A live working pre-warning system based on artificial intelligence accurate positioning

Abstract

This invention relates to the field of artificial intelligence, and more particularly to a live-line work early warning system based on precise positioning using artificial intelligence. The invention utilizes the collaborative operation of an inspection module, an inspection control module, a tag setting module, a positioning module, and a storage module. The inspection and control modules monitor multipath effects in the monitored area. The tag setting module calculates multipath interference characterization values ​​based on image recognition and signal feature values, and identifies risk areas. Through the collaboration of two positioning units in the positioning module, the effective time domain segment is determined and its momentum characteristics are acquired, thereby predicting positioning information for ineffective time domain segments. Finally, the storage module verifies and stores the positioning information, thereby improving the positioning accuracy of actual workers, enhancing the accuracy and reliability of live-line work early warning, and ensuring the safety of live-line work in complex environments.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence, and in particular to a live-line work early warning system based on precise positioning using artificial intelligence. Background Technology

[0002] With the continuous development of the power industry and the increasing demands for the reliability and safety of power supply, live-line work has become increasingly important in power operation and maintenance. Precise positioning technology, as a key support for ensuring the safe and efficient conduct of live-line work, has become an indispensable part of the intelligent development of power operations.

[0003] Chinese Patent Publication No. CN113221640A discloses an invention relating to the technical field of live-line work safety detection systems. It presents an active early warning and safety monitoring system for live-line work based on artificial intelligence-based precise positioning. The system includes an active early warning system, a lidar, an inertial sensor, and a camera. It also includes a human key point recognition system, a live-line identification system, a data fusion system, and a spatial position determination system. The camera is electrically connected to the human key point recognition system, the live-line identification system, and the data fusion system. The lidar and inertial sensor are electrically connected to the data fusion system. The outputs of the human key point recognition system, the live-line identification system, and the data fusion system are connected to the input of the spatial position determination system. Compared with existing technologies, this invention can monitor safe distances in real time and provide active early warnings, preventing or reducing accidents such as personal injury to personnel working on live lines.

[0004] However, the following problems still exist in the existing technology.

[0005] In real-world live-line working scenarios, the complex working environment presents numerous challenges to the accurate transmission of positioning signals. For example, the unique steel structure of the tower itself, various insulator components, and other auxiliary facilities, especially in the confined spaces underground, often create obstacles to signal propagation. When these obstacles are encountered, multipath propagation occurs, meaning the signal no longer travels along a single straight path but instead forms multiple propagation paths due to reflection, diffraction, and other phenomena. This can lead to delays and distortions in the positioning signals received by the receiving equipment, potentially causing errors in the positioning personnel's location judgment. Consequently, the early warning system may fail to issue timely and accurate alarms due to inaccurate positioning, reducing the accuracy and reliability of the live-line working early warning system in complex environments. Summary of the Invention

[0006] To address this issue, the present invention provides a live-line work early warning system based on artificial intelligence for precise positioning. This system overcomes the problem in existing technologies where, in complex live-line work scenarios, when the positioning signal encounters an obstacle, it no longer propagates along a single straight path but instead forms multiple propagation paths due to reflection, diffraction, and other phenomena. This can lead to delays and distortions in the positioning signal acquired by the receiving device, potentially causing errors in the positioning operator's location judgment. Consequently, the early warning system may fail to issue timely and accurate alarms due to inaccurate positioning, reducing the practicality and reliability of the live-line work early warning system in complex environments.

[0007] To achieve the above objectives, the present invention provides a live-line working early warning system based on artificial intelligence for precise positioning, comprising,

[0008] The inspection module includes a first inspection unit and a second inspection unit that can move along a predetermined path in each monitoring area. The first inspection unit is equipped with a signal transmitting unit for continuously sending positioning signals and an image acquisition unit for acquiring images of the monitoring area. The second inspection unit is equipped with a signal receiving unit for receiving positioning signals at various times.

[0009] The inspection control module is connected to the inspection module and is used to control the second inspection unit to follow the first inspection unit at predetermined intervals, perform multipath effect monitoring in each monitoring area, and obtain the signal characteristic values ​​of the positioning signal corresponding to each monitoring area at each time.

