A device anomaly detection system and method based on precise positioning technology

Abstract

The present invention discloses a device anomaly detection system and method based on precise positioning technology, which belongs to the field of data monitoring technology. The present invention includes a multi-segment data acquisition module, a data visualization module, a data fusion analysis module and a device anomaly feedback module; the multi-segment data acquisition module is used to collect the operation data of the unmanned vehicle and transmit the data to a remote terminal; the data visualization module is used to pre-process the collected data and perform digital-to-graphic conversion on the processed data to achieve visualization; the data fusion analysis module realizes anomaly detection and decision-making for the current operation status of the unmanned vehicle through comprehensive analysis of the visualized data; the device anomaly feedback module is used to feedback the abnormal situation of the real-time data of the unmanned vehicle and alarm for the abnormal data; the present invention aims to realize accurate judgment and safe driving of the unmanned vehicle in complex road conditions by fusion analysis of the operation data and environmental data of the unmanned vehicle.

Description

Technical Field

[0001] The present invention relates to the field of data monitoring technology, and in particular to a device anomaly detection system and method based on precise positioning technology. Background Art

[0002] Precision positioning technology is a technology that uses satellite navigation systems or other sensor technologies to determine the exact location of an object in space. Precision positioning technology is a vital part of the equipment abnormality monitoring system, and it can achieve high-precision acquisition of equipment location through means such as the global satellite positioning system.

[0003] With the advancement of the Internet and technology, the process of social intelligence is also developing steadily. The emergence of unmanned vehicles represents the intelligent process of road transportation; however, there are still many unstable effects on unmanned vehicles on the road. Among them, when an unmanned vehicle encounters an emergency intersection while driving, it often issues a warning and brakes, then slowly drives out of the intersection after the situation stabilizes. This method is relatively rigid in complex road conditions and will affect the normal driving of other traffic for a long time; the traditional solution is to set up a dedicated lane for unmanned vehicles or to reduce the probability of accidents by slowing down the speed of unmanned vehicles, but the problems of this solution cannot be ignored. The first method can provide a good environment for unmanned vehicles in the short term, but this model is contrary to the original intention of the intelligent development of unmanned vehicles, and the promotion cost of this method is also high, which is not in line with intelligence; secondly, by slowing down the speed, it can both play the role of unmanned vehicles and reduce the probability of accidents to a certain extent, but this method will cause unnecessary traffic congestion in complex road conditions, making road congestion more serious. Summary of the invention

[0004] The purpose of the present invention is to provide a device anomaly detection system and method based on precise positioning technology to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An equipment anomaly detection system based on precise positioning technology, the equipment anomaly monitoring system based on precise positioning technology comprises a multi-segment data acquisition module, a data visualization module, a data fusion analysis module, and an equipment anomaly feedback module;

[0007] The multi-segment data acquisition module is used to collect the operating data of the unmanned vehicle and transmit the data to the remote terminal through the transmission medium; the data visualization module is used to clean and fuse the collected data, and convert the processed data into a graphic form to realize data interaction; the data fusion analysis module conducts an abnormal analysis and decision-making on the current operating status and data of the unmanned vehicle by conducting a comprehensive analysis of the visualized data chart and the processed data; the equipment abnormality feedback module is used to feedback the abnormal situation of the real-time data of the unmanned vehicle and issue an alarm for the abnormal data;

[0008] The multi-segment data acquisition module is connected to the data visualization module; the data visualization module is connected to the data fusion analysis module; the data fusion analysis module is connected to the equipment abnormality feedback module.

[0009] The multi-segment data acquisition module includes a front-end device data acquisition unit, a data transmission unit and a back-end central control unit; the front-end device data acquisition unit includes a multi-sensor device; the multi-sensor device includes a laser radar, a camera, a millimeter-wave radar, a GPS positioning sensor and an inertial measurement sensor; the laser radar is used to collect environmental distance and shape data during the driving process of the unmanned vehicle; the camera is used to identify traffic signs, vehicles and personnel during the driving process of the unmanned vehicle, and monitor the road conditions and perceive the environment; the millimeter-wave radar is used to measure the motion state data of surrounding vehicles during the driving process of the unmanned vehicle; the GPS positioning sensor is used to obtain real-time position data of the unmanned vehicle; the inertial measurement sensor is used to measure the acceleration and angular velocity data of the vehicle in real time; the data transmission unit uses the 5G signal transmitting and receiving device of the device to transmit the driving data of the unmanned vehicle to the back-end central control unit; the back-end central control unit is used to receive the unmanned vehicle operation data and environmental data collected and transmitted by the front-end acquisition device, and analyze and process the data.

[0010] The data visualization module includes a data fusion unit, a number-shape conversion unit and a data interaction unit; the data fusion unit is used to perform data cleaning, conversion, feature extraction and data missing filling processing on the collected data, and associate and fuse the processed data; the number-shape conversion unit performs model conversion on the processed fused data, and converts the data into visual graphics and tables; the data interaction unit is used to display the processed data and the converted numbers and shapes on the management end through an interface, and provides interactive options for administrators to read and analyze the data independently.

