A kind of inspection robot centralized monitoring system and method

Abstract

The application discloses a kind of inspection robot centralized monitoring system and method, and the application relates to inspection robot monitoring technical field.The composition of the system includes inspection robot perception module, inspection robot data processing module, inspection robot intelligent evaluation module and inspection robot execution module.Inspection robot perception module is used to obtain inspection robot data and its operating environment data;Inspection robot data processing module is divided into illumination intensity processing unit for drawing illumination intensity contrast curve graph, ground three-dimensional grid model construction unit for constructing mine ground three-dimensional grid model and power processing unit for drawing power curve graph and constructing mine power consumption monitoring model;Inspection robot intelligent evaluation module analyzes illumination intensity contrast curve graph, mine ground three-dimensional grid model and inspection robot power, and evaluates abnormal conditions in the operation process of inspection robot;Inspection robot execution module takes corresponding measures according to the evaluated abnormal conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of inspection robot monitoring, in particular to an inspection robot centralized monitoring system and method. BACKGROUND

[0002] The background technology of the inspection robot centralized monitoring system mainly comes from the demand for improvement of traditional manual inspection methods. In dangerous or complex environments, manual inspection has many limitations, such as blind areas, low efficiency, safety risks, etc. To overcome these limitations, the inspection robot centralized monitoring system has emerged. This system integrates sensors, the Internet of Things, data processing and analysis, and remote monitoring technologies to achieve intelligent monitoring of equipment and environments. These technologies work together to enable the system to collect, process, and analyze inspection data in real time, promptly identify and address potential safety hazards. The application of the inspection robot centralized monitoring system not only improves the efficiency and accuracy of inspection work, but also reduces the cost and risk of manual inspection, providing a strong guarantee for the safety production and intelligent management of enterprises.

[0003] Although the existing inspection robot centralized monitoring system and method have made great progress, there are still some problems to be optimized. When the working environment of the inspection robot is insufficiently illuminated, it may cause the monitoring image to be blurred and the color to be distorted, reducing the accuracy of fault identification and the overall monitoring effect. Secondly, the inspection robot working in the mining area has poor mobility due to the rugged terrain, and the mechanical wear is aggravated. Moreover, the inspection robot lacks real-time power monitoring when performing work. When the power is insufficient, the working performance of the inspection robot may be limited, or even cause the inspection robot to power off during task execution, interrupting the inspection task. SUMMARY

[0004] To solve the above problems, the present application provides an inspection robot centralized monitoring system, which comprises an inspection robot perception module, an inspection robot data processing module, an inspection robot intelligent evaluation module and an inspection robot execution module.

[0005] The inspection robot perception module is used to acquire inspection robot data and its operating environment data, wherein the inspection robot data is real-time power data, and the operating environment data is illumination intensity data and mining area ground three-dimensional point cloud data.

[0006] The inspection robot data processing module is divided into an illumination intensity processing unit, a ground three-dimensional grid model construction unit and a power processing unit. The illumination intensity processing unit is used to set the illumination intensity threshold and draw the illumination intensity contrast curve graph. The ground three-dimensional grid model construction unit is used to construct the mining area ground three-dimensional grid model. The power processing unit is used to draw the real-time power curve graph and construct the mining area power consumption monitoring model.

[0007] The intelligent evaluation module of the inspection robot is configured to analyze the light intensity contrast graph, the three-dimensional grid model of the mine area ground, and the real-time power of the inspection robot, and evaluate abnormal conditions in the operation process of the inspection robot.

[0008] The execution module of the inspection robot is configured to take corresponding measures in response to the evaluated abnormal conditions.

[0009] Further, the process of obtaining the data of the inspection robot and the data of the running environment thereof includes:

[0010] A1. The light sensor is installed on the camera of the inspection robot to collect the light intensity of the working environment thereof;

[0011] A2. The laser radar emits a laser beam, which is reflected when projected onto the ground after interacting with the ground. The laser radar receives the reflected light signal, calculates the distance between the laser beam and the ground by combining the displacement formula and the speed of light, and changes the emission angle of the laser beam by the rotating mirror of the laser radar during the above process to scan the mine area environment in all directions, record the angle of each laser projection point, and calculate the precise coordinates of the laser projection point in the three-dimensional space by combining the distance and angle of each laser projection point. Each point contains three coordinate values of x, y, and z, and the three-dimensional point cloud data of the mine area ground is obtained.

