Intelligent safety helmet for high-precision positioning and control system thereof

Abstract

The invention relates to the technical field of high-precision positioning, in particular to an intelligent safety helmet for high-precision positioning and a control system of the intelligent safety helmet. The site modeling module is used for dividing a site model into an alarm area and a non-alarm area; the positioning calculation module is used for obtaining safety helmet site model positioning; the intelligent bidirectional alarm module is used for carrying out UWB alarm and also used for carrying out touch alarm; the precision monitoring module is used for judging the alarm precision of the UWB alarm to obtain an alarm area with abnormal alarm precision; the precision control module is used for optimizing the UWB alarm process to obtain a UWB alarm optimization result; and the precision optimization module is used for analyzing the fault reasons of the high-frequency alarm point locations, eliminating and optimizing the judgment process of the high-frequency alarm point locations according to the fault reasons of the high-frequency alarm point locations, and optimizing the site model. The positioning precision and the alarm precision of the safety helmet in the construction area are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-precision positioning, and particularly to an intelligent safety helmet for high-precision positioning and its control system. Background Art

[0002] In complex scenarios such as urban canyons, indoor environments or mines, satellite signals will produce multipath effects due to reflections from buildings, mountains, mine tunnels, etc., resulting in signal distortion and positioning errors. Especially in the complex underground environment of mines with criss-crossing channels, traditional positioning means are difficult to meet the requirements.

[0003] Chinese Patent Publication No. CN105581411B discloses an intelligent safety helmet and personnel positioning management system and method, including a safety helmet main body and a host processor, an RFID tag, a power supply module, a wireless transmission module, a wearing state monitoring module arranged on the safety helmet main body. It is characterized in that: the wearing state monitoring module includes a controller, an LED lamp, a DC piezoelectric buzzer and two to three capacitive proximity sensors; the capacitive proximity sensors are arranged inside the safety helmet main body. When the intelligent safety helmet is worn on the head, a coupling capacitance is formed between the human body electric field, the head and the conductor layer of the capacitive proximity sensor. By detecting the change of the coupling capacitance to determine the wearing condition of the intelligent safety helmet and output a signal to the capacitive induction controller; the capacitive induction controller receives the signal output by the capacitive proximity sensor, and the built-in induction algorithm of the capacitive induction controller determines whether the head contacts the capacitive proximity sensor, but this solution cannot provide accurate positioning for underground workers, resulting in a decrease in the positioning accuracy of the intelligent safety helmet. Summary of the Invention

[0004] Therefore, the present invention provides an intelligent safety helmet for high-precision positioning and its control system in the technical field of high-precision positioning, especially to overcome the problem of low positioning accuracy of the safety helmet due to complex construction site conditions and signal interference in the prior art.

[0005] To achieve the above object, on the one hand, the present invention provides an intelligent safety helmet for high-precision positioning, including:

[0006] A safety helmet body, as the main part of the safety helmet, for protecting the head of the staff;

[0007] A target tag, installed at the front edge of the safety helmet body, for receiving and feedbacking UWB signals emitted by a UWB base station;

[0008] An altitude measuring instrument, installed at the tail of the safety helmet body, for measuring the real-time altitude of the intelligent safety helmet;

[0009] A reserve battery, installed below the altitude measuring instrument, for supplying power to each component of the intelligent safety helmet;

[0010] The control system of the intelligent safety helmet for high-precision positioning is connected to the helmet body and is used for safety warning of the intelligent safety helmet.

[0011] On the other hand, the present invention also provides a control system of an intelligent safety helmet for high-precision positioning, including:

[0012] A data acquisition module for acquiring UWB signal data, the Z-axis coordinates of the safety helmet, and infrared change data;

[0013] A site modeling module for modeling the construction site according to the UWB signal data to obtain a site model, and dividing the site model into a warning area and a non-warning area according to the site plan;

[0014] A positioning and calculation module for calculating the position of the safety helmet in the site model according to the UWB base station reception time in the UWB signal data to obtain the positioning of the safety helmet in the site model;

[0015] An intelligent two-way warning module for performing UWB warning according to the positioning of the safety helmet in the site model, and also for performing touch warning according to the infrared change data set;

[0016] An accuracy monitoring module for judging the warning accuracy of the UWB warning according to the first warning result of the UWB warning and the second warning result of the touch warning to obtain a warning area with abnormal warning accuracy;

[0017] An accuracy control module for optimizing the UWB warning process according to the warning area with abnormal warning accuracy to obtain a UWB warning optimization result, and also for supplementing the UWB warning optimization result according to the multipath area in the warning area to obtain a supplemented UWB warning optimization result, and also for adjusting the supplemented UWB warning optimization result according to the key area in the warning area to obtain an adjusted UWB warning optimization result, and also for optimizing the key area according to the reserved area;

[0018] An accuracy optimization module for judging high-frequency warning points according to the number of times of abnormal UWB warning accuracy, and adjusting the UWB warning optimization result according to the high-frequency warning points, and also for analyzing the failure causes of the high-frequency warning points, and eliminating and optimizing the judgment process of the high-frequency warning points according to the failure causes of the high-frequency warning points, and optimizing the site model.

[0019] Further, the positioning and calculation module calculates the distance d1 between the target tag and base station A according to the time t1 when the target tag reflects the signal to base station A and the UWB signal propagation speed Vc, sets d1 = t1 × Vc, calculates the distance d2 between the target tag and base station B according to the time t2 when the target tag reflects the signal to base station B and the UWB signal propagation speed Vc, sets d2 = t2 × Vc, where Vc = 3×10 8 m / s, and solves the coordinates (x, y) of the target tag M according to the coordinates (x1, y1) of base station A, the coordinates (x2, y2) of base station B, the distance d1 from the target tag M to base station A, and the distance d2 from the target tag M to base station B, and sets

[0020] Further, when the intelligent two-way warning module performs UWB warning according to the positioning of the safety helmet site model, it compares the Z-axis coordinate z of the target tag with the maximum Z-axis coordinate z0 and the minimum Z-axis coordinate z1 of the warning area, and judges the Z-axis coincidence state between the target tag and the warning area according to the comparison result, where:

[0021] When z > z0, the intelligent two-way warning module determines that the Z-axis coincidence state between the target tag and the warning area is a non-coincidence state;

[0022] When z < z1, the intelligent two-way warning module determines that the Z-axis coincidence state between the target tag and the warning area is a non-coincidence state;

[0023] When z1 ≤ z ≤ z0, the intelligent two-way warning module determines that the Z-axis coincidence state between the target tag and the warning area is a coincidence state.

[0024] Further, the intelligent two-way warning module compares the warning distance L with the preset warning distance L0, judges the coincidence state between the target tag and the warning area according to the comparison result, and performs UWB warning according to the judgment result, where:

[0025] When L ≤ L0, the intelligent two-way warning module determines that the target tag coincides with the warning area, performs UWB warning, and takes the radiation range of the current coordinates of the target tag as the first warning result of the UWB warning;

[0026] When L > L0, the intelligent two-way warning module determines that the target tag does not coincide with the warning area and does not perform UWB warning;

[0027] When the intelligent two-way warning module performs touch warning, it compares the touch distance D between the user and the warning area with the preset touch distance D0, and performs touch warning according to the comparison result, where:

[0028] When D > D0, no touch warning is given;

[0029] When D ≤ D0, a touch warning is given, the infrared touch trap issues a warning and records it, and the radiation range of the current coordinates of the infrared touch trap is used as the second warning result of the touch warning.