[0010] The tag setting module, which is connected to the inspection control module, is used to determine the number of obstacles based on the image of the monitoring area, and calculate the multipath interference characterization value in combination with the signal feature value to calibrate the corresponding monitoring area.

[0011] The positioning module is connected to the tag setting module and includes a first positioning unit and a second positioning unit. The first positioning unit continuously acquires the positioning signal in response to the target starting positioning signal being in a non-calibration area, acquires positioning information based on the positioning signal, predicts the travel vector based on the positioning information, and determines whether to pre-enter the calibration area.

[0012] The second positioning unit responds to the target's pre-entry into the calibration area by acquiring the positioning signal within the time domain segment, filtering the effective time domain segment based on the delay spread value and bit error rate of the signal within the sub-time domain segment, determining the positioning information based on the positioning signal within the effective time domain segment, determining the momentum characteristics, and predicting the positioning information at each moment of the adjacent ineffective time domain segment based on the momentum characteristics.

[0013] A storage module, connected to the positioning module, is used to store positioning information within the valid time domain segment and to verify and store positioning information within the invalid time domain segment.

[0014] Furthermore, the inspection control module is used to control the inspection module to perform multipath effect monitoring, including:

[0015] This is used to control both the first inspection unit and the second inspection unit to stop moving, control the first inspection unit to continuously send positioning signals, and control the second inspection unit to acquire the signal characteristic values ​​of the positioning signals at each time.

[0016] Furthermore, the inspection control module is used to obtain the signal characteristic values ​​of the positioning signals corresponding to each monitoring area at each time, including:

[0017] Used to obtain the signal attenuation of the positioning signal in each monitoring area at each time;

[0018] The variance of the signal attenuation at each time point is used to calculate the characteristic value of the signal.

[0019] Furthermore, the label setting module is used to determine the number of obstacles based on the image of the monitoring area, and to calculate the multipath interferometry characterization value in combination with the signal features, including...

[0020] Used to identify several closed contours in the image of the monitored area and determine the number of obstacles;

[0021] The ratio of the number of obstacles to the preset standard number of obstacles is used to determine the first multipath interference factor;

[0022] The ratio of the signal feature value to a preset signal feature value is used to determine the second multipath interference factor;

[0023] The first multipath interference factor and the second multipath interference factor are weighted and summed to obtain the multipath interference characterization value.

[0024] Furthermore, the label setting module for calibrating the corresponding monitoring area includes,

[0025] If the multipath interference characterization value is greater than or equal to the preset multipath interference standard value, then the corresponding monitoring area is calibrated.

[0026] Furthermore, the positioning module is used to predict the travel vector based on the positioning information and determine whether to pre-enter the calibration area, including:

[0027] Used to obtain location information at at least two time points and determine coordinate points;

[0028] Used to construct a travel vector by connecting coordinate points according to time sequence;

[0029] If the travel vector passes through the calibration area, and the shortest distance between the coordinate point and the calibration area is less than a predetermined distance threshold, then it is determined that the target area is to be entered.

[0030] Furthermore, the positioning module is used to filter valid time domain segments based on the delay spread value and bit error rate of the signal within the sub-time domain segment, including:

[0031] Used to determine the time delay spread of the signal within each sub-time domain segment;

[0032] Used to determine the bit error rate of the signal within each sub-time domain segment;

[0033] If the delay spread value of the signal within the sub-time domain segment is less than the preset delay spread standard value, and the bit error rate of the signal is less than the preset signal bit error rate, then the sub-time domain segment is determined to be a valid time domain segment.

[0034] Furthermore, the positioning module is used to determine positioning information based on positioning signals within the effective time domain segment, and the determination of momentum characteristics includes,

[0035] Used to obtain location information at least two time points within the effective time domain segment to determine momentum characteristics;

[0036] The momentum characteristics include the speed of movement and the direction of movement.

[0037] Furthermore, the positioning module is used to predict the positioning information of adjacent ineffective time segments at each time based on momentum characteristics, including:

[0038] This is used to determine the direction of movement based on the momentum characteristics, and to determine the positioning information of the target at each moment based on the direction of movement and the speed of movement.

