Dashboard identification control system and method based on wheeled inspection robot

Abstract

The application discloses a dashboard identification control system and method based on a wheeled inspection robot, and relates to the technical field of dashboard identification.The instrument parameters of each monitoring device are collected and analyzed to determine the state of each monitoring device, a risk assessment index is generated, and the inspection path is dynamically adjusted based on the working state (risk assessment index) of the monitoring device; the wheeled inspection robot is controlled to identify the dashboard of each point by the received optimal inspection path, the instrument parameters of each point device are obtained, the device is prewarned according to the instrument parameters of the dashboard, and the device prewarning is triggered accordingly; the device without triggering the prewarning is recorded as a monitoring device, and the corresponding instrument parameters are sent to a server for saving as the data basis for the inspection path planning of the wheeled inspection robot in the next round, so that the abnormality can be quickly identified and prewarned, and the intelligent level of device management is significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of instrument panel identification, in particular to an instrument panel identification control system and method based on a wheeled inspection robot. BACKGROUND

[0002] With the development of science and technology, more and more artificial instrument inspection in factory is gradually replaced by robots, such as wheeled inspection robots, because the working environment in many large factories is harsh, usually manifested as high temperature, high noise, harmful gas, dangerous area (high voltage area, enclosed space, etc.), and the wheeled inspection robot can well reduce the personnel risk in the instrument inspection of the factory.

[0003] The current wheeled robot usually identifies and uploads each instrument according to the fixed route in the background during the inspection. This long-term fixed inspection route has great limitations, lacks intelligent automatic planning of the display state of each instrument, and cannot realize self-adaptive inspection in complex scenes. SUMMARY

[0004] The main purpose of the present application is to provide an instrument panel identification control system and method based on a wheeled inspection robot to overcome the problems mentioned in the background.

[0005] To achieve the above purpose, according to one aspect of the present application, an instrument panel identification control system based on a wheeled inspection robot is provided, which comprises a server, an inspection intelligent planning module and an instrument identification control module.

[0006] The server is connected with the wheeled inspection robot to obtain the instrument parameters of each device, and the specific instrument parameters include temperature, power, amplitude and noise value at each monitoring time in the monitoring period.

[0007] The inspection intelligent planning module analyzes and judges the state of each device based on the instrument parameters at each monitoring time in the monitoring window to plan the inspection path of the wheeled robot, specifically:

[0008] Step one: retrieve the instrument parameters of each monitoring device, including temperature, power, amplitude and noise value, and each device corresponds to a set of standard parameters, including standard temperature interval and standard power interval; quantitative analysis is performed according to the instrument parameters and standard parameters to obtain the state value of the monitoring device at each monitoring time.

[0009] Step two: a two-dimensional rectangular coordinate system is constructed with the monitoring time as the horizontal coordinate and the state value as the vertical coordinate, the state value is input into the coordinate system according to the corresponding monitoring time, and the position of the state value in the coordinate system is recorded as a state point, and the state value polyline of the equipment is obtained by connecting the state points in sequence with line segments; the health trend state of the equipment is further analyzed according to the state value polyline to obtain the risk assessment index of the equipment;

[0010] Step three: the risk assessment values of the devices are obtained, the plan layout of the plant area is obtained, and the instrument panel of each device is marked in the plan layout of the plant area according to the corresponding position, thereby obtaining a plurality of point positions; the point position closest to the initial position of the wheeled robot is taken as the starting point, thereby obtaining the constraint condition of the inspection path: starting point-risk assessment value of each point position-starting point; a dynamic programming is generated according to the constraint condition of the inspection path to generate the best inspection route, and the best inspection route is sent to the instrument identification control module;

[0011] The instrument identification control module controls the wheeled inspection robot to identify the instrument panel of each point position device based on the received best inspection path to obtain the instrument parameters of each point position device, and performs early warning analysis on the device to determine whether to trigger the early warning.