[0012] A3. The current sensor is connected to the battery pack of the inspection robot to collect real-time power data.

[0013] Further, in the light intensity processing unit, the process of calculating the light intensity threshold and drawing the light intensity contrast graph includes:

[0014] The light intensity threshold affecting the monitoring image of the inspection robot is calculated by the formula:

[0015] L_threshold = L_min + k * (L_max - L_min)

[0016] Where L_threshold is the light intensity threshold, L_min is the minimum light intensity, L_max is the maximum light intensity, and k is a coefficient between 0 and 1, which is set according to actual requirements to adjust the position of the threshold.

[0017] A two-dimensional coordinate system is established, with the horizontal axis representing time and the vertical axis representing light intensity. The calculated light intensity threshold and real-time light intensity are mapped to the two-dimensional coordinate system as a red line and a black line, respectively, to obtain the light intensity contrast graph.

[0018] Further, in the three-dimensional grid model construction unit, the process of constructing the three-dimensional grid model of the mine area ground includes:

[0019] B1, import the mine area ground three-dimensional point cloud data into the GIS software for denoising, filtering and registration, use the tools and algorithms in the GIS software to segment and classify the point cloud data, and correspond to different ground features;

[0020] B2, use the Delaunay triangulation algorithm, select a point cloud data as the initial point, construct the initial triangle containing the point, insert other points of the point cloud data into the constructed triangular grid, find the influence triangle containing the newly inserted point, delete its common edge, connect the new point and the vertex of the influence triangle, form a new triangle, optimize the newly formed triangle locally by the minimum internal angle maximum principle and the maximum empty circle principle, generate a triangular mesh model describing the shape and features of the mine area ground;

[0021] B3, calculate the surface normal vector N of the generated triangular mesh model:

[0022] N=AB×AC

[0023] Wherein, A(x1, y1, z1), B(x2, y2, z2) and C(x3, y3, z3) three points constitute a triangle, AB=(x2-x1, y2-y1, z2-z1), AC=(x3-x1, y3-y1, z3-z1);

[0024] Through the above calculation, the final mine area ground three-dimensional mesh model is obtained.

[0025] Further, in the power processing unit, the process of setting the light intensity threshold and drawing the light intensity contrast curve includes:

[0026] Set 55% power as the power threshold of the inspection robot, establish a two-dimensional rectangular coordinate system, wherein the horizontal axis is time and the vertical axis is power value, map the real-time power to the coordinate system, and obtain the real-time power curve.

[0027] Further, in the power processing unit, the process of constructing the mine area power consumption monitoring model includes:

[0028] Set the time interval to 10 minutes, calculate the absolute value of the difference between the power of the first 10 minutes and the power of the last 10 minutes, and obtain the power consumption of the inspection robot in the same time period;

[0029] The power consumption of the inspection robot in the same time period and the mine ground three-dimensional grid model are preprocessed, the mine ground three-dimensional grid model is combined into a data matrix by using a principal component analysis algorithm, each row describes a sample, and each column describes a feature, the terrain data and the ground cover data are extracted as feature targets of the mine ground three-dimensional grid model, the correlation coefficients of various features in the data matrix are calculated, the eigenvalues and eigenvectors of the correlation coefficient matrix are solved by using a Jacobi method, the variance contribution rate of each principal component in the data set is analyzed, when the contribution rate is greater than 85%, the principal component is selected as a representative feature, and the feature data of the terrain data and the ground cover data are extracted, wherein the extracted terrain feature data is elevation, slope and slope direction, and the extracted ground cover feature data is vegetation type, soil type and ground obstacle;

[0030] The random forest parameters are set, the power consumption of the inspection robot in the same time period, the terrain feature data and the ground cover feature data are taken as a data set, 70% of the data set is divided into a training set, and 30% of the data set is divided into a test set, the initial mine power consumption detection model is trained by using the training set, the initial mine power consumption detection model monitors the power consumption of the inspection robot in the same time period in real time through the terrain feature data and the ground cover feature data, acquires a nonlinear relationship between real-time elevation, slope, slope direction, vegetation type, soil type and ground obstacle data and real-time power consumption, the initial mine power consumption detection model is evaluated by using the test set, the model parameters are adjusted to optimize the model, and the mine power consumption monitoring model is acquired.

