whether to continue searching in the left subtree or the right subtree. For example, if the current splitting axis is the x dimension, if x 0 is less than the x value of the current node, enter the left subtree for searching; otherwise, enter the right subtree for searching.

[0117] During the search process, record the currently found nearest point Q near and the corresponding nearest distance d near (initially, it can be set to a relatively large value, such as positive infinity). When reaching the leaf node, calculate the distance d(P, Q) between the point Q(x, y, z) in the leaf node and the target query point P(x 0 , y 0 , z 0 ). Among them, d(P, Q) can be determined using the three-dimensional Euclidean distance formula, that is, the following formula (5).

[0118] (5)

[0119] Compare the calculated distance with the current nearest distance d near If d(P, Q) < d near , update the nearest point Q near to Q, and update the nearest distance d near to d(P, Q); if d(P, Q) ≥ d near , since the distance from the current Q in the leaf node to the query point P is greater than or equal to the currently found nearest distance, so this point Q will not become the new nearest point. Therefore, the currently recorded nearest point and nearest distance do not need to be updated and continue to remain as d near and the corresponding nearest point.

[0120] ④ Backtracking process

[0121] When backtracking to the parent node, it is necessary to check whether the area on the other side of the splitting plane may contain closer points.

[0122] Assume that the splitting axis is the x - dimension and the value of the splitting plane is m. The computer device can use the following formula (6) to calculate the distance d from the target query point P(x 0 , y 0 , z 0 ) to the splitting plane in the x - dimension split .

[0123] (6)

[0124] If d split < d near , it indicates that the area on the other side of the splitting plane may contain closer points, and it is necessary to enter this subtree to continue the search, repeating the above steps (calculating the distance when reaching the leaf node, comparing and updating the nearest distance, backtracking, etc.); otherwise, skip this subtree and continue backtracking. After backtracking to the root node, the finally recorded Q near is the point in the dataset that is closest to the target query point P, and d near is the corresponding nearest distance.

[0125] Through the above - mentioned method combining KD - Tree and the three - dimensional Euclidean distance formula, the nearest distance from a certain point to a large number of point clouds can be calculated efficiently.

[0126] Adopting this implementation manner, when the computer device determines that the alarm information output condition is met, it outputs the alarm information. Thus, the safety during the live working process of the operation object can be improved.

[0127] In an alternative implementation manner Figure 2 and Figure 3 in the live working monitoring method shown, the multiple parts include the left foot, right foot, left hand, and right hand of the operation object; the computer device can also determine the first distance between the left foot and the right foot of the operation object, and the second distance between the left hand and the right hand when determining that the operation object enters the equal - potential position along the strain insulator string; when determining that both the first distance and the second distance are less than or equal to N times the structural height of the strain insulator string, it is determined that the operation standard - compliance detection result of the operation object is standard; N is a positive integer greater than 1. Optionally, N is, for example, 2.

[0128] Optionally, assume that the position data corresponding to the left foot of the operation object is C(x 1 , y 1 , z 1 ), and the position data corresponding to the right foot is D(x 2 , y 2 , z 2 ). Then the computer device can use the following formula (7) to determine the first distance between the left foot and the right foot of the operation object.

[0129] (7)

[0130] In formula (7), J(C, D) represents the first distance between the left foot and the right foot of the operation object.

[0131] Optionally, assuming that the position data corresponding to the left hand of the operation object is E(x 3 , y 3 , z 3 ), and the position data corresponding to the right hand is F(x 4 , y 4 , z 4 ), then the computer device can use the following formula (8) to determine the second distance between the left hand and the right hand of the operation object.

[0132] (8)

[0133] In formula (8), S(E, F) represents the second distance between the left hand and the right hand of the operation object.

[0134] By adopting this implementation manner, the computer device can quickly and accurately identify the operation standardization of the operation object by comparing the relationship between the first distance between the left foot and the right foot of the operation object and the second distance between the left hand and the right hand of the operation object respectively and N times the structural height of the strain insulator string. Thus, the accuracy of the operation standardization detection during the live operation of the operation object is improved.