[0012] Further, the specific process of quantitative analysis according to the instrument parameters and the standard parameters is as follows:

[0013] The instrument parameters of each monitoring device are retrieved, and the specific instrument parameters include temperature, power, amplitude and noise value, which are respectively denoted as Tj, Pj, Dj and Zj; wherein j=1, 2, 3…J, J is a positive integer, J represents the total number of monitoring times, and j represents the serial number of any one monitoring time; each device corresponds to a set of standard parameters, and the specific standard parameters include standard temperature interval and standard power interval, which are respectively denoted as [HT1, HT2] and [HP1, HP2];

[0014] The temperature Tj, power Pj, amplitude Dj, noise value Zj, standard temperature interval [HT1, HT2] and standard power interval [HP1, HP2] are normalized and the values are taken, and the values are calculated and analyzed by formula to obtain the state value Uj of the device at each monitoring time, and the specific calculation formula is:

[0015]

[0016] wherein a1, a2, a3, a4 are respectively set proportional constants, the values of which are set by the person skilled in the art according to actual conditions; dTj represents the shortest distance between temperature Tj and the standard temperature interval [HT1, HT2], if temperature Tj is within the standard temperature interval [HT1, HT2], then dTj = 0, if temperature Tj is greater than the maximum value in the standard temperature interval [HT1, HT2], then dTj = Tj-HT2; if temperature Tj is less than the minimum value in the standard temperature interval [HT1, HT2], then dTj = HT1-Tj; similarly, dPj represents the shortest distance between power Pj and the standard temperature interval [HP1, HP2], if power Pj is within the standard power interval [HP1, HP2], then dPj = 0, if power Pj is greater than the maximum value in the standard power interval [HP1, HP2], then dPj = Pj-HP2; if power Pj is less than the minimum value in the standard power interval [HP1, HP2], then dPj = HP1-Pj.

[0017] Further, the specific process of further analyzing the health trend state of the equipment according to the state value line graph is as follows:

[0018] Two adjacent state points can form a state line segment, from which several state line segments can be segmented from the state value line graph, and the mean value of the state values corresponding to the two endpoints of the state line segment is calculated to obtain a line segment value denoted as The slope of the state line segment is calculated by data fitting and denoted as

[0019] The line segment value and the slope of each state line segment are normalized and the numerical values are obtained, and the numerical values are calculated and analyzed according to the formula to obtain the risk assessment index KU of the equipment; the specific calculation formula is as follows:

[0020]

[0021] wherein a1, a2 are respectively set proportional constants, the specific values of which are set by the person skilled in the art according to actual needs.

[0022] Further, the dynamic programming is generated according to the constraint conditions of the inspection path to generate the best inspection route, and the specific steps are as follows:

[0023] 3-1: A heuristic function is defined: the starting point is denoted as P start , the straight line distance h(i) between the current point Pi and the target point P target , and the weighted distance G risk (i);

[0024] 3-2: Cost function definition: actual cost g(i), estimated cost h(i) and total cost f(i);

[0025] 3-3: Dynamic path planning based on heuristic function and cost function;

[0026] 3-4: If the end point P end If it is added to the closed set, it means that the best path has been found. Then, starting from the end point, the parent point is traced back to obtain the best path and send it to the instrument identification control module.

[0027] Furthermore, the specific process of defining the heuristic function is as follows:

[0028] 3-1-1: Let the starting point be P start , and mark the other points as Pi, where Pi represents any point in the plant layout diagram, i=1,2,3……I, I is a positive integer, I represents the point after removing the starting point P start The number of all points other than , i represents any one of them; specifically, the corresponding position coordinates are generated based on their position in the plant layout diagram, marked as (xi, yi), and their corresponding risk assessment value is recorded as KUi;

[0029] 3-1-2: Record the next point as the target point. The next point obtained by performing inspection path planning based on the current point can be used to dynamically plan the dashboard recognition path of the wheeled inspection robot. Specifically:

[0030] The current point Pi and the target point P are obtained by the Euclidean distance calculation formula target The straight-line distance between them is calculated using the Euclidean distance formula: Where (x target ,y target ) is the position coordinate of the target point;

[0031] 3-1-3: Define a heuristic function to calculate the weighted distance. The specific formula for calculating the weighted distance is:

[0032] G risk (i) = h(i) × (1 + w × KUi)

[0033] Where w is a weight coefficient that adjusts the degree of influence of risk on path selection. Its specific value is set by personnel in this field. KUi is the risk assessment index of the device represented by point i; h(i) is the straight-line distance between the device and the target device.