[0030] Further, the accuracy monitoring module compares the warning count T1 of the first warning result of the UWB warning with the warning count T2 of the second warning result of the touch warning, and determines the warning accuracy of the UWB warning according to the comparison result, where:

[0031] When T1 = T2, the accuracy monitoring module determines that the warning accuracy of the UWB warning is normal;

[0032] When T1 > T2, the accuracy monitoring module determines that the warning accuracy of the UWB warning is abnormal, and selects the intersection of the radiation range corresponding to the first warning result of the UWB warning and the radiation range corresponding to the second warning result of the touch warning as the warning area with abnormal warning accuracy;

[0033] When T1 < T2, the accuracy monitoring module determines that the warning accuracy of the UWB warning is abnormal, and selects the intersection of the radiation range corresponding to the first warning result of the UWB warning and the radiation range corresponding to the second warning result of the touch warning as the warning area with abnormal warning accuracy.

[0034] Further, the accuracy control module compares the uniformity f(X) of the warning area with abnormal warning accuracy with the preset uniformity f(X0), sets f(X0) ≥ 0.85, and determines the uniformity of the warning area with abnormal warning accuracy according to the comparison result, where:

[0035] When f(X) < f(X0), the accuracy control module determines that the uniformity of the warning area with abnormal warning accuracy is qualified;

[0036] When f(X) ≥ f(X0), the accuracy control module determines that the uniformity of the warning area with abnormal warning accuracy is unqualified;

[0037] When the uniformity status of the warning area with abnormal warning accuracy is inappropriate, the accuracy control module adjusts the two-dimensional vector of the base station to obtain the adjusted two-dimensional vector of the base station X2 = (x21 + Δx1, y21 + Δy1, x22 + Δx2, y22 + Δy2, …, x2 m +Δx m ,y m +Δy m), calculate the uniformity difference Δf according to the uniformity f(X') of the alarm area with abnormal alarm accuracy after adjustment and the uniformity f(X) of the alarm area with abnormal alarm accuracy. Set Δf = f(X') - f(X). Also, judge the qualification of the uniformity of the alarm area with abnormal alarm accuracy after adjustment according to the calculation result, and optimize the UWB alarm process according to the judgment result, where:

[0038] When Δf < 0, the precision control module determines that the qualification of the uniformity of the alarm area with abnormal alarm accuracy after adjustment is qualified, and optimizes the UWB alarm process. Replace the coordinates of the two-dimensional vector of the base station after adjustment with the coordinates of the two-dimensional vector of the total number of base stations, and use the adjustment result as the UWB alarm optimization result;

[0039] When Δf ≥ 0, the precision control module determines that the qualification of the uniformity of the alarm area with abnormal alarm accuracy after adjustment is unqualified, and continues to adjust the coordinates of the two-dimensional vector of the base station after adjustment until Δf > 0;

[0040] When the precision control module supplements the UWB alarm optimization result, it takes the average signal strength of the alarm area with abnormal alarm accuracy and compares it with the preset average signal strength Set Judge the multipath area according to the comparison result, and supplement the UWB alarm optimization result according to the judgment result, where:

[0041] When , the precision control module determines that the alarm area with abnormal alarm accuracy is not a multipath area, and does not supplement the UWB alarm optimization result;

[0042] When , the precision control module determines that the alarm area with abnormal alarm accuracy is a multipath area, and supplements the UWB alarm optimization result. Set the supplementary coefficient Supplement the uniformity difference Δf according to the supplementary coefficient W, and the preset uniformity difference after supplementation is Δf W , set Δf W = f(X') - f(X) × W, and obtain the UWB alarm optimization result after supplementation.

[0043] Furthermore, the precision control module outputs the recurrent neural network model that meets the performance as the alarm area evaluation model, and inputs the accidents in the alarm area with abnormal alarm accuracy collected in real time into the alarm area evaluation model to output the evaluation result of the alarm area with abnormal alarm accuracy;

[0044] When the alarm area with abnormal alarm accuracy output by the alarm area evaluation model is a key area, according to the weight coefficient where C1 is the area of the key area and Cz is the total area of the alarm area, calculate the adjusted preset uniformity f(X0'), set f(X0') = (1 + α) × f(X0), and re-optimize the UWB alarm process for this key area to obtain the adjusted UWB alarm optimization result;

[0045] When the alarm area with abnormal alarm accuracy output by the alarm area evaluation model is an ordinary alarm area, the preset uniformity f(X0) is not adjusted.

[0046] Furthermore, the accuracy control module compares the new key area uniformity f(X)3 with the adjusted preset uniformity f(X0'), judges the compliance of the new key area uniformity according to the comparison result, and adjusts the total number of base stations in the new key area according to the judgment result, where:

[0047] When f(X)3 ≤ f(X0'), the accuracy control module determines that the compliance of the new key area uniformity is not met, and adjusts the total number of base stations in the new key area. The adjustment method is to gradually increase the total number of base stations in the new key area at an increasing frequency with an increment of 1 until f(X)3 > f(X0');

[0048] When f(X)3 > f(X0'), the accuracy control module determines that the compliance of the new key area uniformity is met, and does not adjust the total number of base stations in the new key area.

[0049] Furthermore, when the accuracy optimization module judges the high-frequency alarm points, it compares the UWB alarm accuracy abnormal times B with the preset UWB alarm accuracy abnormal times B0, sets B0 ≥ 5 times, and judges the alarm point situation of the alarm area according to the comparison result, and adjusts the UWB alarm optimization result according to the judgment result, where:

[0050] When B > B0, the accuracy optimization module determines that the alarm point situation of the alarm area is high-frequency alarm points, sets the adjustment coefficient V = e B-B0 -1, where e is the base of the natural logarithm function, and adjusts the preset uniformity f(X0) of the alarm area where the high-frequency alarm points are located according to the adjustment coefficient to obtain the preset uniformity of the high-frequency alarm area. The adjusted preset uniformity of the high-frequency alarm area is f(X0) B , set f(X0) B = f(X0) × E;

[0051] When B ≤ B0, the accuracy optimization module determines that the alarm point situation of the alarm area is normal alarm points;

[0052] When the warning point situation in the warning area of the accuracy optimization module is a high-frequency warning point, the fault data collected in real time is input into the fault cause analysis model, and the fault cause analysis result of the fault data is output. The fault cause analysis result includes the general cause and the signal transmission cause, where:

[0053] When the fault cause analysis result of the fault data output by the fault cause analysis model is the general cause, check and repair the target tag and the UWB base station;

[0054] When the fault cause analysis result of the fault data output by the fault cause analysis model is the signal transmission cause, remove the high-frequency warning points from the warning area, and optimize the site model according to the signal transmission method. The optimization method is to change the signal transmission method of UWB. The signal transmission methods include simultaneous transmission and intermittent transmission.