[0011] The data fusion analysis module includes a real-time environment simulation unit, a road condition prediction and analysis unit and a dynamic decision-making unit; the real-time environment simulation unit connects the actual operation data of the unmanned vehicle and the environmental data in series by processing the data and converting them into visible numbers to simulate the actual operation of the unmanned vehicle; the road condition prediction and analysis unit combines the environmental data simulation to perform a fusion prediction on the road conditions within the monitoring range of the unmanned vehicle, and uses the actual road condition data as the benchmark data to predict the changes in road conditions within the monitoring area of ​​the unmanned vehicle; wherein the road conditions include changes in the environment, vehicles, personnel and traffic signs; the dynamic decision-making unit makes decisions, controls and adjusts the current driving status data of the unmanned vehicle based on the road condition prediction results and the changes and changes in the predicted road condition data.

[0012] The equipment abnormality feedback module includes an equipment status data feedback unit and an equipment abnormality data alarm unit; the equipment status data feedback unit comprehensively feedbacks the analysis results of the unmanned vehicle's driving status data to provide the administrator with real-time feedback on the driving status of the unmanned vehicle; the equipment abnormality data alarm unit is used to alarm for abnormal situations in the driving data and environmental data collected during the driving process of the unmanned vehicle and the subsequent data processing and analysis process, so as to prompt the unmanned vehicle that there is an abnormal situation.

[0013] A device anomaly detection method based on precise positioning technology, the method comprising the following steps:

[0014] S100, first, the driving data of the unmanned vehicle is collected by multiple sensors installed on the unmanned vehicle and transmitted to the back-end control end;

[0015] S200, the control end receives the data and pre-processes the data, and then visualizes the data through a digital-to-graphic conversion method after preliminary processing;

[0016] S300, the management end conducts a comprehensive analysis of the visualized data table and processed data to determine whether the unmanned vehicle is in an abnormal state and formulate a corresponding decision plan;

[0017] S400. The management end reports and feedbacks the driving status of the unmanned vehicle in real time based on the analysis results, and issues alarm prompts for abnormal data.

[0018] The specific steps of collecting the driving data of the unmanned vehicle through the multi-sensors installed on the unmanned vehicle and transmitting it to the back-end control end in S100 are as follows:

[0019] S101. During the driving process of the unmanned vehicle, the driving data, environmental data and road condition data of the unmanned vehicle are collected in real time through a multi-sensor device of the unmanned vehicle itself; wherein the multi-sensor includes a laser radar, a camera, a millimeter-wave radar, a GPS positioning sensor and an inertial measurement sensor;

[0020] S102: The collected driving data, environmental data and road condition data of the unmanned vehicle are converted into data signals by using the 5G signal transmitting and receiving device of the vehicle body device and transmitted to the management end, and the command data transmitted by the management end is received.

[0021] In S200, the control end receives data and pre-processes the data, and the specific steps of visualizing the data through digital-to-graphic conversion after preliminary processing are as follows:

[0022] S201, the management end receives the data transmitted by the unmanned vehicle end, performs data cleaning, data conversion, feature extraction and data association operations on the data, processes the original data in an orderly manner and performs data association; wherein the data association operations include time-speed data association, time-distance data association, and distance-speed data association;

[0023] S202. Use a two-dimensional chart and a coordinate system to convert the related data into digital form and visualize the data.

[0024] The specific steps of the management end in S300 to comprehensively analyze the visualized data table and processed data to determine whether the unmanned vehicle is in an abnormal state and formulate a corresponding decision plan are as follows:

[0025] S301, analyzing the braking force of the unmanned vehicle through the vehicle's driving speed, distance and power consumption data association diagram; the braking force of the unmanned vehicle is calculated by calculating the unmanned vehicle emergency braking coefficient The calculation formula is: ; Where P is the output power of the unmanned vehicle engine, m is the mass of the unmanned vehicle, v is the initial braking velocity of the unmanned vehicle, and g is the gravity acceleration; the braking coefficient of the unmanned vehicle is compared with the minimum braking coefficient threshold For comparison, if , the unmanned vehicle's braking data is abnormal; when the unmanned vehicle's own data is abnormal, the management end uses emergency instructions to make the unmanned vehicle safely drive off the road to avoid road accidents in subsequent driving;

[0026] S302, if , the unmanned vehicle's own braking performance is normal; when the unmanned vehicle reaches the intersection, the sensor detects that there are other vehicles and the unmanned vehicle in an emergency intersection, and collects the current time of the oncoming vehicle With the next moment The speed data of the other vehicle is used to predict the driving state of the other vehicle by calculating its acceleration change trend. The calculation formula is: ;like The other vehicle starts to slow down. When the other vehicle enters the intersection, the front corner of the other vehicle close to the unmanned vehicle is used as the base point, and the extension line of the current direction of this point is used as the reference direction line of the vehicle. By detecting the offset angle of the reference direction line of the other vehicle Determine whether the other vehicle has deviated from the direction; if , then the other vehicle has a direction deviation behavior, and the unmanned vehicle drives normally; if , the other vehicle is going straight, so the unmanned vehicle adjusts its speed when entering the intersection. within; among them, is the minimum speed for crossing the intersection, The speed of the other vehicle passing through the intersection; by detecting the angle deviation of the other vehicle at the intersection, predict whether it will turn, and formulate corresponding driving strategies according to different behaviors;