[0034] Furthermore, the specific process of cost function definition is:

[0035] 3-2-1: Actual cost g(i): from the starting point Pstart The cost to the current point Pi, the specific formula is expressed as:

[0036]

[0037] Wherein, i is the position of the current point, indicating that we want to calculate the total cost from the starting point to the i-th point; k is the index for accumulating path cost, by accumulating the path cost of each point, from 1 to i, the total cost from the starting point to the current point i is calculated; k-1 represents the index of the previous point of the current point k;

[0038] 3-2-2: Estimate the cost h(i): the heuristic estimate cost from the current point Pi to the target point, defined as g(i) calculated in the above 3-4;

[0039] 3-2-3: Total cost f(i): the final selected cost is the sum of the actual cost and the heuristic estimate cost, and the specific total cost calculation formula is f(i) = g(i) + G risk (i); wherein g(i) is the actual cost from the starting point to the point Pi, G risk (i) is the heuristic estimate cost from the point Pi to the target point.

[0040] Further, the specific process of dynamic path planning according to the heuristic function and the cost function is:

[0041] 3-3-1: Initialize an open set to store the point to be expanded, the starting point P start is added to the open set, and a closed set is initialized to store the points that have been visited; for the starting point P start , initialize g(P start ) = 0 and f(P start ) = G risk (P start );

[0042] 3-3-2: Expand the point, specifically:

[0043] Select the point P current with the minimum cost from the open set, i.e. select argmin Pi∈openset f(i), move P current to the closed set, and for each adjacent point P current of P neighbor , perform the following operations:

[0044] If P neighbor is already in the closed set, skip; calculate the new cost from the starting point P start to P neighbor , and the specific calculation formula is: gnew (P neighbor )=g(P current )+G weightde (P current ,P neighbor );

[0045] If P neighbor is not in the closed set or the new cost is smaller, update its cost and add it to the open set, and the specific calculation formula is: f new (P neighbor )=g new (P current )+G risk (P neighbor ), update the parent point of P neighbor to P current , and thus the path can be tracked.

[0046] Further, based on the received optimal inspection path, the wheeled inspection robot controls the instrument panel recognition of the equipment at each point.

[0047] After receiving the optimal inspection path, the wheeled inspection robot executes the inspection task according to the planned path, and the specific inspection task is to collect and identify the data of the instrument panel of the equipment at each point of the optimal inspection path. The navigation system of the robot uses sensors to sense the environment in real time. During movement, the wheeled inspection robot will track the path in real time, and use an obstacle detection algorithm to avoid obstacles.

[0048] When the wheeled inspection robot approaches the target equipment point, it accurately locates the position of the equipment instrument panel through the visual recognition system and positioning algorithm. When it is confirmed to reach the target point, the wheeled inspection robot collects images through sensors and identifies the images to extract the parameters of the instrument panel. The specific instrument panel parameters include temperature, power, amplitude and noise value. Thus, the temperature, power, amplitude and noise value of the equipment at each point within the monitoring window can be obtained.

[0049] Further, according to the instrument parameters of each point equipment, the equipment is analyzed to determine whether to trigger a warning, and the specific warning analysis process is:

[0050] The temperature, power, amplitude and noise values are compared with the set early warning threshold value respectively, and specifically, the temperature, power, amplitude and noise values of each monitoring time in the monitoring period are respectively compared with the temperature early warning threshold value, power early warning threshold value, amplitude early warning value and noise early warning value to calculate the difference value, and the difference value greater than zero is counted as the temperature early warning number, power early warning number, amplitude early warning number and noise early warning number, and is respectively recorded as N1, N2, N3 and N4; the corresponding difference value greater than zero is calculated to obtain the temperature early warning mean value, power early warning mean value, amplitude early warning mean value and noise early warning mean value of each monitoring time, and is respectively recorded as M1, M2, M3 and M4;

[0051] N1, N2, N3, N4, M1, M2, M3 and M4 are normalized and the values are taken, and the values are calculated and analyzed by formula to obtain the early warning value Y of each point device, and the specific calculation formula is:

[0052]

[0053] Wherein, γ1, γ2, γ3, γ4 are respectively set proportional constants, and the values are set by the person skilled in the art according to the actual demand;

[0054] The early warning value is compared with the set early warning threshold value, if the early warning value is greater than or equal to the set early warning threshold value, an early warning signal is generated, and the position coordinates of the early warning point in the factory layout are sent to the corresponding engineer;

[0055] If the early warning value is less than the set early warning threshold value, the point device is recorded as a monitoring device, and the instrument panel parameters of the monitoring device in the monitoring window are sent to the server for saving, so as to serve as the data basis for planning the next round of inspection path of the wheeled inspection robot.