[0039] Furthermore, the storage module is used to verify the intra-location information of invalid time domain segments, including:

[0040] Location information used to determine the starting time of the next valid time segment adjacent to the invalid time segment;

[0041] Used to obtain the location information of the end time of the predicted ineffective time domain segment;

[0042] Used to determine the distance difference of positioning information, if the distance difference of positioning information is less than the predetermined distance difference threshold, then the corresponding positioning information in the invalid time domain segment is verified to be valid.

[0043] Compared with existing technologies, this invention improves the positioning accuracy of actual workers by setting up an inspection module, an inspection control module, a tag setting module, a positioning module, and a storage module to work together. Based on the inspection and inspection control modules, the inspection module monitors the multipath effect in the monitoring area. Then, based on the tag setting module, the multipath interference characterization value is calculated and the risk area is marked by image recognition and signal feature values. Through the cooperation of two positioning units in the positioning module, the effective time domain segment is determined and its momentum characteristics are obtained, thereby predicting the positioning information of the ineffective time domain segment. Finally, the positioning information is verified and stored by the storage module, thereby improving the positioning accuracy of actual workers, enhancing the accuracy and reliability of live-line operation early warning, and ensuring the safety of live-line operations in complex environments.

[0044] In particular, this invention determines the number of obstacles based on the image of the monitored area and calculates the multipath interference characterization value by combining the signal feature values. In actual live-line working scenarios, the work site is often filled with various complex facilities and obstacles. When the positioning signal encounters these obstacles, reflection, diffraction, and other phenomena occur, thus forming multiple propagation paths, i.e., multipath effect. This multipath effect causes delay and distortion in the positioning signal acquired by the receiving device, specifically manifested as an increase in the signal delay spread and a higher bit error rate. This directly affects the accuracy of positioning, causing deviations in the positioning personnel's location judgment. In live-line working, this positioning error may cause the workers to accidentally enter dangerous areas, making it impossible to issue timely and accurate alarms. Since signal strength may vary at different times due to multipath effects, calculating the variance of signal attenuation at each time point yields the signal characteristic value. This characteristic value characterizes the signal fluctuation at different times and allows for more accurate identification of times or areas where signal interference is significant. By determining the number of obstacles based on the monitoring area image, it's possible to intuitively understand where obstacles exist within the monitoring area and their approximate characteristics. Combining this with the signal characteristic value to calculate the multipath interference characterization value comprehensively reflects the severity of the multipath effect caused by obstacles on the positioning signal in the monitoring area. This method enables precise calibration of the monitoring area, identifying risk areas and providing reliable support for subsequent calibration of these risk areas. It adaptively matches different positioning methods, thereby improving the positioning accuracy of actual workers, enhancing the accuracy and reliability of live-line work early warning, and ensuring the safety of live-line work in complex environments.

[0045] In particular, this invention, through a second positioning unit responding to the target's pre-entry calibration area, acquires positioning signals within a time domain segment and filters valid time domain segments. In live-line working scenarios, signal transmission may be affected by multipath effects, causing signals to no longer propagate along a straight path but instead form multiple propagation paths. This results in the receiving device simultaneously receiving signals from multiple different paths with different time delays. These signals interfere with and superimpose with each other, producing invalid positioning signals. Therefore, by setting a time delay extension standard value, sub-time domain segments less affected by multipath effects can be effectively identified. Bit errors introduce erroneous information into signal transmission, and the bit error rate reflects the signal transmission quality. Based on the two key indicators of time delay extension value and bit error rate within the sub-time domain segment, this invention can effectively filter out valid time domain segments with low interference and accurate transmission. It can eliminate severely interfered and unreliable signal segments, retaining only valid signal segments. These segments are used as the basis for subsequent positioning, thereby improving the positioning accuracy of actual workers, enhancing the accuracy and reliability of live-line working early warning, and ensuring the safety of live-line working in complex environments.