[0027] S303, if , if the other vehicle enters the intersection at an accelerated or constant speed, the unmanned vehicle will issue a warning, and extend the reference direction line based on the front corner of the other vehicle on the side close to the unmanned vehicle, and use the intersection of the two reference direction lines as the predicted collision point, and collect the collision distance between the collision point and the vehicle. and ;in, is the collision distance between the collision point and the unmanned vehicle, is the collision distance from the collision point to the other vehicle; when the unmanned vehicle issues a warning, repeat the acceleration calculation step in step S302 and determine whether the other vehicle has braking behavior; by calculating the acceleration of the other vehicle again, determine whether the other vehicle has discovered the existence of the cross-passing behavior; if there is braking behavior, calculate the emergency braking distance of the unmanned vehicle and the other vehicle according to the current vehicle's driving speed, and the calculation formula is Obtained by calculation and ;in, is the braking distance of the unmanned vehicle, is the braking distance of the other vehicle; the braking coefficient used to calculate the emergency braking distance of the other vehicle is The maximum braking distance of the other vehicle can be calculated by calculating the minimum threshold, and subsequent analysis based on this can reduce the possibility of collision hazards; the collision distance and braking distance corresponding to the vehicle are compared respectively. If and , the unmanned vehicle detects the speed and position of the other vehicle in real time and intelligently adjusts the speed to drive out of the intersection, and uploads the data as a first-level environmental data anomaly; when the braking distance of both parties is less than the collision distance, the potential collision risk of the two vehicles is very small, and the unmanned vehicle fine-tunes the speed according to the speed of the other vehicle to achieve safe passing; if and , then the unmanned vehicle and the other vehicle are mapped into a two-dimensional coordinate system. When the other vehicle stops, the horizontal line of the front of the vehicle is used as the crossing line, and the vertical distance r between the collision point and the crossing line is detected. The center point of the unmanned vehicle's stopping point is connected to the collision point to form a side z, and the length of the side z is , extending perpendicular to the z side from the collision point The distance forms the other side, and the unconnected endpoints of the two line segments are connected to form a collision adjustment triangle; where h is the width of the unmanned vehicle body; then the angle of the endpoint of the collision triangle where the unmanned vehicle is located is calculated The value of is calculated as ;in, When the unmanned vehicle brakes to the corresponding stop point, To compensate for the deflection angle, The driver of the unmanned vehicle drives out of the intersection at the speed specified in the figure, and uploads data as a secondary environmental data anomaly; if the braking distance of the other vehicle exceeds the collision point and the braking distance of the unmanned vehicle is less than the collision point, a coordinate system can be established by mapping, and the unmanned vehicle can be arranged in advance to calculate the safe offset angle of the unmanned vehicle before the collision point. This can enable the unmanned vehicle to safely exit the intersection as soon as possible regardless of whether the other vehicle has completed braking. At the same time, it also facilitates the other vehicle to exit the intersection in time, reducing the time and scope of traffic impact; the offset angle is limited to The reason is that when the angle reaches this value, the unmanned vehicle may easily deviate excessively and change its driving direction, making it difficult to correct the angle after deviation and exit the intersection. and , the unmanned vehicle brakes to the stop point. The speed is the driving speed, the direction does not deviate from the intersection, and the uploaded data is a secondary environmental data anomaly; since the braking coefficient of the other vehicle is calculated by the minimum threshold to calculate the braking distance, the braking distance is the actual maximum distance. If the braking distance of the other vehicle is less than the collision point distance at this time, it means that the other party can brake in time. Then the unmanned vehicle only needs to maintain the original direction and drive out of the intersection at a safe speed after completing the braking; if and , then The steering angle is used to change the direction for emergency avoidance, and the uploaded data is a level 3 environmental data abnormality; if there is no braking behavior, The steering angle is used to change direction for emergency avoidance, and the uploaded data is a level 3 environmental data anomaly; when the braking distances of both vehicles are greater than or equal to the collision point distance, it means that both vehicles cannot pass each other safely. At this time, by increasing the braking angle of the unmanned vehicle and changing its driving direction, emergency avoidance can be performed.

[0028] The specific steps of the management end in S400 reporting and feeding back the driving status of the unmanned vehicle in real time according to the analysis results and issuing an alarm for abnormal data are as follows:

[0029] S401, the management end processes and analyzes the unmanned vehicle driving data and environmental data through visualization, and displays the analysis results in the form of a report;

[0030] S402: The management terminal marks the abnormal data of the unmanned vehicle driving in the report as abnormal and issues a warning to the management personnel.