[0135] In an optional implementation manner, Figure 2 and Figure 3 In the live operation monitoring method shown, the computer device can also determine the standard deviation of the duration and displacement magnitude corresponding to multiple action stages of the operation object based on multiple position data corresponding to any part; the multiple action stages include the tower pole stage (abbreviated as the tower climbing stage) included in the transmission line where the live operation is located, the equal-potential entering stage, the live operation stage, and the tower descending stage; for each action stage, based on the duration corresponding to the targeted action stage and the standard duration corresponding to the targeted action stage, determine the operation efficiency evaluation result of the operation object under the targeted action stage; based on the standard deviation of the displacement magnitude corresponding to the targeted action stage and the standard deviation of the standard displacement magnitude corresponding to the targeted action stage, determine the action trajectory stability evaluation result of the operation object under the targeted action stage; based on the average value of the deviation between each position data of the operation object corresponding to the targeted action stage and the standard position data corresponding to each position data, determine the spatial accuracy evaluation result of the operation object under the targeted action stage.

[0136] In some embodiments, for each action phase, the computer device determines the operation efficiency evaluation result of the operation object in the targeted action phase based on the duration corresponding to the targeted action phase and the standard duration corresponding to the targeted action phase. For each phase s (tower pole climbing phase, equal-potential entering phase, operation phase, and tower pole descending phase), the computer device can separately determine the duration T op-s of the operation object in phase s and the standard duration T sk-s corresponding to this phase s; based on T op-s and T sk-s , it determines the phase time efficiency coefficient; when it is determined that the phase time efficiency coefficient is greater than 1, it determines that the operation efficiency evaluation result of the operation object in phase s is low operation efficiency; when it is determined that the phase time efficiency coefficient is less than or equal to 1, it determines that the operation efficiency evaluation result of the operation object in phase s is high operation efficiency.

[0137] Optionally, when the computer device determines the phase time efficiency coefficient based on T op-s and T sk-s , the following formula (9) can be used.

[0138] (9)

[0139] In formula (9), represents the phase time efficiency coefficient.

[0140] In some embodiments, the computer device determines the action trajectory stability evaluation result of the operation object in the targeted action phase based on the standard deviation of the displacement magnitude corresponding to the targeted action phase and the standard deviation of the standard displacement magnitude corresponding to the targeted action phase. For each phase s, the computer device can separately determine the standard deviation of the displacement magnitude of the operation object within phase s and the standard deviation of the corresponding standard displacement magnitude within phase s; based on and , it determines the trajectory stability coefficient; when it is determined that the trajectory stability coefficient is greater than 1, it determines that the action trajectory stability evaluation result of the operation object in phase s is unstable; when it is determined that the trajectory stability coefficient is less than or equal to 1, it determines that the action trajectory stability evaluation result of the operation object in phase s is stable.

[0141] Optionally, when the computer device determines the trajectory stability coefficient based on and , the following formula (10) can be used.

[0142] (10)

[0143] In formula (10), represents the trajectory stability coefficient.

[0144] In some embodiments, based on the average of the deviations between each position data of the operation object corresponding to the targeted action phase and the standard position data corresponding to each position data, the spatial accuracy evaluation result of the operation object in the targeted action phase is determined. For each phase s, multiple standard position data and multiple position data corresponding to the operation object can be determined respectively; for each position data p op-i ((x op-i ,y op-i ,z op-i ), the distance deviation between it and the standard position data p sk-i (x sk-i ,y sk-i ,z sk-i ) corresponding to this position data is determined; the average value of multiple distance deviations is determined; when it is determined that the average value of multiple distance deviations is greater than the preset spatial accuracy threshold, the spatial accuracy evaluation result of the operation object in phase s is determined to have a large deviation; when it is determined that the average value of multiple distance deviations is less than the preset spatial accuracy threshold, the spatial accuracy evaluation result of the operation object in phase s is determined to have a small deviation.

[0145] Optionally, when the computer device determines the distance deviation between the i-th position data p op-i ((x op-i ,y op-i ,z op-i ) and the standard position data p sk-i (x sk-i ,y sk-i ,z sk-i ) corresponding to the i-th position data, the following formula (11) can be used.

[0146] (11)

[0147] In formula (11), represents the distance deviation between the i-th position data p op-i and the standard position data p sk-i corresponding to the i-th position data.