[0031] Further, in the intelligent evaluation module of the inspection robot, the process of analyzing the illumination intensity comparison curve and the mine ground three-dimensional grid model comprises:

[0032] According to the illumination intensity threshold for normal work of the inspection robot, it is determined through the illumination intensity comparison curve, when the real-time illumination intensity is lower than the illumination intensity threshold, the working environment of the inspection robot is dark, and the monitoring effect is affected.

[0033] Through the mine ground three-dimensional grid model, the real-time terrain and the ground obstacles in the working environment of the inspection robot in the mine are analyzed, when the inspection robot identifies hills, valleys, steep sections of slopes and target motion region obstacles, the movement of the inspection robot is limited.

[0034] Further, the process of analyzing the real-time power of the inspection robot in the intelligent evaluation module of the inspection robot comprises:

[0035] When the inspection robot runs in the flat area of the working environment, the real-time power curve is analyzed to monitor the power in real time; when the inspection robot runs in the mining area, through the mining area power consumption monitoring model, the nonlinear relationship between the real-time elevation, slope, slope direction, vegetation type, soil type, and surface obstacle data and the real-time power consumption of the mining area ground features is used to monitor the power of the inspection robot in the mining area in real time;

[0036] When the power is less than 55%, the performance of the inspection robot decreases, and the power is insufficient to supply the inspection robot to perform a complete task, and the analysis result is wirelessly transmitted to the inspection robot execution module;

[0037] Further, the process of coping with abnormal situations in the inspection robot execution module includes:

[0038] When the light intensity is lower than the light intensity threshold, an instruction is issued to mobilize the inspection robot to turn on the LED light to supplement the light;

[0039] When the inspection robot identifies steep sections of hills, valleys, and slopes, an execution instruction is issued to mobilize the inspection robot to switch to a track running mode; when the inspection robot identifies that the target motion area has obstacles, an execution instruction is issued to mobilize the inspection robot to run around the obstacles;

[0040] When the inspection robot works in the flat area and in the mining area, and the real-time power is less than 55%, the inspection robot centralized monitoring system issues a power shortage alarm prompt to the client through the execution instruction, and the client receives the instruction and takes charging measures to cope.

[0041] Further, a centralized monitoring method of an inspection robot is realized based on the above-mentioned centralized monitoring system of the inspection robot, which is composed of the following steps:

[0042] S1, the light intensity of the working environment of the inspection robot is collected by using the light sensor; the three-dimensional point cloud data of the ground of the mining area is obtained by using the laser radar; and the real-time power data of the inspection robot is collected by using the current sensor;

[0043] S2, the light intensity threshold is calculated by the light intensity processing unit, and the light intensity comparison curve is drawn; the three-dimensional grid model of the ground of the mining area is constructed by the ground three-dimensional grid model construction unit through GIS technology and Delaunay triangulation algorithm; the real-time power curve is drawn by the real-time power processing unit, and the power consumption in the same time period is calculated; the mining area power consumption monitoring model is constructed by the mining area power consumption monitoring model construction unit using the random forest algorithm;

[0044] S3, the light intensity comparison curve, the three-dimensional grid model of the ground of the mining area, and the real-time power of the inspection robot are analyzed, and the analysis result is wirelessly transmitted to the inspection robot execution module;

[0045] S4, when the light intensity is lower than the threshold value, an instruction is issued to mobilize the inspection robot to open the LED light for light compensation;

[0046] S5, when the inspection robot identifies a steep section of hills, valleys and slopes, an execution instruction is issued to mobilize the inspection robot to switch to a track running mode; when the inspection robot identifies that the target motion area has obstacles, an execution instruction is issued to mobilize the inspection robot to run around the obstacles;

[0047] S6, during the work of the inspection robot in the flat area in the mining area, when the real-time power is lower than 55%, the inspection robot centralized monitoring system sends an insufficient power alarm prompt to the client through the execution instruction, and the client receives the instruction and takes charging measures to respond.