[0055] Compared with the prior art, the beneficial effects of the present invention are as follows: The system comprehensively collects UWB signal data, safety helmet positioning data, and infrared change data through the data acquisition module, providing rich and accurate original information for subsequent data analysis and processing. The data fusion module fuses various collected data to form a more valuable data set, improving the availability and relevance of the data, and providing strong support for the accurate analysis and decision-making of subsequent modules. The positioning and calculation module calculates the position of the safety helmet in the site model to achieve real-time positioning and tracking of personnel. The intelligent two-way warning module determines whether the safety helmet is in the warning area and issues a UWB warning, and calculates the touch distance based on the infrared change data and triggers a touch warning to achieve multi-dimensional and all-round safety warnings, effectively reducing the possibility of safety accidents. The accuracy monitoring module compares the touch warning and the UWB warning results to accurately judge the accuracy of the UWB warning, find out the area with abnormal warning accuracy, and provide a clear direction for subsequent optimization, which helps to improve the reliability of the warning system. The accuracy control module optimizes the UWB warning accuracy according to the judgment result of the warning accuracy abnormal area, supplements, adjusts, and optimizes the warning result in combination with the multipath area, the key area, and the reserved area, comprehensively improving the accuracy and stability of the UWB warning. The accuracy optimization module also judges the high-frequency warning points and adjusts the UWB warning optimization result, analyzes the fault cause and optimizes the judgment process, and at the same time optimizes the site model, UWB points, and UWB signal transmission method, continuously improving the overall performance and safety of the system. Brief Description of the Drawings

[0056] Figure 1 It is a schematic structural diagram of the intelligent safety helmet for high-precision positioning in this embodiment;

[0057] Figure 2This is a schematic structural diagram of the system of the intelligent safety helmet for high-precision positioning in this embodiment. Detailed implementation manners

[0058] In order to make the objectives and advantages of the present invention more clearly understood, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only for explaining the present invention and are not used to limit the present invention.

[0059] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0060] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0061] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. 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 directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0062] Please refer to Figure 1 As shown, it is a schematic structural diagram of the intelligent safety helmet for high-precision positioning in this embodiment. The intelligent safety helmet includes:

[0063] A safety helmet cap body 1, which serves as the main part of the safety helmet;

[0064] A target tag 2, installed at the front edge of the safety helmet cap body 1, for receiving and feedbacking the UWB signal emitted by the UWB base station;

[0065] An altitude measuring instrument 3, installed at the tail of the safety helmet cap body 1, for measuring the real-time altitude of the intelligent safety helmet;

[0066] A reserve battery 4, installed below the altitude measuring instrument 3, for supplying power to each component of the intelligent safety helmet;

[0067] A control system 5 of the intelligent safety helmet for high-precision positioning, connected to the safety helmet cap body 1, for performing safety warnings on the safety helmet.

[0068] Please refer to Figure 2 as shown in the figure, which is a schematic structural diagram of the system of the intelligent safety helmet for high-precision positioning in this embodiment. The system includes:

[0069] A data acquisition module for collecting UWB signal data, the Z-axis coordinates of the safety helmet, and infrared change data;

[0070] A site modeling module for modeling the construction site according to the UWB signal data to obtain a site model, and dividing the site model into a warning area and a non-warning area according to the site plan. The site modeling module is connected to the data acquisition module;

[0071] A positioning and calculation module for calculating the position of the safety helmet in the site model according to the UWB base station reception time in the UWB signal data to obtain the positioning of the safety helmet in the site model. The positioning and calculation module is connected to the site modeling module;

[0072] An intelligent two-way warning module for performing UWB warning according to the positioning of the safety helmet in the site model, and also for performing touch warning according to the infrared change data set. The intelligent two-way warning module is connected to the positioning and calculation module;

[0073] An accuracy monitoring module for judging the warning accuracy of the UWB warning according to the first warning result of the UWB warning and the second warning result of the touch warning to obtain a warning area with abnormal warning accuracy. The accuracy monitoring module is connected to the intelligent two-way warning module;

[0074] An accuracy control module for optimizing the UWB warning process according to the warning area with abnormal warning accuracy to obtain a UWB warning optimization result, and also for supplementing the UWB warning optimization result according to the multipath area in the warning area to obtain a supplemented UWB warning optimization result, and also for adjusting the supplemented UWB warning optimization result according to the key area in the warning area to obtain an adjusted UWB warning optimization result, and also for optimizing the key area according to the reserved area. The accuracy control module is connected to the accuracy monitoring module;

[0075] An accuracy optimization module for judging high-frequency warning points according to the number of times of abnormal UWB warning accuracy, and adjusting the UWB warning optimization result according to the high-frequency warning points, and also for analyzing the failure reasons of the high-frequency warning points, and eliminating and optimizing the judgment process of the high-frequency warning points according to the failure reasons of the high-frequency warning points, and optimizing the site model. The accuracy optimization module is connected to the accuracy control module.

[0076] Specifically, the control system of the intelligent safety helmet for high-precision positioning is applied to the intelligent safety helmet for high-precision positioning. The system comprehensively collects UWB signal data, safety helmet positioning data, and infrared change data through the data acquisition module, providing rich and accurate original information for subsequent data analysis and processing. The data fusion module fuses various collected data to form a more valuable data set, improving the usability and relevance of the data and providing strong support for the precise analysis and decision-making of subsequent modules. The positioning calculation module calculates the position of the safety helmet in the site model to achieve real-time positioning and tracking of personnel. The intelligent two-way warning module determines whether the safety helmet is in the warning area and issues a UWB warning, and calculates the touch distance based on the infrared change data and triggers a touch warning to achieve multi-dimensional and all-round safety warnings, effectively reducing the possibility of safety accidents. The accuracy monitoring module compares the touch warning and UWB warning results to accurately judge the accuracy of the UWB warning, find out the areas with abnormal warning accuracy, and provide a clear direction for subsequent optimization, which helps to improve the reliability of the warning system. The accuracy control module optimizes the UWB warning accuracy according to the judgment result of the warning accuracy abnormal area, supplements, adjusts, and optimizes the warning result in combination with the multipath area, key area, and reserved area, comprehensively improving the accuracy and stability of the UWB warning. The accuracy optimization module also determines the high-frequency warning points and adjusts the UWB warning optimization result, analyzes the cause of the fault and optimizes the judgment process, and at the same time optimizes the site model, UWB points, and UWB signal transmission method to continuously improve the overall performance and safety of the system.

[0077] Specifically, when the data acquisition module collects UWB signal data, it sends signals to the target tag through the UWB base station. The target tag reflects the signals back to the UWB base station to obtain UWB signal data. The UWB signal data includes the number of UWB alarm triggers, the signal reception time of each UWB base station, the signal strength change, and the signal propagation speed. When the data acquisition module collects the Z-axis coordinates of the safety helmet, it obtains the Z-axis coordinates of the safety helmet in real time through the altitude coordinate instrument. When the data acquisition module collects the infrared change data, it collects the number of times the infrared touch trap is triggered when the staff wearing the safety helmet passes through the infrared touch trap. The position of the safety helmet refers to the specific point in space of the safety helmet determined by using the UWB signal data through the transmission and reflection of signals between the UWB base station and the target tag. The Z-axis coordinates of the safety helmet refer to the data collected in real time by the altitude coordinate instrument, representing the position information of the safety helmet in the vertical direction, that is, the altitude where the staff is located. The infrared touch trap refers to a monitoring device. When the staff wearing the safety helmet passes near the device, it will trigger the infrared induction of the device, thereby recording the number of triggers. It can be understood that the infrared touch trap is not limited in this embodiment. For example, an infrared induction curtain can be set as the infrared touch trap. The infrared change data includes the infrared distance between the infrared touch trap and the user and the number of alarms of the infrared touch trap when the infrared rays irradiate the user.

[0078] Specifically, the data acquisition module plays a role in obtaining the position trajectory of the safety helmet, vertical direction positioning, and monitoring the entry and exit of personnel in a specific area through the signal interaction between the UWB base station and the target tag, the altitude coordinate instrument, and the infrared touch trap, comprehensively improving the monitoring level of the staff's status and the working environment.