[0148] Optionally, when the computer device determines the average value of multiple distance deviations, the following formula (12) can be used.

[0149] (12)

[0150] In formula (12), represents the average value of multiple distance deviations; m represents the number of distance deviations.

[0151] The process by which the computer device determines the action phase of the operation object will be described below.

[0152] Exemplarily, assume that any part is a certain intelligent wearable device (such as a safety helmet), then the multiple position data corresponding to the any part are a series of three-dimensional coordinate points arranged in chronological order, denoted as P = {p 1 , p 2 ,..., p n}, where p i (x i , y i , z i ) represents the i-th position point, and each position point corresponds to a timestamp t i .

[0153] Among them, the displacement vector between two adjacent points p i (x i , y i , z i ) and p i+1 (x i+1 , y i+1 , z i+1 ) is , the displacement magnitude is , and the time interval is .

[0154] In some embodiments, the computer device can determine that the action phase of the operation object is the tower climbing phase in the following manner: based on the z-dimension data in the multiple position data, determine the first height change rate of the operation object ; when it is determined that the first height change rate is greater than the first preset height change rate threshold r z-th , the duration T is greater than the first preset duration threshold T z-th , and the average value of the horizontal displacement is less than the first preset horizontal displacement threshold d z-th , determine that the action phase of the operation object is the tower climbing phase.

[0155] Optionally, when the computer device determines the height change rate of the operation object based on the z-dimension data in the multiple position data, the following formula (13) can be used.

[0156] (13)

[0157] Optionally, the computer device can determine the horizontal displacement corresponding to two adjacent position data based on the x-dimension data in the multiple position data by using the following formula (14); then, based on the multiple horizontal displacements, determine the average value of the horizontal displacement.

[0158] (14)

[0159] In some embodiments, the computer device may determine that the action phase of the operation object is the equal-potential entering phase in the following manner: Determine the position p of the operation object i from the equal-potential position p eq (x eq , y eq , z eq ) of the distance d eq-i ; When determining that the distance d eq-i is less than the preset distance threshold d eq-th , and the duration is greater than the second duration threshold T eq-th , determine that the action phase of the operation object is the equal-potential entering phase.

[0160] Optionally, when the computer device determines the distance d i between the position p eq of the operation object and the equal-potential position p eq (x eq , y eq ), the following formula (15) can be used. eq-i (15)

[0161] (15)

[0162] In some embodiments, the computer device may determine that the action phase of the operation object is the operation phase in the following manner: Determine the distance fluctuation i from the position p eq of the operation object to the equal-potential position p eq (x eq , y eq ); When determining that the distance fluctuation is less than the preset distance fluctuation threshold d , and the duration between the current moment and the pole climbing stage and the equal-potential entering stage is greater than the third preset duration threshold, determine that the action phase of the operation object is the operation phase. op-th

[0163] In some embodiments, the computer device may determine that the action phase of the operation object is the down-pole stage in the following manner: Based on the z-dimension data in the multiple position data, determine the second height change rate of the operation object ; When determining that the second height change rate is greater than the second preset height change rate threshold r z-th-down , the duration is greater than the fourth preset duration threshold T z-th-down , and the average value of the horizontal position is less than the second preset horizontal displacement threshold d z-th-down ​In this case, it is determined that the action stage of the operation object is the stage of getting off the tower.

[0164] Optionally, the computer device determines the second height change rate of the operation object based on the z-dimension data in the multiple position data. When doing so, the following formula (16) can be used.

[0165] (16)

[0166] Optionally, the computer device can determine the horizontal displacement corresponding to two adjacent position data by using the above formula (14) based on the x-dimension data in the multiple position data; then, based on the multiple horizontal displacements, determine the average value of the horizontal displacements.

[0167] By adopting this implementation manner, the computer device can determine the standard deviations of the durations and displacement magnitudes corresponding to the multiple action stages of the operation object based on the multiple position data corresponding to any part, and based on the standard deviations of the durations and displacement magnitudes corresponding to the multiple action stages and the standard deviations of the standard duration and standard displacement magnitude corresponding to each stage, evaluate the skills of the operation object (such as operation efficiency, action trajectory stability, and spatial accuracy, etc.), thereby, the accuracy of the skill level evaluation of the operation object during live working can be improved.