[0048] The beneficial effects of the present application: compared with the traditional inspection robot centralized monitoring system and method, the sensor technology, laser radar technology, three-dimensional modeling technology, model construction technology and modern information technology in the system are closely combined, a variety of sensor technology and laser radar technology are integrated, the light intensity data and real-time power data of the inspection robot and the three-dimensional point cloud data of the mining area are accurately captured, and through the random forest algorithm and big data analysis technology, the real-time and comprehensive monitoring of the inspection robot centralized monitoring system is achieved, the light intensity comparison curve, the three-dimensional grid model of the mining area ground, the real-time power curve and the mining area power consumption monitoring model obtained after data processing, real-time analysis of the light intensity, mining area ground environment and real-time power consumption of the inspection robot during operation, real-time monitoring of abnormalities, timely response to abnormalities generated during system operation, solve the problem that when the working environment of the inspection robot is insufficient, the monitoring image picture is blurred, the accuracy of fault identification is reduced, and the overall monitoring effect is reduced, the inspection robot working in the mining area, due to the rugged ground, the moving performance will be worse, the mechanical wear will be more serious, the inspection robot lacks real-time power monitoring during work, and the working performance of the inspection robot may be limited due to insufficient power, and even the inspection robot is powered off during task execution, interrupting the inspection task, ensure that the method in the present application can refine the dynamic monitoring standard of the inspection robot centralized monitoring system in a more accurate range, so that the monitored data becomes a more accurate index under the same conditions, the research and application of this method significantly enhances the intelligent degree of the inspection robot centralized monitoring system during work. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 It is a block diagram of an inspection robot centralized monitoring system;

[0050] Figure 2 It is a flow chart of an inspection robot centralized monitoring method. DETAILED DESCRIPTION

[0051] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work are within the protection scope of the present application.

[0052] As shown in Figure 1 and Figure 2 The present application provides a technical solution: a centralized monitoring system of an inspection robot, comprising an inspection robot perception module, an inspection robot data processing module, an inspection robot intelligent evaluation module and an inspection robot execution module.

[0053] The inspection robot perception module is used to acquire inspection robot data and its running environment data, wherein the inspection robot data is real-time power data, and the running environment data is illumination intensity data and mine area ground three-dimensional point cloud data.

[0054] The inspection robot data processing module is divided into an illumination intensity processing unit, a ground three-dimensional grid model construction unit and a power processing unit, wherein the illumination intensity processing unit is used to set an illumination intensity threshold and draw an illumination intensity contrast curve graph; the ground three-dimensional grid model construction unit is used to construct a mine area ground three-dimensional grid model; and the power processing unit is used to draw a real-time power curve graph and construct a mine area power consumption monitoring model.

[0055] The inspection robot intelligent evaluation module is used to analyze the illumination intensity contrast curve graph, the mine area ground three-dimensional grid model and the real-time power of the inspection robot, and evaluate abnormal conditions in the running process of the inspection robot.

[0056] The inspection robot execution module takes corresponding measures in response to the evaluated abnormal conditions.

[0057] The acquisition process of the inspection robot data and its running environment data comprises:

[0058] A1, install an illumination sensor on the camera of the inspection robot to collect the illumination intensity of its working environment;

[0059] A2, the laser radar emits a laser beam, the laser beam is projected to the ground, interacts with the ground and reflects, the laser radar receives the reflected light signal, combines the displacement formula and the light speed value, calculates the distance between the light beam and the ground, in the above process, the rotation mirror of the laser radar changes the emission angle of the laser beam, scans the mining area environment in all directions, records the angle of each laser projection point, combines the distance and angle of each laser projection point, and the laser radar calculates the accurate coordinates of the laser projection point in three-dimensional space, each point contains three coordinate values of x, y and z, and then obtains the three-dimensional point cloud data of the mining area ground;

[0060] A3, the current sensor is connected with the battery pack of the inspection robot to collect real-time power data.

[0061] In the light intensity processing unit, the process of calculating the light intensity threshold and drawing the light intensity contrast curve includes:

[0062] The light intensity threshold affecting the monitoring image of the inspection robot is calculated by the formula:

[0063] L_threshold = L_min + k * (L_max - L_min)

[0064] Wherein, L_threshold is the light intensity threshold, L_min is the minimum light intensity, L_max is the maximum light intensity, k is a coefficient between 0 and 1, which is set according to actual demand to adjust the position of the threshold;

[0065] A two-dimensional coordinate system is established, the horizontal axis describes time and the vertical axis describes light intensity, the calculated light intensity threshold and real-time light intensity are respectively mapped to the two-dimensional coordinate system as red line and black line, and the light intensity contrast curve is obtained.