[0079] Specifically, the site modeling module inputs the signal strength change and the signal propagation speed into the GIS software to construct the site model, and divides the site model into regions according to the construction plan to obtain the alarm region and the non-alarm region.

[0080] It can be understood that the way of dividing the site model in this embodiment is not limited. For example, the site model can be divided according to the alarm region coordinates and non-alarm region coordinates in the construction plan. The construction plan refers to the engineering arrangement and regional planning of the construction site by the staff.

[0081] Specifically, the positioning and calculation module calculates the distance d1 between the target tag and base station A according to the time t1 when the target tag reflects the signal to base station A and the UWB signal propagation speed Vc, sets d1 = t1×Vc, calculates the distance d2 between the target tag and base station B according to the time t2 when the target tag reflects the signal to base station B and the UWB signal propagation speed Vc, sets d2 = t2×Vc, where Vc = 3×10 8 m / s, and solves the coordinates (x, y) of the target tag M according to the coordinates (x1, y1) of base station A, the coordinates (x2, y2) of base station B, the distance d1 from the target tag M to base station A, and the distance d2 from the target tag M to base station B, and sets

[0082] Specifically, the time t1 when the target tag reflects the signal to base station A refers to the propagation time of the reflected signal without obstacles between the target tag and base station A. In this embodiment, the acquisition method of the time t1 when the target tag reflects the signal to base station A is not limited. For example, a monitoring camera on the site can be set to select a base station without obstacles between the target tag and the base station, and the propagation time of the reflected signal of the base station without obstacles between the target tags is obtained through the built-in clock, and it is used as the time t1 when the target tag reflects the signal to base station A. The time t2 when the target tag reflects the signal to base station B refers to the propagation time of the reflected signal without obstacles between the target tag and base station B. The acquisition method of the time t2 when the target tag reflects the signal to base station B is the same as the acquisition method of the time t1 when the target tag reflects the signal to base station A.

[0083] Specifically, the method of solving the target tag through the base station coordinates can accurately calculate the specific position of the current target tag in the site model, which is beneficial to monitoring the behavior and activity trajectory of the target tag and facilitating the issuance of instructions to the target tag.

[0084] Specifically, when the intelligent two-way warning module performs UWB warning according to the positioning of the safety helmet site model, it compares the Z-axis coordinate z of the target tag with the maximum Z-axis coordinate z0 and the minimum Z-axis coordinate z1 of the warning area, and judges the Z-axis coincidence state between the target tag and the warning area according to the comparison result, where:

[0085] When z > z0, the intelligent two-way warning module determines that the Z-axis coincidence state between the target tag and the warning area is a non-coincidence state;

[0086] When z < z1, the intelligent two-way warning module determines that the Z-axis coincidence state between the target tag and the warning area is a non-coincidence state;

[0087] When z1 ≤ z ≤ z0, the intelligent two-way warning module determines that the Z-axis coincidence state of the target tag and the warning area is the coincidence state.

[0088] Specifically, the maximum Z-axis coordinate of the warning area refers to the highest limit value in the Z-axis direction of the pre-set warning area in the site model. For example, if z0 = 5 is set, the minimum Z-axis coordinate of the warning area refers to the lowest limit value in the Z-axis direction of the warning area in the site model. For example, if z1 = 2 is set, the Z-axis coincidence state of the warning area is a state description for judging the positional relationship between the target tag and the set warning area in the Z-axis direction. When the Z-axis coordinate of the target tag is between the minimum Z-axis coordinate and the maximum Z-axis coordinate of the warning area, it is determined that the Z-axis coincidence state of the target tag and the warning area is the coincidence state, indicating that a person or an object is within the warning area; when the Z-axis coordinate of the target tag is greater than the maximum Z-axis coordinate or less than the minimum Z-axis coordinate, it is determined as the non-coincidence state, indicating that a person or an object is outside the warning area.

[0089] Specifically, by comparing the Z-axis coordinate of the target tag with the maximum and minimum Z-axis coordinates of the warning area to judge the coincidence state, precise monitoring of a specific height area can be achieved. In an actual scenario, such as in a construction site, a high-risk area can be set as the warning area. When the Z-axis coordinate of the target tag on the safety helmet worn by a worker is greater than the maximum Z-axis coordinate of the warning area, it means that the person is in a dangerous high area. The intelligent two-way warning module determines non-coincidence and gives a timely warning to remind the person to pay attention to safety; the same applies when the coordinate is less than the minimum Z-axis coordinate of the warning area.

[0090] Specifically, when the Z-axis coincidence state of the target tag and the warning area is the coincidence state, the intelligent two-way warning module calculates the warning distance L according to the coordinates (x, y) of the target tag M and the coordinates (xmax, ymax) of the farthest warning area boundary point Qmax, and sets And compares the warning distance L with the preset warning distance L0, and judges the coincidence state of the target tag and the warning area according to the comparison result, and performs UWB warning according to the judgment result, where:

[0091] When L ≤ L0, the intelligent two-way warning module determines that the target tag coincides with the warning area and performs UWB warning, and takes the radiation range of the current coordinates of the target tag as the first warning result of the UWB warning;

[0092] When L > L0, the intelligent two-way warning module determines that the target tag does not coincide with the warning area and does not perform UWB warning;

[0093] Among them, the preset warning distance L0 is calculated according to the coordinates (xmax, ymax) of the farthest warning area boundary point Qmax and the coordinates (xmin, ymin) of the nearest warning area boundary point Qmin, and it is set that The preset warning distance L0 is an index for judging whether the target tag is located within the warning area. The farthest warning area boundary point refers to the boundary point on the warning area boundary that is the farthest from the target tag, and the nearest warning area boundary point refers to the boundary point on the warning area boundary that is the closest to the target tag.

[0094] Specifically, the radiation range of the current coordinates of the target tag refers to a circular range with the current coordinate point of the target tag as the center and a radius of R1. For example, R1 = 1m is set.

[0095] Specifically, when the Z-axis of the target tag coincides with the warning area, by calculating the warning distance and comparing it with the preset warning distance, the judgment on whether the target tag is in the warning area is further refined. When L is less than or equal to L0, it is determined as coincidence and an alarm is issued. This enables the staff to promptly know that they are in a dangerous warning area. For example, in a complex industrial production workshop, it can effectively remind personnel to evacuate the dangerous area in time to avoid the occurrence of safety accidents. When L is greater than L0, it is determined as non-coincidence and no alarm is issued to avoid unnecessary false alarms, thereby improving the accuracy and effectiveness of the alarm.

[0096] Specifically, when the intelligent two-way warning module performs touch warning, it compares the touch distance D between the user and the warning area with the preset touch distance D0, and performs touch warning according to the comparison result, where:

[0097] When D > D0, no touch warning is performed;

[0098] When D ≤ D0, touch warning is performed, the infrared touch trap issues a warning and records it, and the radiation range of the current coordinates of the infrared touch trap is used as the second warning result of the touch warning.

[0099] Specifically, the touch distance between the user and the warning area refers to that of the infrared touch trap. The preset touch distance is an index for judging whether to perform touch warning. The radiation range of the current coordinates of the infrared touch trap refers to a circular range with the current coordinate point of the infrared touch trap as the center and a radius of R2. For example, R2 = 1m is set.