[0031] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention collects status data and environmental data of the entire driving process of the unmanned vehicle through the action of multiple modules, analyzes and makes decisions, and realizes remote monitoring of the operation of the unmanned vehicle; among them, the in-depth analysis of the emergency meeting scene of the unmanned vehicle in complex road conditions is realized through comprehensive visual analysis of multiple situations and multiple data, so as to realize the safe meeting of the unmanned vehicle in emergency meeting under different situations, predict the meeting trend through multi-directional judgment, and calculate the safe meeting offset angle, so as to achieve the minimum reaction time and the minimum impact range to solve the emergency meeting accident; the present invention is different from the traditional perspective of blindly driving slowly to reduce the probability of accidents, and comprehensively improves the analysis, judgment and problem-solving capabilities of the unmanned vehicle in encountering emergencies through multi-angle judgment, so as to realize the unmanned vehicle's more intelligent, safer and faster driving ability on conventional roads. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0033] Figure 1 It is a structural schematic diagram of a device anomaly detection system based on precise positioning technology of the present invention;

[0034] Figure 2 It is a schematic diagram of the steps of a device abnormality detection method based on precise positioning technology of the present invention; DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0037] An equipment anomaly detection system based on precise positioning technology, the equipment anomaly monitoring system based on precise positioning technology comprises a multi-segment data acquisition module, a data visualization module, a data fusion analysis module, and an equipment anomaly feedback module;

[0038] The multi-segment data acquisition module is used to collect the operating data of the unmanned vehicle and transmit the data to the remote terminal through the transmission medium; the data visualization module is used to clean and fuse the collected data, and convert the processed data into a graphic form to realize data interaction; the data fusion analysis module conducts an abnormal analysis and decision-making on the current operating status and data of the unmanned vehicle by conducting a comprehensive analysis of the visualized data chart and the processed data; the equipment abnormality feedback module is used to feedback the abnormal situation of the real-time data of the unmanned vehicle and issue an alarm for the abnormal data;

[0039] The multi-segment data acquisition module is connected to the data visualization module; the data visualization module is connected to the data fusion analysis module; the data fusion analysis module is connected to the equipment abnormality feedback module.

[0040] The multi-segment data acquisition module includes a front-end device data acquisition unit, a data transmission unit and a back-end central control unit; the front-end device data acquisition unit includes a multi-sensor device; wherein the multi-sensor device includes a lidar, a camera, a millimeter-wave radar, a GPS positioning sensor and an inertial measurement sensor; the data transmission unit utilizes the 5G signal transmitting and receiving device of the device to transmit the driving data of the unmanned vehicle to the back-end central control unit; the back-end central control unit is used to receive the unmanned vehicle operation data and environmental data collected and transmitted by the front-end acquisition device, and analyze and process the data.

[0041] The data visualization module includes a data fusion unit, a number-shape conversion unit and a data interaction unit; the data fusion unit is used to perform data cleaning, conversion, feature extraction and data missing filling processing on the collected data, and associate and fuse the processed data; the number-shape conversion unit performs model conversion on the processed fused data, and converts the data into visual graphics and tables; the data interaction unit is used to display the processed data and the converted numbers and shapes on the management end through an interface, and provides interactive options for administrators to read and analyze the data independently.

[0042] The data fusion analysis module includes a real-time environment simulation unit, a road condition prediction and analysis unit and a dynamic decision-making unit; the real-time environment simulation unit connects the actual operation data of the unmanned vehicle and the environmental data in series by processing the data and converting them into visible numbers to simulate the actual operation of the unmanned vehicle; the road condition prediction and analysis unit combines the environmental data simulation to perform a fusion prediction on the road conditions within the monitoring range of the unmanned vehicle, and uses the actual road condition data as the benchmark data to predict the changes in road conditions within the monitoring area of ​​the unmanned vehicle; wherein the road conditions include changes in the environment, vehicles, personnel and traffic signs; the dynamic decision-making unit makes decisions, controls and adjusts the current driving status data of the unmanned vehicle based on the road condition prediction results and the changes and changes in the predicted road condition data.

[0043] The equipment abnormality feedback module includes an equipment status data feedback unit and an equipment abnormality data alarm unit; the equipment status data feedback unit comprehensively feedbacks the analysis results of the unmanned vehicle's driving status data to provide the administrator with real-time feedback on the driving status of the unmanned vehicle; the equipment abnormality data alarm unit is used to alarm for abnormal situations in the driving data and environmental data collected during the driving process of the unmanned vehicle and the subsequent data processing and analysis process, so as to prompt the unmanned vehicle that there is an abnormal situation.