[0046] In particular, this invention determines positioning information and momentum characteristics based on positioning signals within the effective time domain segment. Based on these momentum characteristics, it predicts positioning information for each moment in adjacent ineffective time domain segments. However, due to multipath effects and dynamic environmental changes, the reliability and stability of signals cannot be guaranteed. This leads to severe interference and signal quality degradation in ineffective time domain segments, making them unsuitable for accurate positioning. The target's movement speed and direction possess a certain continuity and inertia. Based on the principle of inertia in physics, it is assumed that the target's movement speed and direction will not change drastically in the short term. Therefore, these momentum characteristics can be used to reasonably predict positioning information in adjacent ineffective time domain segments. Thus, a travel vector can be constructed based on positioning information from at least two time points to determine the target's momentum characteristics, thereby predicting positioning information for each moment in adjacent ineffective time domain segments. By using momentum characteristics within the effective time domain segment for prediction, continuous positioning information can be provided within the ineffective time domain segment, compensating for insufficient or unreliable signals. This method can effectively reduce positioning interruptions or error accumulation caused by signal quality problems, ensure the continuity and accuracy of positioning information, thereby improving the positioning accuracy of actual operators, enhancing the accuracy and reliability of live-line operation early warning, and ensuring the safety of live-line operations in complex environments. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the live-line working early warning system based on artificial intelligence for precise positioning, as an embodiment of the invention.

[0048] Figure 2 This is a logic diagram for determining whether to calibrate the current monitoring area in an embodiment of the invention;

[0049] Figure 3This is a logic diagram for determining whether to pre-enter the calibration region according to an embodiment of the invention;

[0050] Figure 4 This is a logic diagram for determining whether a sub-time domain segment is a valid time domain segment in an embodiment of the invention.

[0051] Figure 5 This is a logic diagram for verifying whether to store internal positioning information of invalid time domain segments in an embodiment of the invention. Detailed Implementation

[0052] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0053] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0054] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0055] Please see Figure 1 The diagram shown is a structural schematic of a live-line work early warning system based on artificial intelligence precise positioning, according to an embodiment of the invention. The live-line work early warning system based on artificial intelligence precise positioning of the present invention includes:

[0056] The inspection module includes a first inspection unit and a second inspection unit that can move along a predetermined path in each monitoring area. The first inspection unit is equipped with a signal transmitting unit for continuously sending positioning signals and an image acquisition unit for acquiring images of the monitoring area. The second inspection unit is equipped with a signal receiving unit for receiving positioning signals at various times.

[0057] The inspection control module is connected to the inspection module and is used to control the second inspection unit to follow the first inspection unit at predetermined intervals, perform multipath effect monitoring in each monitoring area, and obtain the signal characteristic values ​​of the positioning signal corresponding to each monitoring area at each time.

[0058] The tag setting module, which is connected to the inspection control module, is used to determine the number of obstacles based on the image of the monitoring area, and calculate the multipath interference characterization value in combination with the signal feature value to calibrate the corresponding monitoring area.

[0059] The positioning module is connected to the tag setting module and includes a first positioning unit and a second positioning unit. The first positioning unit continuously acquires the positioning signal in response to the target starting positioning signal being in a non-calibration area, acquires positioning information based on the positioning signal, predicts the travel vector based on the positioning information, and determines whether to pre-enter the calibration area.

[0060] The second positioning unit responds to the target's pre-entry into the calibration area by acquiring the positioning signal within the time domain segment, filtering the effective time domain segment based on the delay spread value and bit error rate of the signal within the sub-time domain segment, determining the positioning information based on the positioning signal within the effective time domain segment, determining the momentum characteristics, and predicting the positioning information at each moment of the adjacent ineffective time domain segment based on the momentum characteristics.

[0061] A storage module, connected to the positioning module, is used to store positioning information within the valid time domain segment and to verify and store positioning information within the invalid time domain segment.

[0062] In implementation, there are no restrictions on the specific structure of the inspection module. The first inspection unit and the second inspection unit can be mobile inspection vehicles, as long as they can carry the corresponding equipment and move around.

[0063] Specifically, there are no restrictions on the structure of the signal transmitting unit and the signal receiving unit. In practical applications, it is only necessary to ensure that the signal receiving unit can obtain positioning information based on the positioning signal emitted by the signal transmitting unit. For example, the signal transmitting unit can be a UWB positioning tag, and the signal receiving unit can be a UWB positioning base station. The target carries a UWB positioning tag and obtains the target's positioning information through the UWB positioning base station. Of course, other methods can also be used, which will not be elaborated here.

[0064] Specifically, there are no restrictions on the specific structure of the inspection control module, tag setting module, positioning module, and storage module. They can all be composed of logic components, including field-programmable processors, computers, or microprocessors in computers.