[0100] Specifically, by accurately comparing the touch distance D between the user and the warning area with the preset touch distance D0, it is possible to promptly identify whether a person has entered the dangerous area. When D is less than or equal to D0, an alarm is triggered, and the infrared touch trap emits a warning, which can effectively remind the person that they are about to step into the dangerous area, avoid approaching the danger source due to negligence, reduce the probability of safety accidents, and build a solid defense line for the safety of personnel.

[0101] Specifically, the accuracy monitoring module compares the number of alarm times T1 of the first alarm result of the UWB alarm with the number of alarm times T2 of the second alarm result of the touch alarm, and judges the alarm accuracy of the UWB alarm according to the comparison result, where:

[0102] When T1 = T2, the accuracy monitoring module determines that the alarm accuracy of the UWB alarm is normal;

[0103] When T1 > T2, the accuracy monitoring module determines that the alarm accuracy of the UWB alarm is abnormal, and selects the intersection of the radiation range corresponding to the first alarm result of the UWB alarm and the radiation range corresponding to the second alarm result of the touch alarm as the alarm area with abnormal alarm accuracy;

[0104] When T1 < T2, the accuracy monitoring module determines that the alarm accuracy of the UWB alarm is abnormal, and selects the intersection of the radiation range corresponding to the first alarm result of the UWB alarm and the radiation range corresponding to the second alarm result of the touch alarm as the alarm area with abnormal alarm accuracy.

[0105] Specifically, the UWB alarm accuracy refers to the alarm accuracy of the alarm area corresponding to the UWB alarm.

[0106] Specifically, by comparing the first alarm number T1 of the UWB alarm with the second alarm number T2 of the touch alarm, it is possible to effectively judge the status of the safety helmet. When T1 is greater than T2, it is determined that the safety helmet is damaged, which can avoid abnormal positioning and alarm caused by the damage of the safety helmet, ensure that the staff is always under safety protection and effective monitoring during the operation, and guarantee the safety of personnel.

[0107] Specifically, the accuracy control module calculates the uniformity f(X) of the alarm area with abnormal alarm accuracy according to the total number of base stations m in the alarm area with abnormal alarm accuracy, the two-dimensional vector X of the total number of base stations X = (x1, y1, x2, y2,..., xm, ym), the signal strength Si of the i-th sampling point, and the average signal strength of the alarm area with abnormal alarm accuracy where i = 1, 2,..., m, m is a positive integer, and it is set that Compare the uniformity f(X) of the alarm area with abnormal alarm accuracy with the preset uniformity f(X0), where f(X0)≥0.85 is set, and judge the uniformity of the alarm area with abnormal alarm accuracy according to the comparison result, where:

[0108] When f(X) < f(X0), the precision control module determines that the uniformity of the alarm area with abnormal alarm accuracy is qualified;

[0109] When f(X)≥f(X0), the precision control module determines that the uniformity of the alarm area with abnormal alarm accuracy is unqualified.

[0110] Specifically, the two-dimensional vector of the total number of base stations is a mathematical expression used to describe the distribution of base stations in the alarm area, including the two-dimensional coordinates of each base station, that is, the X-axis coordinate and the Y-axis coordinate. The average signal strength of the alarm area with abnormal alarm accuracy refers to the average value obtained by statistically calculating the signal strengths collected at each sampling point in the alarm area with abnormal alarm accuracy. The uniformity of the alarm area with abnormal alarm accuracy refers to the average number of UWB base stations per unit alarm area in the alarm area with abnormal alarm accuracy. The unit alarm area refers to the alarm area with abnormal alarm accuracy that divides the area into several unit alarm areas with the same area. The preset uniformity is a preset standard value used as a reference for judging whether the uniformity of the alarm area with abnormal alarm accuracy is qualified, such as setting f(X0)=0.85.

[0111] Specifically, by calculating the uniformity of the alarm area with abnormal alarm accuracy and comparing it with the preset uniformity, the signal distribution situation of the alarm area can be effectively evaluated. When the uniformity is less than the preset value and is determined to be qualified, it means that the base station signal distribution in this area is relatively uniform, and the UWB alarm can be triggered more accurately, reducing false alarms and missed alarms, greatly improving the accuracy and reliability of the alarm, and ensuring the safety of personnel and equipment. For areas with unqualified uniformity, that is, when the uniformity is greater than or equal to the preset value, the problem of uneven signal distribution can be discovered in time, which helps technicians to optimize the base station layout or adjust the signal parameters targeted, reasonably allocate resources, and avoid the alarm failure or over-alarm in some areas due to uneven signal coverage, thereby improving the performance and efficiency of the entire UWB alarm system and reducing the maintenance cost.

[0112] Specifically, when the uniformity state of the alarm area with abnormal alarm accuracy is inappropriate, the precision control module calculates the adjustment value Δx of the X-axis coordinate of the base station according to the first base station X j (x j , y j ) and the second base station X j+1 (x j+1 , y j+1 ) jand the Y-axis coordinate adjustment value Δy of the base station j , j = 1, 2, ..., m, where the first base station and the second base station are adjacent base stations, and it is set that Adjust the two-dimensional vector of the base station to obtain the two-dimensional vector X2 of the adjusted base station = (x21 + Δx1, y21 + Δy1, x22 + Δx2, y22 + Δy2, …, x2 m + Δx m , y m + Δy m ). According to the total number m of base stations in the alarm area with abnormal alarm accuracy, the two-dimensional vector X2 of the adjusted base station = (x21 + Δx1, y21 + Δy1, x22 + Δx2, y22 + Δy2, …, x2 m + Δx m , y m + Δy m ), the signal strength S of the adjusted j-th sampling point j and the average signal strength of the alarm area with abnormal alarm accuracy after adjustment Calculate the uniformity f(X') of the alarm area with abnormal alarm accuracy after adjustment, and set Calculate the uniformity difference Δf according to the uniformity f(X') of the alarm area with abnormal alarm accuracy after adjustment and the uniformity f(X) of the alarm area with abnormal alarm accuracy. Set Δf = f(X') - f(X). Also, judge the qualification of the uniformity of the alarm area with abnormal alarm accuracy after adjustment according to the calculation result, and optimize the UWB alarm process according to the judgment result, where:

[0113] When Δf < 0, the precision control module determines that the qualification of the uniformity of the alarm area with abnormal alarm accuracy after adjustment is qualified, and optimizes the UWB alarm process. Replace the two-dimensional vector coordinates of the total number of base stations with the coordinates of the two-dimensional vector of the adjusted base station, and use the adjustment result as the UWB alarm optimization result;

[0114] When Δf ≥ 0, the precision control module determines that the qualification of the uniformity of the alarm area with abnormal alarm accuracy after adjustment is unqualified, and continues to adjust the coordinates of the two-dimensional vector of the adjusted base station until Δf > 0.

[0115] Specifically, when the uniformity state of the warning area with abnormal warning accuracy is inappropriate, the adjustment values of the X-axis and Y-axis coordinates of the base station are calculated by calculating the coordinates of adjacent base stations, and the two-dimensional vector of the base station is adjusted. After the adjustment, the uniformity is recalculated, and the priority is judged according to the uniformity difference, which can effectively evaluate the effectiveness of the adjustment strategy. When the uniformity difference is less than 0, it is determined that the uniformity after adjustment is superior, and the two-dimensional vector coordinates of the adjusted base station are used to optimize the UWB warning process, which can quickly improve the signal uniformity of the warning area, thereby improving the accuracy of the warning, reducing false alarms and missed alarms, and ensuring the safety of personnel and equipment; when the uniformity difference is greater than or equal to 0, the two-dimensional vector coordinates of the adjusted base station are continuously adjusted until the priority condition is met. This dynamic adjustment mechanism ensures the effectiveness and adaptability of the optimization scheme, can fully explore the potential of base station layout adjustment, improve resource utilization efficiency, continuously improve the performance of the UWB warning system, reduce maintenance costs, and enhance the stability and reliability of the entire system.