[0066] In the ground three-dimensional grid model construction unit, the process of constructing the three-dimensional grid model of the mining area ground includes:

[0067] B1, the three-dimensional point cloud data of the mining area ground is imported into GIS software for denoising, filtering and registration, the point cloud data is processed by segmentation and classification using the tools and algorithms in the GIS software, and different ground features are corresponded;

[0068] B2, using Delaunay triangulation algorithm, selecting a point cloud data as initial point, constructing initial triangle containing the point, inserting other points of point cloud data into the constructed triangular grid, finding the influence triangle containing the newly inserted point, deleting its common edge, connecting the new point and the vertex of the influence triangle to form a new triangle, locally optimizing the newly formed triangle by the minimum internal angle maximum principle and the maximum empty circle principle, generating the triangular mesh model describing the shape and characteristics of the mining area ground;

[0069] B3, calculating the surface normal vector N of the generated triangular mesh model:

[0070] N = AB x AC

[0071] wherein A (x1, y1, z1), B (x2, y2, z2) and C (x3, y3, z3) are three points forming a triangle, AB = (x2-x1, y2-y1, z2-z1), AC = (x3-x1, y3-y1, z3-z1);

[0072] Through the above calculation, the final mine ground three-dimensional grid model is obtained.

[0073] In the power processing unit, the process of setting the light intensity threshold and drawing the light intensity contrast curve includes:

[0074] Set 55% power as the power threshold of the inspection robot, establish a two-dimensional rectangular coordinate system, wherein the horizontal axis is time and the vertical axis is power value, map the real-time power to the coordinate system, and obtain the real-time power curve.

[0075] In the power processing unit, the process of constructing the mine power consumption monitoring model includes:

[0076] Set the time interval to 10 minutes, calculate the absolute value of the difference between the power of the first 10 minutes and the power of the last 10 minutes, and obtain the power consumption of the inspection robot in the same time period;

[0077] Preprocess the power consumption of the inspection robot in the same time period and the mine ground three-dimensional grid model, use the principal component analysis algorithm to combine the mine ground three-dimensional grid model into a data matrix, each row describes a sample, and each column describes a feature, extract the terrain data and surface cover data as the feature target of the mine ground three-dimensional grid model, calculate the correlation coefficient of each feature in the data matrix, use the Jacobi method to solve the eigenvalue and eigenvector of the correlation coefficient matrix, analyze the variance contribution rate of each principal component in the data set, when the contribution rate is greater than 85%, select the principal component as the representative feature, construct the expression of each principal component, and extract the feature data of the terrain data and surface cover data, wherein the extracted terrain feature data is elevation, slope and slope direction, and the extracted surface cover feature data is vegetation type, soil type and surface obstacle;

[0078] The random forest parameters are set, the power consumption of the inspection robot in the same time period, the terrain feature data and the ground cover feature data are taken as the data set, 70% of the data set is divided into a training set and 30% of the data set is divided into a test set, the initial mine power consumption detection model is trained by using the training set, the initial mine power consumption detection model monitors the power consumption of the inspection robot in the same time period in real time through the terrain feature data and the ground cover feature data, obtains the nonlinear relationship between the real-time elevation, slope, slope direction, vegetation type, soil type and ground obstacle data and the real-time power consumption, and the initial mine power consumption detection model is evaluated by using the test set, the model parameters are adjusted to optimize the model, and the mine power consumption monitoring model is obtained.

[0079] In the intelligent evaluation module of the inspection robot, the process of analyzing the illumination intensity comparison curve and the mine ground three-dimensional grid model includes:

[0080] Through the illumination intensity comparison curve, the illumination intensity threshold for normal operation of the inspection robot is determined, and when the real-time illumination intensity is lower than the illumination intensity threshold, the working environment of the inspection robot is dark, which affects the monitoring effect.

[0081] Through the mine ground three-dimensional grid model, the real-time topography and surface obstacles of the working environment of the inspection robot in the mine are analyzed, and when the inspection robot identifies hills, valleys, steep sections of slopes and target motion area obstacles, the movement of the inspection robot is limited.

[0082] The process of analyzing the real-time power of the inspection robot in the intelligent evaluation module of the inspection robot includes:

[0083] When the inspection robot runs in a flat area of the working environment, the real-time power curve is analyzed to monitor the power in real time; when the inspection robot runs in the mine, the nonlinear relationship between the real-time elevation, slope, slope direction, vegetation type, soil type and ground obstacle data and the mine ground features and the real-time power consumption is used to monitor the power of the inspection robot in the mine in real time through the mine power consumption monitoring model;

[0084] When the power is lower than 55%, the running performance of the inspection robot decreases, and the power is insufficient to supply the inspection robot to perform a complete task, and the analysis result is wirelessly transmitted to the inspection robot execution module.