[0056] In order to achieve the above purpose, according to another aspect of the present application, a wheeled inspection robot instrument panel identification control method is provided, which comprises the following steps:

[0057] S1: The instrument parameters of each device are obtained by communicating with the wheeled inspection robot, and the instrument parameters include the temperature, power, amplitude and noise values of each monitoring time in the monitoring period;

[0058] S2: The state of each device is analyzed and judged based on the instrument parameters of each monitoring time in the monitoring window to plan the inspection path of the wheeled robot; specifically:

[0059] Step one: call the instrument parameters of each monitoring device, the specific instrument parameters including temperature, power, amplitude and noise value, the device corresponds to a set of standard parameters, the specific standard parameters including standard temperature interval, standard power interval;According to the instrument parameters and standard parameters, the state value of the monitoring device at each monitoring time is obtained by quantitative analysis;

[0060] Step two: taking the monitoring time as the horizontal coordinate and the state value as the vertical coordinate to construct a two-dimensional rectangular coordinate system, inputting the state value into the coordinate system according to its corresponding monitoring time, and recording the position of the state value in the coordinate system as a state point, and connecting the state points in turn to obtain the state value line chart of the device;According to the state value line chart, the health trend state of the device is further analyzed to obtain the risk assessment index of the device;

[0061] Step three: the risk assessment value of the device is obtained, the plane layout of the plant is obtained, and the instrument panel of each device is marked in the plane layout of the plant according to its corresponding position, so as to obtain several point positions;The point closest to the initial position of the wheeled robot is taken as the starting point, so as to obtain the constraint condition of the inspection path: starting point-risk assessment value of each point position-starting point;According to the constraint condition of the inspection path, a dynamic programming is generated to generate the best inspection route, and it is sent to the instrument identification control module;

[0062] S3: based on the received best inspection path, the wheeled inspection robot is controlled to identify the instrument panel of each point position device to obtain the instrument parameters of each point position device, and the device is analyzed to determine whether the warning is triggered.

[0063] The beneficial effects of the present application are as follows:

[0064] The present application collects and analyzes the instrument parameters (such as temperature, power, amplitude, noise value, etc.) of each monitoring device to determine the state of each monitoring device, generates a risk assessment index, and dynamically adjusts the inspection path based on the working state (risk assessment index) of the monitoring device. This method discards the traditional fixed route method and can adjust the inspection priority according to the risk assessment index of the device. The state of the device is no longer fixed, but changes constantly during the inspection process, making the inspection path more flexible and intelligent.

[0065] The present application integrates the state value and risk assessment index of the device into the dynamic path planning algorithm. When planning the inspection path, not only the spatial position (Euclidean distance) of the device is considered, but also the health risk (risk assessment index) of the device is included in the decision-making process. According to the definition of weighted distance and heuristic function, high-risk devices can be dynamically selected to optimize the inspection route, so that the robot can first reach the device position that needs urgent inspection, thereby improving the inspection efficiency and response speed, and realizing flexible adjustment of the inspection strategy according to the health state of the on-site device to cope with complex on-site changes.

[0066] The application controls the wheeled inspection robot for the instrument panel identification of each point by the received optimal inspection route, obtains the instrument parameters of each point device, not only improves the pertinence of inspection, but also avoids unnecessary redundant inspection, provides adaptive path adjustment and monitoring function of the device instrument panel, so that the robot can continuously and efficiently perform tasks in complex scenes; according to the instrument parameters of the instrument panel, the device is prewarned and analyzed, and the device prewarning is triggered accordingly; the device without triggering the prewarning is recorded as a monitoring device, and the corresponding instrument parameters are sent to the server for saving, as the data basis for the inspection path planning of the wheeled inspection robot in the next round, realizing rapid identification of abnormality and prewarning, and significantly improving the intelligent level of device management. BRIEF DESCRIPTION OF DRAWINGS

[0067] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application, and the illustrative embodiments of the present application and their description serve the purpose of explaining the present application. In the drawings:

[0068] Figure 1 is a schematic diagram of the system module connection of the present application;

[0069] Figure 2 is a schematic diagram of the method flow of the present application. DETAILED DESCRIPTION

[0070] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0071] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present application.

[0072] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above description of the drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0073] In order to make the purposes and advantages of the present application more clear and apparent, the present application will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0074] According to the embodiments of the present application, as shown in Figure 1 A dashboard identification control system based on a wheeled inspection robot is provided, which comprises a server, a meter identification module and an inspection control module.