[0044] A device anomaly detection method based on precise positioning technology, the method comprising the following steps:

[0045] S100, first, the driving data of the unmanned vehicle is collected by multiple sensors installed on the unmanned vehicle and transmitted to the back-end control end;

[0046] S200, the control end receives the data and pre-processes the data, and then visualizes the data through a digital-to-graphic conversion method after preliminary processing;

[0047] S300, the management end conducts a comprehensive analysis of the visualized data table and processed data to determine whether the unmanned vehicle is in an abnormal state and formulate a corresponding decision plan;

[0048] S400. The management end reports and feedbacks the driving status of the unmanned vehicle in real time based on the analysis results, and issues alarm prompts for abnormal data.

[0049] The specific steps of collecting the driving data of the unmanned vehicle through the multi-sensors installed on the unmanned vehicle and transmitting it to the back-end control end in S100 are as follows:

[0050] S101. During the driving process of the unmanned vehicle, the driving data, environmental data and road condition data of the unmanned vehicle are collected in real time through a multi-sensor device of the unmanned vehicle itself; wherein the multi-sensor includes a laser radar, a camera, a millimeter-wave radar, a GPS positioning sensor and an inertial measurement sensor;

[0051] S102: The collected driving data, environmental data and road condition data of the unmanned vehicle are converted into data signals by using the 5G signal transmitting and receiving device of the vehicle body device and transmitted to the management end, and the command data transmitted by the management end is received.

[0052] In S200, the control end receives data and pre-processes the data, and the specific steps of visualizing the data through digital-to-graphic conversion after preliminary processing are as follows:

[0053] S201, the management end receives the data transmitted by the unmanned vehicle end, performs data cleaning, data conversion, feature extraction and data association operations on the data, processes the original data in an orderly manner and performs data association; wherein the data association operations include time-speed data association, time-distance data association, and distance-speed data association;

[0054] S202. Use a two-dimensional chart and a coordinate system to convert the related data into digital form and visualize the data.

[0055] The specific steps of the management end in S300 to comprehensively analyze the visualized data table and processed data to determine whether the unmanned vehicle is in an abnormal state and formulate a corresponding decision plan are as follows:

[0056] S301, analyzing the braking force of the unmanned vehicle through the vehicle's driving speed, distance and power consumption data association diagram; the braking force of the unmanned vehicle is calculated by calculating the unmanned vehicle emergency braking coefficient The calculation formula is: ; Where P is the output power of the unmanned vehicle engine, m is the mass of the unmanned vehicle, v is the initial braking velocity of the unmanned vehicle, and g is the gravity acceleration; the braking coefficient of the unmanned vehicle is compared with the minimum braking coefficient threshold For comparison, if , then the unmanned vehicle’s braking data is abnormal;

[0057] S302, if , the unmanned vehicle's own braking performance is normal; when the unmanned vehicle reaches the intersection, the sensor detects that there are other vehicles and the unmanned vehicle in an emergency intersection, and collects the current time of the oncoming vehicle With the next moment The speed data of the other vehicle is used to predict the driving state of the other vehicle by calculating its acceleration change trend. The calculation formula is: ;like , then the other vehicle starts to slow down. When the other vehicle enters the intersection, the front corner of the other vehicle close to the unmanned vehicle is used as the base point, and the extension line of the current direction of this point is used as the reference direction line of the vehicle. By detecting the offset angle of the reference direction line of the other vehicle Determine whether the other vehicle has deviated from the direction; if , then the other vehicle has a direction deviation behavior, and the unmanned vehicle drives normally; if , the other vehicle is going straight, so the unmanned vehicle adjusts its speed when entering the intersection. within; among them, is the minimum speed for crossing the intersection, The speed of the other vehicle passing through the intersection;

[0058] S303, if , if the other vehicle enters the intersection at an accelerated or constant speed, the unmanned vehicle will issue a warning, and extend the reference direction line based on the front corner of the other vehicle on the side close to the unmanned vehicle, and use the intersection of the two reference direction lines as the predicted collision point, and collect the collision distance between the collision point and the vehicle. and ;in, is the collision distance between the collision point and the unmanned vehicle, is the collision distance between the collision point and the other vehicle; when the unmanned vehicle issues a warning, repeat the acceleration calculation step in step S302 and determine whether the other vehicle has braking behavior; if there is braking behavior, the emergency braking distances of the unmanned vehicle and the other vehicle are calculated according to the current vehicle's driving speed, and the calculation formula is: Obtained by calculation and ;in, is the braking distance of the unmanned vehicle, is the braking distance of the other vehicle; the collision distance and braking distance corresponding to the vehicle are compared respectively. and The unmanned vehicle detects the speed and position of the other vehicle in real time, intelligently adjusts the speed to drive out of the intersection, and uploads the data as a first-level environmental data anomaly; if and , then the unmanned vehicle and the other vehicle are mapped into a two-dimensional coordinate system. When the other vehicle stops, the horizontal line of the front of the vehicle is used as the crossing line, and the vertical distance r between the collision point and the crossing line is detected. The center point of the unmanned vehicle's stopping point is connected to the collision point to form a side z, and the length of the side z is , extending perpendicular to the z side from the collision point The distance forms the other side, and the unconnected endpoints of the two line segments are connected to form a collision adjustment triangle; where h is the width of the unmanned vehicle body; then the angle of the endpoint of the collision triangle where the unmanned vehicle is located is calculated The value of is calculated as ;in, ; When the unmanned vehicle brakes to the corresponding stop point To compensate for the deflection angle, The driving speed is out of the intersection, and the uploaded data is abnormal for the secondary environmental data; if and , the unmanned vehicle brakes to the stop point. The driving speed is the same as the direction of the road, and the uploaded data is abnormal for the secondary environmental data; if and , then The steering angle is used to change the direction for emergency avoidance, and the uploaded data is a level 3 environmental data abnormality; if there is no braking behavior, The steering angle is changed to make emergency avoidance, and the uploaded data is level 3 environmental data abnormality.