[0085] In the inspection robot execution module, the process of dealing with abnormal situations includes:

[0086] When the illumination intensity is lower than the illumination intensity threshold, an instruction is issued to move the inspection robot to turn on the LED light to supplement the light;

[0087] When the inspection robot identifies a steep section of hills, valleys, and slopes, an execution instruction is issued to mobilize the inspection robot to switch the track operation mode; when the inspection robot identifies that the target motion area has obstacles, an execution instruction is issued to mobilize the inspection robot to run around the obstacles;

[0088] When the inspection robot works in a flat area and in a mining area, when the real-time power is less than 55%, the inspection robot centralized monitoring system is mobilized by an execution instruction to issue a power shortage warning prompt to the client, the client receives the instruction, and takes charging measures to respond.

[0089] A centralized monitoring method of an inspection robot, based on the above-mentioned centralized monitoring system of the inspection robot, consists of the following steps:

[0090] S1, use the light sensor to collect the light intensity of the working environment of the inspection robot; obtain the three-dimensional point cloud data of the mine area ground by laser radar; use the current sensor to collect the real-time power data of the inspection robot;

[0091] S2, the light intensity processing unit calculates the light intensity threshold and draws the light intensity comparison curve; the three-dimensional grid model construction unit constructs the three-dimensional grid model of the mine area ground by GIS technology and Delaunay triangulation algorithm; the real-time power processing unit draws the real-time power curve and calculates the power consumption in the same time period; the mine area power consumption monitoring model construction unit constructs the mine area power consumption monitoring model using the random forest algorithm;

[0092] S3, analyze the light intensity comparison curve, the three-dimensional grid model of the mine area ground, and the real-time power of the inspection robot, and wirelessly transmit the analysis results to the inspection robot execution module;

[0093] S4, when the light intensity is lower than the threshold, an instruction is issued to mobilize the inspection robot to turn on the LED light for light compensation;

[0094] S5, when the inspection robot identifies a steep section of hills, valleys, and slopes, an execution instruction is issued to mobilize the inspection robot to switch the track operation mode; when the inspection robot identifies that the target motion area has obstacles, an execution instruction is issued to mobilize the inspection robot to run around the obstacles;

[0095] S6, when the real-time power is less than 55% during the inspection robot's work in a flat area and in a mining area, the inspection robot centralized monitoring system is mobilized by an execution instruction to issue a power shortage warning prompt to the client, the client receives the instruction, and takes charging measures to respond.

[0096] It has to be noted that, in the present document, the terms "first", "second", etc. merely serve to identify different entities or actions and do not necessarily require or imply any actual relationship or order between these entities or actions. Moreover, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. In other words, without further restriction, reference to elements in a "comprising" list is not a limitation as other non-listed or inherent elements are also contemplated. The statement "including one... limited element" does not exclude the presence of additional identical elements in the process, method, article, or apparatus. While embodiments of the application have been shown and described, it is to be understood that various additional changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the spirit and scope of the application, which is defined by the appended claims and their equivalents.