[0065] Specifically, there are no restrictions on the specific structure of the image acquisition unit. The image acquisition unit can be a photographic device, as long as it can acquire images of the monitored area.

[0066] Specifically, the inspection control module is used to control the inspection module to perform multipath effect monitoring, including:

[0067] This is used to control both the first inspection unit and the second inspection unit to stop moving, control the first inspection unit to continuously send positioning signals, and control the second inspection unit to acquire the signal characteristic values ​​of the positioning signals at each time.

[0068] Specifically, the inspection control module is used to obtain the signal characteristic values ​​of the positioning signals of each monitoring area at each time, including:

[0069] Used to obtain the signal attenuation of the positioning signal in each monitoring area at each time;

[0070] The variance of the signal attenuation at each time point is used to calculate the characteristic value of the signal.

[0071] In practice, there are no restrictions on the method of obtaining the signal attenuation of the positioning signal at different times. It can be done through the signal strength monitoring function built into the positioning signal transceiver or through other methods. It is only necessary to ensure that the obtained signal attenuation data can accurately reflect the propagation loss of the signal at different times. This will not be elaborated further.

[0072] Specifically, the label setting module is used to determine the number of obstacles based on the image of the monitored area, and to calculate the multipath interferometry characterization value in combination with the signal features, including:

[0073] Used to identify several closed contours in the image of the monitored area and determine the number of obstacles;

[0074] The ratio of the number of obstacles to the preset standard number of obstacles is used to determine the first multipath interference factor;

[0075] The ratio of the signal feature value to a preset signal feature value is used to determine the second multipath interference factor;

[0076] The first multipath interference factor and the second multipath interference factor are weighted and summed to obtain the multipath interference characterization value.

[0077] In implementation, there is no limitation on the method of identifying several closed contours in the image of the monitoring area. Existing image processing algorithms for identifying closed contours or self-trained image processing algorithms or models that can achieve the corresponding functions can be used, and the corresponding functions can be implemented by importing them into the logic components.

[0078] In implementation, the preset standard number of obstacles is pre-set. Those skilled in the art can determine the number of obstacles in each scene by collecting a large amount of image data from different monitoring areas and calculate the average number of obstacles in each scene. The preset standard number of obstacles is set as the product of the average number of obstacles in each scene and the accuracy coefficient. The accuracy coefficient is selected in the range [1.05, 1.15]. In implementation, it is preferably 1.

[0079] In implementation, the preset signal characteristic value is pre-set. Those skilled in the art can collect a large amount of signal attenuation under different regional environments to solve the variance of signal attenuation at each time under each regional environment, obtain the signal characteristic value under each regional environment, and determine the mean of the signal characteristic value under each regional environment. The preset signal characteristic value is set as the product of the mean of the signal characteristic value under each regional environment and the accuracy coefficient. The accuracy coefficient is selected in the interval [1.05, 1.15]. In implementation, it is preferably 1.

[0080] In practice, when the first multipath interference factor and the second multipath interference factor are weighted and summed, the weight of the first multipath interference factor is 0.55 and the weight of the second multipath interference factor is 0.44.

[0081] Specifically, the label setting module is used to calibrate the corresponding monitoring area, including:

[0082] If the multipath interference characterization value is greater than or equal to the preset multipath interference standard value, then the corresponding monitoring area is calibrated.

[0083] In implementation, the preset multipath interference standard value is determined in advance, and the preset multipath interference standard value is selected within [1.15, 1.25].

[0084] This invention determines the number of obstacles based on the monitored area image and calculates multipath interference characterization values ​​by combining the signal feature values. In actual live-line working scenarios, the work site is often filled with various complex facilities and obstacles. When the positioning signal encounters these obstacles, reflection and diffraction occur, forming multiple propagation paths, i.e., multipath effect. This multipath effect causes delay and distortion in the positioning signal acquired by the receiving device, specifically manifested as increased signal delay spread and higher bit error rate. This directly affects the accuracy of positioning, causing deviations in the positioning personnel's location judgment. In live-line working, this positioning error may cause workers to accidentally enter dangerous areas, preventing timely and accurate alarms from being issued. Since signal strength may vary at different times due to multipath effects, calculating the variance of signal attenuation at each time point yields the signal characteristic value. This characteristic value characterizes the signal fluctuation at different times and allows for more accurate identification of times or areas where signal interference is significant. By determining the number of obstacles based on the monitoring area image, it's possible to intuitively understand where obstacles exist within the monitoring area and their approximate characteristics. Combining this with the signal characteristic value to calculate the multipath interference characterization value comprehensively reflects the severity of the multipath effect caused by obstacles on the positioning signal in the monitoring area. This method enables precise calibration of the monitoring area, identifying risk areas and providing reliable support for subsequent calibration of these risk areas. It adaptively matches different positioning methods, thereby improving the positioning accuracy of actual workers, enhancing the accuracy and reliability of live-line work early warning, and ensuring the safety of live-line work in complex environments.