[0116] Specifically, when the precision control module supplements the UWB warning optimization result, it calculates the average signal strength of the warning area with abnormal warning precision and compares it with the preset average signal strength to make a judgment on the multipath area according to the comparison result, and supplements the UWB warning optimization result according to the judgment result, where: When

[0117] When the precision control module determines that the warning area with abnormal warning precision is not a multipath area and does not supplement the UWB warning optimization result;

[0118] When the precision control module determines that the warning area with abnormal warning precision is a multipath area and supplements the UWB warning optimization result, and sets a supplementary coefficient to supplement the uniformity difference Δf according to the supplementary coefficient W, and the preset uniformity difference after supplementation is Δf W , set Δf W = f(X') - f(X) × W to obtain the supplemented UWB warning optimization result.

[0119] Specifically, the preset average signal strength is a reference value set in advance, which is used as a benchmark for judging whether the signal strength of the warning area with abnormal warning precision meets the standard. For example, set The supplemented preset uniformity difference refers to the value obtained by supplementing and calculating the uniformity difference through setting a supplement coefficient when the average signal strength is less than the preset value. The supplemented UWB alarm optimization result refers to the overall optimized alarm system state finally obtained by supplementing the uniformity difference through the supplement coefficient when the average signal strength does not meet the standard on the basis of the UWB alarm optimization result.

[0120] Specifically, by comparing the average signal strength of the alarm area with abnormal alarm accuracy with the preset average signal strength, it is possible to accurately identify whether the signal strength meets the standard. When the average signal strength is greater than or equal to the preset value, no supplement is performed, avoiding unnecessary operations and ensuring the efficient operation of the system.

[0121] Specifically, when the accuracy control module adjusts the supplemented UWB alarm optimization result, it divides the accident dataset of the alarm area into a training set, a validation set, and a test set, selects a recurrent neural network model as the neural network architecture of the alarm area evaluation model, selects an Adam optimizer and a cross-entropy loss function to train the recurrent neural network model, loads the training set into the recurrent neural network model, performs forward propagation through the recurrent neural network model, calculates the output value of the model, calculates the loss function value according to the output value and the true value of the recurrent neural network model, calculates the gradient through the backpropagation algorithm, and updates the weights and biases of the recurrent neural network model. Repeat the processes of forward propagation, loss calculation, and backpropagation until the preset number of training rounds is reached. Verify the performance of the recurrent neural network model on the validation set, output the recurrent neural network model that meets the performance as the alarm area evaluation model, and input the accidents of the alarm area with abnormal alarm accuracy collected in real time into the alarm area evaluation model to output the evaluation result of the alarm area with abnormal alarm accuracy. The evaluation result includes a key area and a general alarm area;

[0122] When the alarm area output by the alarm area evaluation model with abnormal alarm accuracy is a key area, according to the weight coefficient where C1 is the area of the key area and Cz is the total area of the alarm area, calculate the adjusted preset uniformity f(X0'), set f(X0') = (1 + α) × f(X0), and re-optimize the UWB alarm process for this key area to obtain the adjusted UWB alarm optimization result;

[0123] When the alarm area output by the alarm area evaluation model with abnormal alarm accuracy is a general alarm area, the preset uniformity f(X0) is not adjusted.

[0124] Specifically, the key area refers to the area with the highest accident incidence rate or the highest degree of importance in the warning area, and the general warning area refers to the area in the warning area except the key area. In this embodiment, the settings of parameters such as the number of layers of the recurrent neural network, the number of neurons in each layer, and the activation function are not limited, and those skilled in the art can freely set them according to actual needs, as long as the accuracy requirements of the model output are met. The preset number of training rounds refers to the preset value of the number of rounds when training the model, such as 10 rounds. Meeting the performance means that the accuracy rate of the output value of the recurrent neural network model reaches the preset accuracy rate, such as set to reach 95%.

[0125] Specifically, by means of machine learning, the accident data set in the warning area is divided and trained using a recurrent neural network model to mine data patterns, accurately distinguish key and general warning areas, adopt differential strategies for different areas, not only improve the resource utilization efficiency, but also ensure the accuracy and reliability of key area warnings, and can also be adjusted according to real-time accident dynamics to improve the system performance and stability, and build a solid defense line for the safety of personnel and equipment.

[0126] Specifically, when the precision control module optimizes the key area, it calculates the total number of base stations m3 in the new key area according to the area C1 of the key area, the area C2 of the reserved area, and the signal strength coverage area C3 of a single base station, and sets According to the total number of base stations m3 in the new key area, the two-dimensional vector X3=(x31,y31,x32,y32,…,x3 m ,y3 m ) of the total number of base stations in the new key area, the signal strength Si” of the i”th sampling point in the new key area, and the average signal strength of the new key area calculate the uniformity f(X)3 of the new key area, i” = 1, 2,... m3, m3 is a positive integer, and set Compare the uniformity f(X)3 of the new key area with the adjusted preset uniformity f(X0'), judge the compliance situation of the uniformity of the new key area according to the comparison result, and adjust the total number of base stations in the new key area according to the judgment result, where:

[0127] When f(X)3 ≤ f(X0'), the precision control module determines that the compliance situation of the uniformity of the new key area is not compliant, and adjusts the total number of base stations in the new key area. The adjustment method is to gradually increase the total number of base stations in the new key area at an increasing frequency with an increment of 1 until f(X)3 > f(X0');

[0128] When f(X)3 > f(X0'), the precision control module determines that the compliance situation of the uniformity of the new key area is compliant and does not adjust the total number of base stations in the new key area.

[0129] Specifically, the reserved area refers to an important construction area reserved in the engineering plan because the engineering progress has not reached this area. The total number of base stations in the new key area refers to the total number of base stations in the new key area formed after the combination of the key area and the reserved area. The uniformity of the new key area refers to the uniformity of the new key area formed after the combination of the key area and the reserved area.

[0130] Specifically, by using the area of the key area, the area of the reserved area, and the coverage area of the signal strength of a single base station model, the total number of base stations in the new key area is accurately calculated, avoiding the problems of resource waste caused by too many base stations and insufficient signal coverage caused by too few base stations, and realizing the rational utilization of resources.

[0131] Specifically, when the accuracy optimization module judges the high-frequency alarm points, it compares the number of UWB alarm accuracy anomalies B with the preset number of UWB alarm accuracy anomalies B0, sets B0≥5 times, and judges the alarm point situation in the alarm area according to the comparison result, and adjusts the UWB alarm optimization result according to the judgment result, where:

[0132] When B>B0, the accuracy optimization module determines that the alarm point situation in the alarm area is a high-frequency alarm point, and sets the adjustment coefficient V = e B-B0 -1, where e is the base of the natural logarithm function. According to the adjustment coefficient, the preset uniformity f(X0) of the alarm area where the high-frequency alarm point is located is adjusted to obtain the preset uniformity of the high-frequency alarm area. The adjusted preset uniformity of the high-frequency alarm area is f(X0) B , set f(X0) B =f(X0)×E;

[0133] When B≤B0, the accuracy optimization module determines that the alarm point situation in the alarm area is a normal alarm point.