[0059] The specific steps of the management end in S400 reporting and feeding back the driving status of the unmanned vehicle in real time according to the analysis results and issuing an alarm for abnormal data are as follows:

[0060] S401, the management end processes and analyzes the unmanned vehicle driving data and environmental data through visualization, and displays the analysis results in the form of a report;

[0061] S402: The management terminal marks the abnormal data of the unmanned vehicle driving in the report as abnormal and issues a warning to the management personnel.

[0062] In the example:

[0063] There is an unmanned vehicle connected to the back-end management center and transmitting data to each other through 5G signals. The unmanned vehicle is equipped with an equipment abnormality monitoring system based on precise positioning technology; the unmanned vehicle uses this system to inspect its own status data at regular intervals and points. At a certain moment, the engine output power of the unmanned vehicle is 25 kilowatts, the mass of the unmanned vehicle is 200 kilograms, and the speed of the unmanned vehicle is 16 meters per second. Calculation formula calculate is 0.78, due to the minimum braking coefficient threshold is 0.6, , so the unmanned vehicle's own braking state is normal; when the unmanned vehicle drives to the intersection at a speed of 10 meters per second, the sensor detects that there are other vehicles and the unmanned vehicle in an emergency intersection. The speed data of the oncoming vehicle at the current moment is 11 meters per second, and the speed data of the next second is 11 meters per second; the driving state of the other vehicle is predicted by calculating its acceleration change trend, and the calculation formula is: , the calculated result a is 0 meters per square second; If the other vehicle enters the intersection at an accelerated or constant speed, the unmanned vehicle will issue a warning, extend the reference direction line based on the front corner of the other vehicle on the side close to the unmanned vehicle, and use the intersection of the two reference direction lines as the predicted collision point, and collect the collision distance between the collision point and the vehicle. and They are 10 meters and 8 meters respectively; when the unmanned vehicle issues a warning, the acceleration value of the other vehicle is calculated again. The current speed of the other vehicle is 11 meters per second, and the next second is 10 meters per second, so its acceleration is calculated as -1 meter per square second; since its acceleration is less than zero, it means that it brakes after receiving the warning from the unmanned vehicle, so the emergency braking distance of the unmanned vehicle and the other vehicle is calculated according to the current vehicle speed. The calculation formula is , obtained by calculation and They are 6.4 meters and 8.3 meters respectively; and , then the unmanned vehicle and the other vehicle are mapped to a two-dimensional coordinate system. When the other vehicle stops, the horizontal line of the front of the vehicle is the crossing line, and the vertical distance between the collision point and the crossing line is detected to be 0.3 meters. The center point of the unmanned vehicle's stopping point is connected to the collision point to form one side z, and the length of z is 3.6 meters. The other side is formed by extending the collision point perpendicular to the z side by 1.8 meters. The unconnected endpoints of the two line segments are connected to form a collision adjustment triangle; the width of the unmanned vehicle is 1.5 meters; then the angle of the endpoint of the collision triangle where the unmanned vehicle is located is calculated The value of is calculated as , the calculation result is 22 degrees. When the unmanned vehicle brakes to the corresponding stopping point, it uses 22 degrees as the remedial deflection angle, drives out of the intersection at a speed of 5 meters per second, and uploads data as secondary environmental data anomalies; the minimum driving speed at the intersection is 5 meters per second; the management end receives the unmanned vehicle data, and provides comprehensive report feedback, marking the secondary environmental data anomalies and issuing warnings.