[0085] Please see Figure 2 and Figure 3 As shown, Figure 2 This is a logic diagram for determining whether to calibrate the current monitoring area according to an embodiment of the invention. Figure 3 This is a logic diagram for determining whether to pre-enter a calibration area according to an embodiment of the invention. Specifically, the positioning module is used to predict the travel vector based on positioning information, and determining whether to pre-enter the calibration area includes...

[0086] Used to obtain location information at at least two time points and determine coordinate points;

[0087] Used to construct a travel vector by connecting coordinate points according to time sequence;

[0088] If the travel vector passes through the calibration area, and the shortest distance between the coordinate point and the calibration area is less than a predetermined distance threshold, then it is determined that the target area is to be entered.

[0089] It is understandable that the direction of the travel vector is the coordinate point at the previous time step pointing to the coordinate point at the next time step.

[0090] In practice, the predetermined distance threshold is preset and selected within the range of [1m, 3m]. In practice, 2m is preferred.

[0091] Please see Figure 4 As shown, this is a logic determination diagram for whether a sub-time domain segment is a valid time domain segment according to an embodiment of the invention. Specifically, the positioning module is used to filter valid time domain segments based on the delay spread value and bit error rate of the signal within the sub-time domain segment, including...

[0092] Used to determine the time delay spread of the signal within each sub-time domain segment;

[0093] Used to determine the bit error rate of the signal within each sub-time domain segment;

[0094] If the delay spread value of the signal within the sub-time domain segment is less than the preset delay spread standard value, and the bit error rate of the signal is less than the preset signal bit error rate, then the sub-time domain segment is determined to be a valid time domain segment.

[0095] In implementation, the preset delay spread standard value is predetermined. Those skilled in the art can collect a large amount of signal data under different environments to determine the delay spread value in each scenario and calculate the average value of the delay spread value in each scenario. The preset delay spread standard value is set as the product of the average value of the delay spread value in each scenario and the offset coefficient. The offset coefficient is selected in the range [1.25, 1.45], and is preferably 1.35 in implementation.

[0096] In implementation, the preset signal bit error rate is predetermined. Those skilled in the art can collect a large number of signal bit error rates under different environments, determine the signal bit error rate in each scenario, and calculate the average value of the signal bit error rate in each scenario. The preset signal bit error rate is set as the product of the average value of the signal bit error rate in each scenario and the offset coefficient, which is selected in the range [1.25, 1.45].

[0097] This invention utilizes a second positioning unit to respond to the target's pre-entry calibration area, acquire positioning signals within a time domain segment, and filter effective time domain segments. In live-line working scenarios, signal transmission may be affected by multipath effects, causing signals to no longer propagate along a straight path but instead form multiple propagation paths. This results in the receiving device simultaneously receiving signals from multiple different paths with different time delays. These signals interfere with and superimpose with each other, producing invalid positioning signals. Therefore, by setting a time delay extension standard value, sub-time domain segments less affected by multipath effects can be effectively identified. Bit errors introduce erroneous information into signal transmission, and the bit error rate reflects the signal transmission quality. Based on two key indicators—the time delay extension value and the bit error rate—this invention can effectively filter out effective time domain segments with low interference and accurate transmission, eliminating severely interfered and unreliable signal segments and retaining only effective signal segments. These segments are then used as the basis for subsequent positioning, thereby improving the positioning accuracy of actual workers, enhancing the accuracy and reliability of live-line work early warning, and ensuring the safety of live-line work in complex environments.