[0168] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages, and these steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0169] Based on the same inventive concept, the embodiments of the present application also provide a live working monitoring device for implementing the above-mentioned live working monitoring method. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the following live working monitoring device can refer to the limitations on the live working monitoring method in the above text, and will not be repeated here.

[0170] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of a live working monitoring device provided by an embodiment of the present application. AsFigure 4 As shown, the live working monitoring device may include, but is not limited to:

[0171] An acquisition module 401, configured to acquire a plurality of position data and a plurality of acceleration data respectively corresponding to a plurality of parts of a working object collected by a plurality of intelligent wearable devices during the live working process of the working object;

[0172] A processing module 402, configured to perform time synchronization processing on the plurality of position data and the plurality of acceleration data by using a timestamp alignment algorithm to obtain the processed plurality of position data and the processed plurality of acceleration data;

[0173] The processing module 402 is further configured to perform filtering processing on the processed plurality of position data and the processed plurality of acceleration data respectively in different ways to obtain the filtered plurality of position data and the filtered plurality of acceleration data;

[0174] A determination module 403, configured to determine the peak value of the acceleration amplitude based on the filtered plurality of acceleration data, and determine the action trajectory of the working object based on the filtered plurality of position data;

[0175] The determination module 403 is further configured to identify the violation behavior of the working object during the live working process based on the peak value of the acceleration amplitude and the action trajectory to obtain a violation behavior identification result.

[0176] In one embodiment, when the determination module 404 is configured to identify the violation behavior of the working object during the live working process based on the peak value of the acceleration amplitude and the action trajectory to obtain a violation behavior identification result, it is specifically configured to: determine the start time and end time corresponding to the target action of the working object during the live working process based on the peak value of the acceleration amplitude or the mutation data in the filtered plurality of position data; in the case where the determined action trajectory is a target trajectory, determine the centripetal acceleration and the direction of the centripetal acceleration corresponding to the working object during the time period from the start time to the end time; in the case where the centripetal acceleration corresponding to the start time indicates that the working object is in an accelerating state, the centripetal acceleration corresponding to the end time indicates that the working object is in a decelerating state, and the direction of the centripetal acceleration points to the center of curvature of the action trajectory, determine that the violation behavior identification result for the target action of the working object is that no violation behavior occurs.

[0177] In one embodiment, the target trajectory is an arc trajectory; the determination module 403 is further configured to determine the curvature corresponding to the action trajectory, and in the case where the curvature is greater than a preset curvature threshold, determine that the action trajectory is an arc; in the case where the determined action trajectory is an arc and the arc length corresponding to the action trajectory is greater than a preset arc length threshold, determine that the action trajectory is an arc trajectory.

[0178] In one embodiment, when the processing module 402 is used to filter the processed multiple position data and the processed multiple acceleration data in different ways to obtain the filtered multiple position data and the filtered multiple acceleration data, it is specifically used for: using a Kalman filter to filter the processed multiple position data to obtain the filtered multiple position data; and using a Butterworth low-pass filter to filter the high-frequency noise in the processed multiple acceleration data to obtain the filtered multiple acceleration data.

[0179] In one embodiment, the acquisition module 401 is further configured to acquire point cloud data of the transmission line where the live working is located; the processing module 402 is further configured to output an alarm message when it is determined that the operation object is currently at the ground potential position and the minimum distance between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the electrical part in the transmission line where the live working is located is less than the first preset distance threshold; output an alarm message when it is determined that the operation object is currently at the intermediate potential position and the sum of the first minimum distance and the second minimum distance is less than the second preset distance threshold; the first minimum distance is the minimum distance between the position data of multiple parts at the current moment and the point cloud data corresponding to the electrical part; the second minimum distance is the minimum distance between the position data of multiple parts at the current moment and the point cloud data corresponding to the non-electrical part in the transmission line where the live working is located; output an alarm message when it is determined that the operation object is currently at the equipotential position and the minimum distance between the position data corresponding to multiple parts at the current moment and the point cloud data corresponding to the non-electrical part is less than the third preset distance threshold.