[0064] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0065] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A device anomaly detection method based on precise positioning technology, characterized in that: The method comprises the following steps: S100, first, the driving data of the unmanned vehicle is collected by multiple sensors installed on the unmanned vehicle and transmitted to the back-end control end; S200, the control end receives the data and pre-processes the data, and then visualizes the data through a digital-to-graphic conversion method after preliminary processing; S300, the management end conducts a comprehensive analysis of the visualized data table and processed data to determine whether the unmanned vehicle is in an abnormal state and formulate a corresponding decision plan; S400: The management terminal reports and feedbacks the driving status of the unmanned vehicle in real time based on the analysis results, and issues an alarm for abnormal data; The specific steps of collecting the driving data of the unmanned vehicle through the multi-sensors installed on the unmanned vehicle and transmitting it to the back-end control end in S100 are as follows: S101. During the driving process of the unmanned vehicle, the driving data, environmental data and road condition data of the unmanned vehicle are collected in real time through a multi-sensor device of the unmanned vehicle itself; wherein the multi-sensor includes a laser radar, a camera, a millimeter-wave radar, a GPS positioning sensor and an inertial measurement sensor; S102, using the 5G signal transmitting and receiving device of the vehicle body device to convert the collected unmanned vehicle driving data, environmental data and road condition data into data signals and transmit them to the management end, and receive the command data transmitted by the management end; In S200, the control end receives data and pre-processes the data, and the specific steps of visualizing the data through digital-to-graphic conversion after preliminary processing are as follows: S201, the management end receives the data transmitted by the unmanned vehicle end, performs data cleaning, data conversion, feature extraction and data association operations on the data, processes the original data in an orderly manner and performs data association; wherein the data association operations include time-speed data association, time-distance data association, and distance-speed data association; S202, using a two-dimensional chart and a coordinate system to convert the associated data into digital form and visualize the data; The specific steps of the management end in S300 to comprehensively analyze the visualized data table and processed data to determine whether the unmanned vehicle is in an abnormal state and formulate a corresponding decision plan are as follows: S301, analyzing the braking force of the unmanned vehicle's own data through the vehicle's driving speed, distance and power consumption data association diagram; the braking force of the unmanned vehicle is analyzed by calculating the unmanned vehicle's emergency braking coefficient μ, and its calculation formula is: Among them, P is the output power of the unmanned vehicle engine, m is the mass of the unmanned vehicle, v is the initial braking velocity of the unmanned vehicle, and g is the gravity acceleration; the braking coefficient of the unmanned vehicle is compared with the minimum braking coefficient threshold μ min For comparison, if μ<μ min , then the unmanned vehicle’s braking data is abnormal; S302, if μ ≥ μ min , the unmanned vehicle's own braking performance is normal; when the unmanned vehicle detects through the sensor that there are other vehicles and the unmanned vehicle in an emergency intersection at the intersection, the speed data of the oncoming vehicle at the current time t0 and the next time t1 are collected, and the driving state of the other vehicle is predicted by calculating its acceleration change trend. The calculation formula is: If a<0, the other vehicle starts to slow down. When the other vehicle enters the intersection, the front angle of the other vehicle close to the unmanned vehicle is used as the base point, and the extension line of the current direction of this point is used as the reference direction line of the vehicle. By detecting the deviation angle θ of the reference direction line of the other vehicle, it is determined whether the other vehicle has direction deviation behavior; if θ>θ0, the other vehicle has direction deviation behavior, and the unmanned vehicle drives normally; if θ≤θ0, the other vehicle is driving straight, and the unmanned vehicle adjusts its speed to [v0,v1) when entering the intersection; where v0 is the minimum speed for passing the intersection, and v1 is the speed of the other vehicle passing the intersection; S303, if a ≥ 0, the other vehicle enters the intersection at an accelerated or constant speed, and the unmanned vehicle issues a warning, extends reference direction lines based on the front corner of the other vehicle on the side close to the unmanned vehicle, and uses the intersection of the two reference direction lines as the predicted collision point, and collects the collision distance s from the collision point to the vehicle. cd1 and cd2 ; Among them, s cd1 is the collision distance between the collision point and the unmanned vehicle, s cd2 is the collision distance between the collision point and the other vehicle; when the unmanned vehicle issues a warning, repeat the acceleration calculation step in step S302 and determine whether the other vehicle has braking behavior; if there is braking behavior, the emergency braking distances of the unmanned vehicle and the other vehicle are calculated according to the current vehicle's driving speed, and the calculation formula is: According to the calculation, s bd1 and bd2 ; Among them, s bd1 is the braking distance of the unmanned vehicle, s bd2 is the braking distance of the other vehicle; the collision distance and braking distance corresponding to the vehicle are compared respectively. If s bd1 <s cd1 And s bd2 <s cd2 , the unmanned vehicle detects the speed and position of the other vehicle in real time, intelligently adjusts the speed to drive out of the intersection, and uploads the data as a first-level environmental data anomaly; if s bd1 <s cd1 And s bd2 ≥s cd2 , then the unmanned vehicle and the other vehicle are mapped into a two-dimensional coordinate system. When the other vehicle stops, the horizontal line of the front of the vehicle is used as the crossing line, and the vertical distance r between the collision point and the crossing line is detected. The center point of the unmanned vehicle's stopping point and the collision point are connected to form a side z, and the length of the side z is s. cd1 -s bd1 , the collision point is perpendicular to the z side and extends a distance of r+h to form the other side, and the unconnected endpoints of the two line segments are connected to form a collision adjustment triangle; where h is the width of the unmanned vehicle body; then the value of the angle α of the endpoint of the collision triangle where the unmanned vehicle is located is calculated, and the calculation formula is in, When the unmanned vehicle brakes to the corresponding stop point, it uses α as the remedial deflection angle, drives out of the intersection at v0 as the driving speed, and uploads data as secondary environmental data anomaly; if s bd1 ≥s cd1 And s bd2 <s cd2 , the unmanned vehicle brakes to the stop point, takes v0 as the driving speed, drives out of the intersection without deviation, and uploads data as secondary environmental data anomaly; if s bd1 ≥s cd1 And s bd2 ≥s cd2 , then The steering angle is used to change the direction for emergency avoidance, and the uploaded data is a level 3 environmental data abnormality; if there is no braking behavior, The steering angle is changed to make emergency avoidance, and the uploaded data is level 3 environmental data abnormality.