Claims

1. A centralized monitoring system for inspection robots, comprising an inspection robot perception module, an inspection robot data processing module, an inspection robot intelligent evaluation module and an inspection robot execution module, characterized in that: the inspection robot perception module is configured to obtain inspection robot data and its operating environment data, wherein the inspection robot data is real-time power data, and the operating environment data is illumination intensity data and mine ground three-dimensional point cloud data; the inspection robot data processing module is divided into an illumination intensity processing unit, a ground three-dimensional grid model construction unit and a power processing unit, wherein the illumination intensity processing unit is configured to set an illumination intensity threshold and draw an illumination intensity contrast curve; the ground three-dimensional grid model construction unit is configured to construct a mine ground three-dimensional grid model; and the power processing unit is configured to draw a real-time power curve and construct a mine power consumption monitoring model; the inspection robot intelligent evaluation module is configured to analyze the illumination intensity contrast curve, the mine ground three-dimensional grid model and the real-time power of the inspection robot, and evaluate abnormal conditions in the operation process of the inspection robot; the inspection robot execution module is configured to take corresponding measures for the evaluated abnormal conditions; the process of obtaining the inspection robot data and its operating environment data comprises: A1. installing an illumination sensor on the camera of the inspection robot to collect the illumination intensity of its working environment; A2. the laser radar emits a laser beam, which is reflected when it hits the ground. The laser radar receives the reflected light signal, calculates the distance between the laser beam and the ground based on the displacement formula and the speed of light, and changes the emission angle of the laser beam by rotating the mirror of the laser radar to scan the mine environment in all directions. The angle of each laser projection point is recorded, and the laser radar calculates the precise coordinates of the laser projection points in three-dimensional space based on the distance and angle of each laser projection point. Each point contains x, y and z coordinate values, and the mine ground three-dimensional point cloud data is obtained; A3. connecting the current sensor to the battery pack of the inspection robot to collect real-time power data; the process of calculating the illumination intensity threshold and drawing the illumination intensity contrast curve in the illumination intensity processing unit comprises: calculating the illumination intensity threshold affecting the monitoring image of the inspection robot by the formula: L_threshold = L_min + k * (L_max - L_min) where L_threshold is the illumination intensity threshold, L_min is the minimum illumination intensity, L_max is the maximum illumination intensity, and k is a coefficient between 0 and 1, used to adjust the position of the threshold; a two-dimensional coordinate system is established, with the horizontal axis representing time and the vertical axis representing illumination intensity. The calculated illumination intensity threshold and real-time illumination intensity are mapped to the two-dimensional coordinate system as a red line and a black line, respectively, to obtain the illumination intensity contrast curve.

2. The centralized monitoring system of the patrol robot according to claim 1, characterized in that: in the ground three-dimensional grid model construction unit, the process of constructing the mine ground three-dimensional grid model comprises: B1, import the 3D point cloud data of the mining area ground into the GIS software for denoising, filtering and registration, use the tools and algorithms in the GIS software to segment and classify the point cloud data, and correspond to different ground features; B2, use the Delaunay triangulation algorithm, select a point cloud data as the initial point, construct the initial triangle containing the point, insert other points of the point cloud data into the constructed triangle grid, find the influence triangle containing the newly inserted point, delete its common edge, connect the new point and the vertex of the influence triangle, form a new triangle, and locally optimize the newly formed triangle by the minimum internal angle maximum principle and the maximum empty circle principle, generate a triangular mesh model describing the shape and features of the mining area ground; B3, calculate the surface normal vector N of the generated triangular mesh model: N=AB×AC Wherein, A(x1, y1, z1), B(x2, y2, z2) and C(x3, y3, z3) are three points forming a triangle, AB=(x2-x1, y2-y1, z2-z1), AC=(x3-x1, y3-y1, z3-z1); Through the above calculation, the final 3D mesh model of the mining area ground is obtained.

3. The centralized monitoring system of a patrol robot according to claim 2, characterized in that: In the power processing unit, the process of setting the light intensity threshold and drawing the light intensity contrast curve includes: Set 55% power as the power threshold of the inspection robot, establish a two-dimensional rectangular coordinate system, wherein the horizontal axis is time and the vertical axis is power value, map the real-time power to the coordinate system, and obtain the real-time power curve.

4. The centralized monitoring system of claim 3, wherein: In the power processing unit, the process of constructing the mining area power consumption monitoring model includes: Set the time interval to 10 minutes, calculate the absolute value of the difference between the power of the first 10 minutes and the last 10 minutes, and obtain the power consumption of the inspection robot in the same time period; Preprocess the power consumption of the inspection robot in the same time period and the 3D mesh model of the mining area ground, use principal component analysis algorithm, combine the 3D mesh model of the mining area ground into a data matrix, each row describes a sample, and each column describes a feature, extract the terrain data and surface cover data as the feature target of the 3D mesh model of the mining area ground, calculate the correlation coefficient of each feature in the data matrix, use Jacobi method to solve the eigenvalue and eigenvector of the correlation coefficient matrix, analyze the variance contribution rate of each principal component in the data set, when the contribution rate is greater than 85%, select the principal component as the representative feature, construct the expression of each principal component, and extract the feature data of the terrain data and surface cover data, wherein the extracted terrain feature data is elevation, slope and slope direction, and the extracted surface cover feature data is vegetation type, soil type and surface obstacle; The random forest parameters are set, the same time period power consumption of the inspection robot, terrain feature data and ground cover feature data are taken as a data set, 70% of the data set is divided into a training set and 30% of the data set is divided into a test set, the initial mine power consumption monitoring model is trained by using the training set, the initial mine power consumption monitoring model monitors the power consumption of the inspection robot in the same time period in real time through the terrain feature data and the ground cover feature data, the nonlinear relationship between the real-time elevation, slope, slope direction, vegetation type, soil type and ground obstacle data and the real-time power consumption is obtained, the initial mine power consumption monitoring model is evaluated by using the test set, the model parameters are adjusted to optimize the model, and the mine power consumption monitoring model is obtained.