[0098] Specifically, the positioning module is used to determine positioning information based on positioning signals within a valid time domain segment, and the determination of momentum characteristics includes,

[0099] Used to obtain location information at least two time points within the effective time domain segment to determine momentum characteristics;

[0100] The momentum characteristics include the speed of movement and the direction of movement.

[0101] It is understandable that, based on the coordinate values ​​of two time points, the position of the target at the two time points can be obtained and the travel distance can be determined. The corresponding movement speed can be determined based on the time interval, and the movement direction is the direction from the coordinate point at the earlier time point to the coordinate point at the later time point.

[0102] Specifically, the positioning module is used to predict the positioning information of adjacent ineffective time segments at each time based on momentum characteristics, including:

[0103] This is used to determine the direction of movement based on the momentum characteristics, and to determine the positioning information of the target at each moment based on the direction of movement and the speed of movement.

[0104] It is understandable that once the direction and speed of movement are determined, the target's position at each moment can be predicted based on the corresponding speed and the original direction of movement. This will not be elaborated further.

[0105] This invention determines positioning information and momentum characteristics based on positioning signals within the effective time domain segment. Based on these momentum characteristics, it predicts positioning information for each moment in adjacent ineffective time domain segments. However, due to multipath effects and dynamic environmental changes, the reliability and stability of signals cannot be guaranteed. This leads to severe interference and signal quality degradation in ineffective time domain segments, rendering them unusable for accurate positioning. The target's speed and direction of movement possess a certain continuity and inertia. Based on the principle of inertia in physics, it is assumed that the target's speed and direction will not change drastically in the short term. Therefore, these momentum characteristics can be used to reasonably predict positioning information in adjacent ineffective time domain segments. Thus, a travel vector can be constructed based on positioning information from at least two time points to determine the target's momentum characteristics, thereby predicting positioning information for each moment in adjacent ineffective time domain segments. By utilizing momentum characteristics within the effective time domain segment for prediction, continuous positioning information can be provided within the ineffective time domain segment, compensating for insufficient or unreliable signals. This method can effectively reduce positioning interruptions or error accumulation caused by signal quality problems, ensure the continuity and accuracy of positioning information, thereby improving the positioning accuracy of actual operators, enhancing the accuracy and reliability of live-line operation early warning, and ensuring the safety of live-line operations in complex environments.

[0106] Please see Figure 5 This is a logic decision diagram for verifying whether to store intra-location information of invalid time domain segments, as described in an embodiment of the invention. Specifically, the storage module is used to verify intra-location information of invalid time domain segments, including...

[0107] Location information used to determine the starting time of the next valid time segment adjacent to the invalid time segment;

[0108] Used to obtain the location information of the end time of the predicted ineffective time domain segment;

[0109] Used to determine the distance difference of positioning information, if the distance difference of positioning information is less than the predetermined distance difference threshold, then the corresponding positioning information in the invalid time domain segment is verified to be valid.

[0110] It is understandable that the positioning information obtained in the next valid time segment adjacent to the non-valid time segment has a higher confidence level. The end time of the non-valid time segment is adjacent to the beginning time of the valid time segment. Based on this, the position information is determined by the positioning signal with a higher confidence level, and the predicted positioning information is verified to ensure accuracy.

[0111] Specifically, the distance difference between two positioning information is the distance between the corresponding coordinate points of the two positioning information. The distance difference threshold is predetermined. The purpose of setting the distance difference threshold is to reflect the situation where the predicted positioning information deviates significantly from the actual positioning information. Therefore, the distance difference threshold is selected within the range [3m, 5m] to reflect the situation where the error is large. In practice, 4m is preferred.