[0075] The server is connected in communication with the wheeled inspection robot in the factory area and the sensors carried on the wheeled inspection robot to obtain meter parameters of each monitoring device, and the specific meter parameters include temperature, power, amplitude and noise values at each monitoring time in the monitoring window.

[0076] The inspection intelligent planning module analyzes and judges the state of each device based on the meter parameters at each monitoring time in the monitoring window to plan the inspection path of the wheeled robot, so as to identify and upload the dashboard of the monitoring device in time; specifically:

[0077] Step one: obtain the meter parameters of each monitoring device, and the specific meter parameters include temperature, power, amplitude and noise values, and are respectively denoted as Tj, Pj, Dj and Zj; wherein j = 1, 2, 3 …… J, J is a positive integer, J represents the total number of monitoring times, and j represents the serial number of any one monitoring time;

[0078] Each device corresponds to a set of standard parameters, and the specific standard parameters include standard temperature interval and standard power interval, which are respectively denoted as [HT1, HT2] and [HP1, HP2]. It should be noted that the standard parameters refer to a set of ideal, predefined working ranges or standard values that the device should follow under normal working conditions. The specific standard temperature interval refers to the range within which the working temperature of the device should be maintained during normal operation. This temperature interval is usually defined by the device manufacturer or industry standards to ensure that the device can operate within an appropriate temperature range to avoid damage caused by overheating or excessively low temperature. The standard power interval refers to the range within which the power consumption or output power of the device should be located under normal operating conditions. The standard power interval is usually defined based on the design specifications, load requirements, and expected working conditions of the device.

[0079] The temperature Tj, power Pj, amplitude Dj, noise value Zj, standard temperature interval [HT1, HT2], and standard power interval [HP1, HP2] are normalized and their values are taken. The state value Uj of the device at each monitoring time is obtained by formulaic calculation and analysis of the values. The specific calculation formula is:

[0080]

[0081] where a1, a2, a3, a4 are proportional constants set by the person skilled in the art according to the actual situation; dTj represents the shortest distance between temperature Tj and standard temperature interval [HT1, HT2]. If temperature Tj is within the standard temperature interval [HT1, HT2], then dTj = 0. If temperature Tj is greater than the maximum value in the standard temperature interval [HT1, HT2], then dTj = Tj - HT2. If temperature Tj is less than the minimum value in the standard temperature interval [HT1, HT2], then dTj = HT1 - Tj. Similarly, dPj represents the shortest distance between power Pj and standard temperature interval [HP1, HP2]. If power Pj is within the standard power interval [HP1, HP2], then dPj = 0. If power Pj is greater than the maximum value in the standard power interval [HP1, HP2], then dPj = Pj - HP2. If power Pj is less than the minimum value in the standard power interval [HP1, HP2], then dPj = HP1 - Pj. According to the formula, the greater the shortest distance between temperature Tj and standard temperature interval [HT1, HT2], the worse the device state, and the greater the state value. The greater the shortest distance between power Pj and standard power interval [HP1, HP2], the worse the device state, and the greater the state value. The greater the amplitude and the greater the noise value, the more unstable the device operation, and the greater the state value.

[0082] Step two: a two-dimensional rectangular coordinate system is constructed with the monitoring time as the horizontal coordinate and the state value as the vertical coordinate, the state value is input into the coordinate system according to the corresponding monitoring time, and the position of the state value in the coordinate system is recorded as a state point, and the state value polyline of the equipment is obtained by connecting the state points in sequence with line segments; two adjacent state points can form a state line segment, and the state value of the two endpoints (adjacent two state points in the original state value polyline) is calculated by mean value to obtain the line segment value, denoted as The slope of the state line segment is calculated by data fitting, denoted as It should be noted that for a certain state line segment, the larger the line segment value, the greater the abnormal risk of the state of the equipment, and the larger the slope, the greater the increasing trend of the state of the equipment, which means that the abnormal risk of the equipment is increasing;

[0083] The line segment value and the slope of each state line segment are normalized and the numerical values are obtained, and the risk assessment index KU of the equipment is obtained by formula calculation and analysis of the numerical values; the specific calculation formula is:

[0084]

[0085] Wherein, α1 and α2 are proportional constants, and their specific values are set by the person skilled in the art according to actual needs; as can be seen from the formula, when the line segment value is larger, it indicates that the state of the equipment itself has an abnormal risk, and the risk assessment index of the equipment is larger; when the slope is greater than zero, if is larger, it indicates that the state value of the equipment is increasing, which means that the abnormal risk of the equipment is increasing, and the risk assessment index of the equipment is larger; when the slope is less than zero, when the absolute value of is larger, it indicates that the state value of the equipment is decreasing, which means that the abnormal risk of the equipment is decreasing, and the risk assessment index of the equipment is smaller;