5. The centralized monitoring system of a patrol robot according to claim 4, characterized in that: In the intelligent evaluation module of the inspection robot, the process of analyzing the illumination intensity comparison curve and the mine ground three-dimensional grid model includes: Through the illumination intensity comparison curve, the illumination intensity threshold for normal operation of the inspection robot is determined. When the real-time illumination intensity is lower than the illumination intensity threshold, the working environment of the inspection robot is dark, which affects the monitoring effect; Through the mine ground three-dimensional grid model, the real-time terrain and ground obstacles of the working environment of the inspection robot in the mine are analyzed. When the inspection robot identifies hills, valleys, steep sections of slopes and target motion area obstacles, the movement of the inspection robot is limited.

6. The centralized monitoring system of a patrol robot according to claim 5, wherein: In the intelligent evaluation module of the inspection robot, the process of analyzing the real-time power of the inspection robot includes: When the inspection robot runs in a flat area of the working environment, the real-time power curve is analyzed to monitor the power in real time. When the inspection robot runs in the mine, the nonlinear relationship between the real-time elevation, slope, slope direction, vegetation type, soil type and ground obstacle data and the mine ground features and the real-time power consumption is used to monitor the power of the inspection robot in the mine in real time through the mine power consumption monitoring model; When the power is lower than 55%, the running performance of the inspection robot decreases, and the power is insufficient to supply the inspection robot to perform a complete task. The analysis result is wirelessly transmitted to the inspection robot execution module.

7. The centralized monitoring system of a patrol robot according to claim 6, characterized in that: In the inspection robot execution module, the process of dealing with abnormal situations includes: When the illumination intensity is lower than the illumination intensity threshold, an instruction is issued to mobilize the inspection robot to open the LED light to supplement the light; When the inspection robot identifies hills, valleys, steep sections of slopes and target motion area obstacles, an execution instruction is issued to mobilize the inspection robot to switch to a track running mode; when the inspection robot identifies that there are obstacles in the target motion area, an execution instruction is issued to mobilize the inspection robot to run around the obstacles; When the real-time power of the inspection robot is lower than 55% in the flat area and in the mine, the inspection robot central monitoring system issues a power shortage alarm prompt to the client through the execution instruction, the client receives the instruction and takes charging measures to deal with it.

8. A centralized monitoring method of a patrol robot, implemented based on the centralized monitoring system of the patrol robot according to any one of claims 1-7, characterized in that, The following steps are included: S1, use the light sensor to collect the illumination intensity of the working environment of the inspection robot; use the laser radar to obtain the three-dimensional point cloud data of the mine ground; use the current sensor to collect the real-time power data of the inspection robot; S2, the light intensity processing unit calculates the light intensity threshold and draws the light intensity contrast curve; the ground three-dimensional grid model construction unit constructs the mine area ground three-dimensional grid model through GIS technology and Delaunay triangulation algorithm; the real-time power processing unit draws the real-time power curve and calculates the power consumption in the same time period; the mine area power consumption monitoring model construction unit constructs the mine area power consumption monitoring model by using random forest algorithm; S3, analyze the light intensity contrast curve, the mine area ground three-dimensional grid model and the real-time power of the inspection robot, and wirelessly transmit the analysis results to the inspection robot execution module; S4, when the light intensity is lower than the threshold, an instruction is issued to mobilize the inspection robot to open the LED light compensation processing; S5, when the inspection robot recognizes the steep sections of hills, valleys and slopes, an execution instruction is issued to mobilize the inspection robot to switch to the track running mode; when the inspection robot recognizes that the target motion area has obstacles, an execution instruction is issued to mobilize the inspection robot to run around the obstacles; S6, during the work of the inspection robot in the flat area in the mine area, when the real-time power is lower than 55%, the inspection robot centralized monitoring system sends a power shortage alarm prompt to the client through the execution instruction, and the client receives the instruction and takes charging measures to respond.

Images