2. According to claim 1, a device anomaly detection method based on precise positioning technology is characterized by: The specific steps of the management end in S400 reporting and feeding back the driving status of the unmanned vehicle in real time according to the analysis results and issuing an alarm for abnormal data are as follows: S401, the management end processes and analyzes the unmanned vehicle driving data and environmental data through visualization, and displays the analysis results in the form of a report; S402: The management terminal marks the abnormal data of the unmanned vehicle driving in the report as abnormal and issues a warning to the management personnel.

3. A device anomaly detection system based on precise positioning technology, using the device anomaly detection method based on precise positioning technology as claimed in claim 1 or 2, characterized in that: The equipment abnormality monitoring system based on precise positioning technology includes a multi-segment data acquisition module, a data visualization module, a data fusion analysis module, and an equipment abnormality feedback module; The multi-segment data acquisition module is used to collect the operating data of the unmanned vehicle and transmit the data to the remote terminal through the transmission medium; the data visualization module is used to clean and fuse the collected data, and convert the processed data into a graphic form to realize data interaction; the data fusion analysis module conducts an abnormal analysis and decision-making on the current operating status and data of the unmanned vehicle by conducting a comprehensive analysis of the visualized data chart and the processed data; the equipment abnormality feedback module is used to feedback the abnormal situation of the real-time data of the unmanned vehicle and issue an alarm for the abnormal data; The multi-segment data acquisition module is connected to the data visualization module; the data visualization module is connected to the data fusion analysis module; the data fusion analysis module is connected to the equipment abnormality feedback module.

4. The device anomaly detection system based on precise positioning technology according to claim 3 is characterized in that: The multi-segment data acquisition module includes a front-end device data acquisition unit, a data transmission unit and a back-end central control unit; the front-end device data acquisition unit includes a multi-sensor device; wherein the multi-sensor device includes a lidar, a camera, a millimeter-wave radar, a GPS positioning sensor and an inertial measurement sensor; the data transmission unit utilizes the 5G signal transmitting and receiving device of the device to transmit the driving data of the unmanned vehicle to the back-end central control unit; the back-end central control unit is used to receive the unmanned vehicle operation data and environmental data collected and transmitted by the front-end acquisition device, and analyze and process the data.

5. The device anomaly detection system based on precise positioning technology according to claim 4 is characterized in that: The data visualization module includes a data fusion unit, a number-shape conversion unit and a data interaction unit; the data fusion unit is used to perform data cleaning, conversion, feature extraction and data missing filling processing on the collected data, and associate and fuse the processed data; the number-shape conversion unit performs model conversion on the processed fused data, and converts the data into visual graphics and tables; the data interaction unit is used to display the processed data and the converted numbers and shapes on the management end through an interface, and provides interactive options for administrators to read and analyze the data independently.

6. The device anomaly detection system based on precise positioning technology according to claim 5, characterized in that: The data fusion analysis module includes a real-time environment simulation unit, a road condition prediction and analysis unit and a dynamic decision-making unit; the real-time environment simulation unit connects the actual operation data of the unmanned vehicle and the environmental data in series by processing the data and converting them into visible numbers to simulate the actual operation of the unmanned vehicle; the road condition prediction and analysis unit combines the environmental data simulation to perform a fusion prediction on the road conditions within the monitoring range of the unmanned vehicle, and uses the actual road condition data as the benchmark data to predict the changes in road conditions within the monitoring area of ​​the unmanned vehicle; wherein the road conditions include changes in the environment, vehicles, personnel and traffic signs; the dynamic decision-making unit makes decisions, controls and adjusts the current driving status data of the unmanned vehicle based on the road condition prediction results and the changes and changes in the predicted road condition data.

7. The device anomaly detection system based on precise positioning technology according to claim 6 is characterized by: The equipment abnormality feedback module includes an equipment status data feedback unit and an equipment abnormality data alarm unit; the equipment status data feedback unit comprehensively feedbacks the analysis results of the unmanned vehicle's driving status data to provide the administrator with real-time feedback on the driving status of the unmanned vehicle; the equipment abnormality data alarm unit is used to alarm for abnormal situations in the driving data and environmental data collected during the driving process of the unmanned vehicle and the subsequent data processing and analysis process, so as to prompt the unmanned vehicle that there is an abnormal situation.

Images