[0180] In one embodiment, the multiple parts include the left foot, right foot, left hand, and right hand of the operation object; the determination module 403 is further configured to determine the first distance between the left foot and the right foot of the operation object, and the second distance between the left hand and the right hand when it is determined that the operation object enters the equipotential position along the strain insulator string; determine that the operation standard detection result of the operation object is standard when it is determined that both the first distance and the second distance are less than or equal to N times the structural height of the strain insulator string; N is a positive integer greater than 1.

[0181] In one embodiment, the determination module 403 is further configured to determine the standard deviation of the duration and displacement magnitude corresponding to multiple action phases of the operation object based on the multiple position data corresponding to any part; the multiple action phases include the tower pole phase, the equal-potential entering phase, the live working phase, and the tower pole descending phase included in the transmission line where the live working is located; for each action phase, based on the duration corresponding to the targeted action phase and the standard duration corresponding to the targeted action phase, determine the operation efficiency evaluation result of the operation object under the targeted action phase; based on the standard deviation of the displacement magnitude corresponding to the targeted action phase and the standard deviation of the standard displacement magnitude corresponding to the targeted action phase, determine the action trajectory stability evaluation result of the operation object under the targeted action phase; based on the average value of the deviations between each position data of the operation object corresponding to the targeted action phase and the standard position data corresponding to each position data, determine the spatial accuracy evaluation result of the operation object under the targeted action phase.

[0182] Each module in the above live working monitoring device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor in the terminal device in the form of hardware or be independent of it, or can be stored in the memory in the terminal device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0183] In an exemplary embodiment, the embodiment of the present application provides a computer device, which can be a terminal device, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a live working monitoring method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0184] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0185] In an exemplary embodiment, the present application provides a computer device, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, it implements the steps in the above-mentioned live working monitoring method.

[0186] In an exemplary embodiment, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, it implements the steps in the above-mentioned live working monitoring method.

[0187] In an exemplary embodiment, the present application provides a computer program product, including a computer program. When the computer program is executed by the processor, it implements the steps in the above-mentioned live working monitoring method.

[0188] It should be noted that the data involved in this application (including but not limited to multiple location data, multiple acceleration data, processed multiple location data, processed multiple acceleration data, filtered multiple location data, filtered multiple acceleration data, peak values of acceleration amplitudes, and movement trajectories, etc.) are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0189] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0190] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0191] The above-described embodiments merely represent several implementation manners of this application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A method for monitoring live working, characterized in that: The method comprises: During live working on a working object, a plurality of position data and a plurality of acceleration data corresponding to a plurality of parts of the working object respectively collected by a plurality of smart wearable devices are obtained; Using a timestamp alignment algorithm, time synchronization processing is performed on the plurality of position data and the plurality of acceleration data to obtain a plurality of processed position data and a plurality of processed acceleration data; Performing filtering processing on the processed multiple position data and the processed multiple acceleration data in different ways to obtain multiple filtered position data and multiple filtered acceleration data; Determine the peak value of the acceleration amplitude based on the filtered multiple acceleration data, and determine the movement trajectory of the working object based on the filtered multiple position data; Based on the peak value of the acceleration amplitude and the movement trajectory, the illegal behavior of the operating object during the live working process is identified to obtain a illegal behavior identification result.

2. The method according to claim 1, characterized in that The identifying of the illegal behavior of the operating object during the live working process based on the peak value of the acceleration amplitude and the action trajectory to obtain the illegal behavior identification result includes: Determine the start time and the end time corresponding to the target action of the working object during the live working process based on the peak value of the acceleration amplitude or the mutation data in the filtered multiple position data; When it is determined that the motion trajectory is the target trajectory, determining the centripetal acceleration corresponding to the operation object and the direction of the centripetal acceleration within a time period corresponding to the start time to the end time; When it is determined that the centripetal acceleration corresponding to the starting moment indicates that the working object is in an accelerating state, the centripetal acceleration corresponding to the ending moment indicates that the working object is in a decelerating state, and the direction of the centripetal acceleration points to the center of curvature of the motion trajectory, it is determined that the violation behavior identification result for the target action of the working object is that no violation behavior has occurred.