[0112] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A live-line working early warning system based on artificial intelligence for precise positioning, characterized in that, include: The inspection module includes a first inspection unit and a second inspection unit that can move along a predetermined path in each monitoring area. The first inspection unit is equipped with a signal transmitting unit for continuously sending positioning signals and an image acquisition unit for acquiring images of the monitoring area. The second inspection unit is equipped with a signal receiving unit for receiving positioning signals at various times. The inspection control module is connected to the inspection module and is used to control the second inspection unit to follow the first inspection unit at predetermined intervals, perform multipath effect monitoring in each monitoring area, and obtain the signal characteristic values ​​of the positioning signal corresponding to each monitoring area at each time. The tag setting module, which is connected to the inspection control module, is used to determine the number of obstacles based on the image of the monitoring area, and calculate the multipath interference characterization value in combination with the signal feature value to calibrate the corresponding monitoring area. The positioning module is connected to the tag setting module and includes a first positioning unit and a second positioning unit. The first positioning unit continuously acquires the positioning signal in response to the target starting positioning signal being in a non-calibration area, acquires positioning information based on the positioning signal, predicts the travel vector based on the positioning information, and determines whether to pre-enter the calibration area. The second positioning unit responds to the target's pre-entry into the calibration area by acquiring the positioning signal within the time domain segment, filtering the effective time domain segment based on the delay spread value and bit error rate of the signal within the sub-time domain segment, determining the positioning information based on the positioning signal within the effective time domain segment, determining the momentum characteristics, and predicting the positioning information at each moment of the adjacent ineffective time domain segment based on the momentum characteristics. A storage module, connected to the positioning module, is used to store positioning information within the valid time domain segment and to verify and store positioning information within the invalid time domain segment.

2. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The inspection control module is used to control the inspection module to perform multipath effect monitoring, including... This is used to control both the first inspection unit and the second inspection unit to stop moving, control the first inspection unit to continuously send positioning signals, and control the second inspection unit to acquire the signal characteristic values ​​of the positioning signals at each time.

3. The live-line working early warning system based on artificial intelligence precise positioning according to claim 2, characterized in that, The inspection control module is used to obtain the signal characteristic values ​​of the positioning signals of each monitoring area at each time, including... Used to obtain the signal attenuation of the positioning signal in each monitoring area at each time; The variance of the signal attenuation at each time point is used to calculate the characteristic value of the signal.

4. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The label setting module is used to determine the number of obstacles based on the image of the monitored area, and to calculate the multipath interferometry characterization value in combination with the signal features, including... Used to identify several closed contours in the image of the monitored area and determine the number of obstacles; The ratio of the number of obstacles to the preset standard number of obstacles is used to determine the first multipath interference factor; The ratio of the signal feature value to a preset signal feature value is used to determine the second multipath interference factor; The first multipath interference factor and the second multipath interference factor are weighted and summed to obtain the multipath interference characterization value.

5. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The label setting module is used to calibrate the corresponding monitoring area, including: If the multipath interference characterization value is greater than or equal to the preset multipath interference standard value, then the corresponding monitoring area is calibrated.

6. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The positioning module is used to predict the travel vector based on positioning information and determine whether to pre-enter the calibration area, including... Used to obtain location information at at least two time points and determine coordinate points; Used to construct a travel vector by connecting coordinate points according to time sequence; If the travel vector passes through the calibration area, and the shortest distance between the coordinate point and the calibration area is less than a predetermined distance threshold, then it is determined that the target area is to be entered.

7. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The positioning module is used to filter valid time domain segments based on the delay spread value and bit error rate of the signal within the sub-time domain segment. Used to determine the time delay spread of the signal within each sub-time domain segment; Used to determine the bit error rate of the signal within each sub-time domain segment; If the delay spread value of the signal within the sub-time domain segment is less than the preset delay spread standard value, and the bit error rate of the signal is less than the preset signal bit error rate, then the sub-time domain segment is determined to be a valid time domain segment.

8. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The positioning module is used to determine positioning information based on positioning signals within a valid time domain segment, and the determination of momentum characteristics includes, Used to obtain location information at least two time points within the effective time domain segment to determine momentum characteristics; The momentum characteristics include the speed of movement and the direction of movement.

9. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The positioning module is used to predict the positioning information of adjacent ineffective time segments at each time based on momentum characteristics, including: This is used to determine the direction of movement based on the momentum characteristics, and to determine the positioning information of the target at each moment based on the direction of movement and the speed of movement.

10. The live-line working early warning system based on artificial intelligence precise positioning according to claim 1, characterized in that, The storage module is used to verify the intra-location information of invalid time domain segments, including: Location information used to determine the starting time of the next valid time segment adjacent to the invalid time segment; Used to obtain the location information of the end time of the predicted ineffective time domain segment; Used to determine the distance difference of positioning information, if the distance difference of positioning information is less than the predetermined distance difference threshold, then the corresponding positioning information in the invalid time domain segment is verified to be valid.

Images