[0134] Specifically, the high-frequency alarm point refers to the number of UWB alarm accuracy anomalies at a certain coordinate point being higher than the preset number of UWB alarm accuracy anomalies. The number of UWB alarm accuracy anomalies refers to the number of times the alarm accuracy of UWB alarm at a certain point is abnormal. The preset number of UWB alarm accuracy anomalies is a judgment index for judging whether the alarm area is a high-frequency alarm point, such as setting B0 = 5 times.

[0135] Specifically, by comparing the number of UWB alarm accuracy anomalies B with the preset number of UWB alarm accuracy anomalies B0, high-frequency alarm points can be accurately identified.

[0136] Specifically, when the alarm point situation in the alarm area of the accuracy optimization module is a high-frequency alarm point, the fault data set is divided into a training set, a validation set, and a test set. A convolutional neural network model is selected as the neural network architecture of the fault cause analysis model. The Adam optimizer and the cross-entropy loss function are selected to train the convolutional neural network model. The training set is loaded into the convolutional neural network model, and forward propagation is performed through the convolutional neural network model to calculate the output value of the convolutional neural network model. The loss function value is calculated based on the output value and the true value of the recurrent neural network model. The gradient is calculated through the backpropagation algorithm, and the weights and biases of the convolutional neural network model are updated. The processes of forward propagation, loss calculation, and backpropagation are repeated until the preset number of training rounds is reached. The performance of the convolutional neural network model is verified on the validation set. The convolutional neural network model that meets the performance is output as the fault cause analysis model, and the fault data collected in real time is input into the fault cause analysis model to output the fault cause analysis result of the fault data. The fault cause analysis result includes a general cause and a signal transmission cause, where:

[0137] When the fault cause analysis result of the fault data output by the fault cause analysis model is a general cause, the target tag and the UWB base station are inspected and repaired;

[0138] When the fault cause analysis result of the fault data output by the fault cause analysis model is a signal transmission cause, the high-frequency alarm points are removed from the alarm area, and the site model is optimized according to the signal transmission method. The optimization method is to change the signal transmission method of the UWB. The signal transmission methods include simultaneous transmission and intermittent transmission.

[0139] Specifically, the general cause refers to other causes except the signal transmission method cause, such as the failure of the UWB base station to receive signals and the damage of the target tag. The signal transmission method refers to the method by which the UWB base station sends wireless signals to the surrounding space. The simultaneous transmission means that the UWB base station sends signals to multiple directions or multiple targets at the same time point. The intermittent transmission means that the UWB base station sends signals periodically at a certain time interval. It can be understood that in this embodiment, the settings of parameters such as the number of layers of the convolutional neural network, the number of neurons in each layer, and the activation function are not limited. Those skilled in the art can freely set them according to actual needs as long as the accuracy requirements of the model output are met. The preset number of training rounds refers to the preset value of the number of rounds for training the model, such as 10 rounds. Meeting the performance means that the accuracy rate of the output value of the recurrent neural network model reaches the preset accuracy rate, such as being set to reach 95%.

[0140] Specifically, when the cause of the fault is determined to be a general cause through the fault cause analysis model, targeted inspection and maintenance of the target tag and the UWB base station can quickly solve problems at the equipment level, ensure the normal operation of the equipment, and avoid continuous alarms and potential safety hazards caused by equipment failures. When it is determined that the cause is signal transmission, high-frequency alarm points are eliminated and the site model is optimized. By changing the UWB signal transmission method, such as from simultaneous transmission to intermittent transmission, or vice versa, the signal transmission effect can be effectively improved, high-frequency alarms caused by signal problems can be reduced, and the overall stability and reliability of the system can be enhanced.

[0141] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle 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 fall within the protection scope of the present invention.

Claims

1. A smart helmet for high-precision positioning, characterized in that: include: The helmet body is the main part of the helmet and is used to protect the worker's head. The target tag is installed on the front edge of the helmet body and is used to receive and feedback the UWB signal transmitted by the UWB base station; The altitude measuring instrument is installed at the tail of the helmet body and is used to measure the real-time altitude of the smart helmet; The reserve battery is installed under the altitude measuring instrument and is used to power various components of the smart helmet; A control system for a smart helmet for high-precision positioning is connected to the helmet body and is used to provide safety warnings for the smart helmet.

2. A system for a smart helmet for high-precision positioning as claimed in claim 1, characterized in that: include: Data acquisition module, used to collect UWB signal data, Z-axis coordinates of the helmet and infrared change data; The site modeling module is used to model the construction site according to the UWB signal data, obtain the site model, and divide the site model into warning areas and non-warning areas according to the site planning; A positioning solution module is used to calculate the position of the helmet in the site model according to the UWB base station receiving time in the UWB signal data to obtain the location of the helmet site model; Intelligent two-way alarm module, used for UWB alarm based on helmet site model positioning, and also for touch alarm based on infrared change data set; The accuracy monitoring module is used to judge the alarm accuracy of the UWB alarm according to the first alarm result of the UWB alarm and the second alarm result of the touch alarm, and obtain the alarm area with abnormal alarm accuracy; An accuracy control module, used to optimize the UWB alarm process according to the alarm area with abnormal alarm accuracy to obtain a UWB alarm optimization result, and also used to supplement the UWB alarm optimization result according to the multipath area in the alarm area to obtain a supplemented UWB alarm optimization result, and also used to adjust the supplemented UWB alarm optimization result according to the key area in the alarm area to obtain an adjusted UWB alarm optimization result, and also used to optimize the key area according to the reserved area; The accuracy optimization module is used to judge the high-frequency alarm points according to the number of abnormal UWB alarm accuracy, and adjust the UWB alarm optimization results according to the high-frequency alarm points. It is also used to analyze the causes of failures of the high-frequency alarm points, and eliminate and optimize the judgment process of the high-frequency alarm points according to the causes of failures of the high-frequency alarm points, and optimize the site model.

3. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: The positioning solution module calculates the distance d1 between the target tag and base station A according to the time t1 of the target tag reflecting the signal to base station A and the UWB signal propagation speed Vc, and sets d1=t1×Vc. The distance d2 between the target tag and base station B is calculated according to the time t2 of the target tag reflecting the signal to base station B and the UWB signal propagation speed Vc, and sets d2=t2×Vc, where Vc=3×10 8 m / s, and solve the coordinates (x, y) of the target tag M according to the coordinates (x1, y1) of base station A, the coordinates (x2, y2) of base station B, the distance d1 from the target tag M to base station A, and the distance d2 from the target tag M to base station B, and set 4. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: When the intelligent two-way alarm module performs UWB alarm according to the helmet site model positioning, the Z-axis coordinate z of the target tag is compared with the maximum Z-axis coordinate z0 of the alarm area and the minimum Z-axis coordinate z1 of the alarm area, and the Z-axis coincidence state of the target tag and the alarm area is determined according to the comparison result, wherein: When z>z0, the intelligent two-way alarm module determines that the Z-axis coincidence state between the target tag and the alarm area is a non-coincidence state; When z<z1, the intelligent two-way alarm module determines that the Z-axis coincidence state between the target tag and the alarm area is a non-coincidence state; When z1≤z≤z0, the intelligent bidirectional alarm module determines that the Z-axis coincidence state of the target tag and the alarm area is an overlap state.

5. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: The intelligent two-way alarm module compares the alarm distance L with the preset alarm distance L0, and determines the overlap state of the target tag and the alarm area according to the comparison result, and performs a UWB alarm according to the judgment result, wherein: When L≤L0, the intelligent two-way alarm module determines that the target tag coincides with the alarm area, and performs a UWB alarm, taking the radiation range of the current coordinates of the target tag as the first alarm result of the UWB alarm; When L>L0, the intelligent two-way alarm module determines that the target tag does not overlap with the alarm area and does not issue a UWB alarm; When the intelligent two-way alarm module performs a touch alarm, the touch distance D between the user and the alarm area is compared with the preset touch distance D0, and a touch alarm is performed according to the comparison result, wherein: When D>D0, no touch alarm is given; When D≤D0, a touch alarm is performed, the infrared touch trap issues a warning and records it, and the radiation range of the current coordinates of the infrared touch trap is used as the second alarm result of the touch alarm.

6. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: The accuracy monitoring module compares the alarm number T1 of the first alarm result of the UWB alarm with the alarm number T2 of the second alarm result of the touch alarm, and determines the alarm accuracy of the UWB alarm according to the comparison result, wherein: When T1=T2, the accuracy monitoring module determines that the alarm accuracy of the UWB alarm is normal; When T1>T2, the accuracy monitoring module determines that the alarm accuracy of the UWB alarm is abnormal, and selects the intersection of the radiation range corresponding to the first alarm result of the UWB alarm and the radiation range corresponding to the second alarm result of the touch alarm as the alarm area of ​​abnormal alarm accuracy; When T1<T2, the accuracy monitoring module determines that the alarm accuracy of the UWB alarm is abnormal, and selects the intersection of the radiation range corresponding to the first alarm result of the UWB alarm and the radiation range corresponding to the second alarm result of the touch alarm as the alarm area of ​​abnormal alarm accuracy.

7. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: The accuracy control module compares the uniformity f(X) of the alarm area with abnormal alarm accuracy with the preset uniformity f(X0), sets f(X0)≥0.85, and judges the uniformity of the alarm area with abnormal alarm accuracy according to the comparison result, wherein: When f(X)<f(X0), the accuracy control module determines that the uniformity of the alarm area with abnormal alarm accuracy is qualified; When f(X)≥f(X0), the accuracy control module determines that the uniformity of the alarm area with abnormal alarm accuracy is unqualified; When the uniformity state of the alarm area with abnormal alarm accuracy is inappropriate, the accuracy control module adjusts the two-dimensional vector of the base station to obtain the adjusted two-dimensional vector of the base station X2=(x21+Δx1,y21+Δy1,x22+Δx2,y22+Δy2,…,x2 m +Δx m ,y m +Δy m ), calculate the uniformity difference Δf according to the uniformity f(X') of the alarm area with abnormal alarm accuracy after adjustment and the uniformity f(X) of the alarm area with abnormal alarm accuracy, set Δf=f(X')-f(X), and judge the uniformity of the alarm area with abnormal alarm accuracy after adjustment according to the calculation result, and optimize the UWB alarm process according to the judgment result, wherein: When Δf<0, the precision control module determines that the uniformity of the alarm area with abnormal alarm precision after adjustment is qualified, and optimizes the UWB alarm process, replaces the two-dimensional vector coordinates of the total number of base stations with the coordinates of the two-dimensional vector of the adjusted base station, and uses the adjustment result as the UWB alarm optimization result; When Δf≥0, the precision control module determines that the uniformity of the alarm area with abnormal alarm precision after adjustment is unqualified, and continues to adjust the coordinates of the two-dimensional vector of the adjusted base station until Δf>0; When the precision control module supplements the UWB alarm optimization result, the average signal strength of the alarm area with abnormal alarm precision is calculated. The average signal strength of the preset Compare and set The multipath area is judged according to the comparison results, and the UWB alarm optimization results are supplemented according to the judgment results, including: when When the accuracy control module determines that the alarm area with abnormal alarm accuracy is not a multipath area, the UWB alarm optimization result is not supplemented; when When the alarm accuracy is abnormal, the accuracy control module determines that the alarm area with abnormal alarm accuracy is a multipath area, and supplements the UWB alarm optimization result and sets the supplement coefficient The uniformity difference Δf is supplemented according to the supplement coefficient W, and the preset uniformity difference after supplementation is Δf W , set Δf W =f(X')-f(X)×W, and the supplemented UWB alarm optimization result is obtained.

8. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: The accuracy control module outputs the recurrent neural network model that meets the performance as the alarm area evaluation model, and inputs the alarm area accidents with abnormal alarm accuracy collected in real time into the alarm area evaluation model, and outputs the evaluation results of the alarm area with abnormal alarm accuracy; When the alarm area evaluation model outputs an abnormal alarm accuracy alarm area as a critical area, according to the weight coefficient Where C1 is the area of ​​the key area, Cz is the total area of ​​the alarm area, the adjusted preset uniformity f(X0') is calculated, f(X0') is set to (1+α)×f(X0), and the UWB alarm process of the key area is re-optimized to obtain the adjusted UWB alarm optimization result; When the alarm area assessment model outputs an abnormal alarm accuracy alarm area as a normal alarm area, the preset uniformity f(X0) is not adjusted.

9. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: The precision control module compares the uniformity of the new key area f(X)3 with the adjusted preset uniformity f(X0'), judges whether the uniformity of the new key area meets the standard according to the comparison result, and adjusts the total number of base stations in the new key area according to the judgment result, wherein: When f(X)3≤f(X0'), the precision control module determines that the uniformity of the new key area is not up to standard, and adjusts the total number of base stations in the new key area by gradually increasing the total number of base stations in the new key area with an increase frequency of 1 until f(X)3>f(X0'); When f(X)3>f(X0'), the accuracy control module determines that the uniformity of the new key area meets the standard, and does not adjust the total number of base stations in the new key area.

10. The system for high-precision positioning of a smart helmet according to claim 2, characterized in that: When judging the high-frequency alarm point, the accuracy optimization module compares the UWB alarm accuracy abnormality times B with the preset UWB alarm accuracy abnormality times B0, sets B0≥5 times, and judges the alarm point situation of the alarm area according to the comparison result, and adjusts the UWB alarm optimization result according to the judgment result, wherein: When B>B0, the accuracy optimization module determines that the alarm point in the alarm area is a high-frequency alarm point, and sets the adjustment coefficient V=e B-B0 -1, e is the base of the natural logarithm function, and the preset uniformity f(X0) of the alarm area to which the high-frequency alarm point belongs is adjusted according to the adjustment coefficient to obtain the preset uniformity of the high-frequency alarm area. The adjusted preset uniformity of the high-frequency alarm area is f(X0) B , set f(X0) B =f(X0)×E; When B≤B0, the accuracy optimization module determines that the alarm point situation of the alarm area is a normal alarm point; When the alarm point situation in the alarm area is a high-frequency alarm point, the accuracy optimization module inputs the real-time collected fault data into the fault cause analysis model, and outputs the fault cause analysis result of the fault data, wherein the fault cause analysis result includes general causes and signal sending causes, wherein: When the fault cause analysis result of the fault data output by the fault cause analysis model is a general cause, inspecting and repairing the target tag and the UWB base station; When the fault cause analysis result of the fault data output by the fault cause analysis model is a signal sending reason, the high-frequency alarm points are removed from the alarm area, and the site model is optimized according to the signal sending method. The optimization method is to change the UWB signal sending method, and the signal sending method includes simultaneous sending and intermittent sending.

Images