3. The method according to claim 2, characterized in that The target trajectory is an arc trajectory; the method further comprises: Determining a curvature corresponding to the motion trajectory, and determining that the motion trajectory is an arc when the curvature is greater than a preset curvature threshold; When it is determined that the motion trajectory is an arc and the arc length corresponding to the motion trajectory is greater than a preset arc length threshold, the motion trajectory is determined to be the arc trajectory.

4. The method according to claim 1, characterized in that The filtering of the processed multiple position data and the processed multiple acceleration data in different ways to obtain the filtered multiple position data and the filtered multiple acceleration data includes: Using a Kalman filter, filtering the processed multiple position data to obtain multiple filtered position data; and, A Butterworth low-pass filter is used to filter high-frequency noise in the processed acceleration data to obtain filtered acceleration data.

5. The method according to claim 1, characterized in that: The method further comprises: Acquire point cloud data of the power transmission line where the live work is located; Outputting an alarm message when it is determined that the working object is currently located at a ground potential position and the minimum distance between the position data corresponding to the plurality of parts at the current moment and the point cloud data corresponding to the electrical part of the transmission line where the live working is located is less than a first preset distance threshold; When it is determined that the working object is currently located at an intermediate potential position and the sum of the first minimum distance and the second minimum distance is less than the second preset distance threshold, the alarm information is output; the first minimum distance is the minimum distance between the position data of the plurality of parts at the current moment and the point cloud data corresponding to the electrical part; the second minimum distance is the minimum distance between the position data of the plurality of parts at the current moment and the point cloud data corresponding to the non-electrical part of the transmission line where the live work is located; When it is determined that the work object is currently located at an equipotential position and the minimum distance between the position data corresponding to the multiple parts at the current moment and the point cloud data corresponding to the non-electrical part is less than a third preset distance threshold, the alarm information is output.

6. The method according to claim 1, characterized in that The plurality of parts include a left foot, a right foot, a left hand and a right hand of the work object; the method further comprises: In the case where it is determined that the working object has entered an equipotential position along the tension insulator string, determining a first distance between the left foot and the right foot of the working object, and a second distance between the left hand and the right hand; When it is determined that the first distance and the second distance are both less than or equal to N times the structural height of the tension insulator string, the operation normativeness inspection result of the operation object is determined to be normative; and N is a positive integer greater than 1.

7. The method according to claim 1, characterized in that The method further comprises: Based on the multiple position data corresponding to any of the parts, determine the standard deviation of the duration and displacement size corresponding to the multiple action stages of the operation object; the multiple action stages include the tower climbing stage included in the transmission line where the live operation is located, the equipotential stage, the live operation stage, and the tower climbing stage; For each of the action stages, based on the duration corresponding to the action stage and the standard duration corresponding to the action stage, determine the operation efficiency evaluation result of the operation object in the action stage; Determine a stability evaluation result of the motion trajectory of the operation object in the action stage based on the standard deviation of the displacement size corresponding to the action stage and the standard deviation of the standard displacement size corresponding to the action stage; Based on the average value of the deviation between each position data of the work object corresponding to the action stage and the standard position data corresponding to each position data, the spatial accuracy evaluation result of the work object in the action stage is determined.

8. A live working monitoring device, characterized in that: The device comprises: An acquisition module, used to acquire a plurality of position data and a plurality of acceleration data corresponding to a plurality of parts of the working object respectively collected by a plurality of smart wearable devices during live working of the working object; A processing module, used for performing time synchronization processing on the plurality of position data and the plurality of acceleration data by using a timestamp alignment algorithm to obtain a plurality of processed position data and a plurality of processed acceleration data; The processing module is further used to filter the processed multiple position data and the processed multiple acceleration data in different ways to obtain the filtered multiple position data and the filtered multiple acceleration data; A determination module, configured to determine a peak value of the acceleration amplitude based on the filtered multiple acceleration data, and to determine a movement trajectory of the operation object based on the filtered multiple position data; The determination module is used to identify the illegal behavior of the operating object during the live working process based on the peak value of the acceleration amplitude and the action trajectory, and obtain the illegal behavior identification result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images