[0086] Step three: the risk assessment values of the equipment are obtained, the plan layout of the plant area is obtained, and the instrument panel of each equipment is marked in the plan layout of the plant area according to its corresponding position, so that a plurality of points are obtained, and each point represents an instrument panel of an equipment, and the wheeled inspection robot needs to identify the instrument panel of each point; the point closest to the initial position of the wheeled robot is taken as the starting point, and the constraint condition of the inspection path is obtained: starting point-risk assessment value of each point-starting point; the dynamic programming is generated according to the constraint condition of the inspection path to generate the most suitable inspection route, which is:

[0087] 3-1: Heuristic function definition:

[0088] 3-1-1: Mark the starting point as P start , and mark other points as Pi, where Pi represents any one point in the plant layout, i = 1, 2, 3 … I, I is a positive integer, I represents the number of all points excluding the starting point P start , and i represents any one of the points; Specifically, generate the corresponding position coordinates as (xi, yi) according to its position in the plant layout, and the corresponding risk assessment value is marked as KUi;

[0089] 3-1-2: Mark the next point as the target point, and the next point obtained by the current point's inspection path planning (i.e. the target point) can dynamically plan the dashboard identification path of the wheeled inspection robot, specifically:

[0090] The straight-line distance between the current point Pi and the target point P target is calculated by the Euclidean distance formula, and the specific Euclidean distance formula is: Where (x target , y target ) is the position coordinates of the target point (i.e. the next point of the current wheeled inspection robot);

[0091] 3-1-3: In order to integrate device risk into heuristic search, a heuristic function is defined to calculate the weighted distance, and the specific calculation formula of the weighted distance is:

[0092] G risk (i) = h(i) x (1 + w x KUi)

[0093] Where w is a weight coefficient that adjusts the influence of risk on path selection, and its specific value is set by personnel in the art, KUi is the risk assessment index of the device represented by point i; h(i) is the straight-line distance between the device and the target device, and this heuristic function will tend to select high-risk devices, and the technician can adjust w to adjust the proportion of straight-line distance and risk assessment index to the weighted distance;

[0094] 3-2: Cost function definition:

[0095] 3-2-1: Actual cost g(i): The cost from the starting point P start to the current point Pi, which usually refers to the cumulative weighted distance from the starting point P start to the current point, and the specific calculation formula is expressed as:

[0096]

[0097] where i is the position of the current point, represents the total cost from the start point to the ith point; k is the index used to accumulate the path cost, by accumulating the path cost of each point from 1 to i, the total cost from the start point to the current point i is calculated; k-1 represents the previous point of the current point k, the cost between the previous point and the current point is added to the total cost;

[0098] 3-2-2: Estimate the cost h(i): the heuristic estimate cost from the current point Pi to the target point, defined as g(i) calculated in 3-4 above;

[0099] 3-2-3: Total cost f(i): the final selected cost is the sum of the actual cost and the heuristic estimate cost, and the specific total cost calculation formula is f(i) = g(i) + G risk (i); where g(i) is the actual cost from the start point to the point Pi, G risk (i) is the heuristic estimate cost from the point Pi to the target point;

[0100] 3-3: Dynamic path planning according to the heuristic function and the cost function, specifically:

[0101] 3-3-1: Initialize an open set to store the point to be expanded, the start point P start is added to the open set, and a closed set is initialized to store the points that have been visited; for the start point P start , initialize g(P start ) = 0 and f(P start ) = G risk (P start );

[0102] 3-3-2: Expand the point, specifically:

[0103] Select the point P current with the minimum cost from the open set, that is, select argmin Pi∈openset f(i), move P current to the closed set, and for each neighboring point P current of P neighbor , perform the following operations:

[0104] If P neighbor is already in the closed set, skip; calculate the new cost from the start point P start to P neighbor , and the specific calculation formula is: g new (P neighbor ) = g(P current ) + G weightde (Pcurrent ,P neighbor );

[0105] If P neighbor is not in the closed set, or the new cost is smaller, update its cost and add it to the open set, the specific calculation formula is: f new (P neighbor )=g new (P current )+G risk (P neighbor ), update the parent point of P neighbor to P current , and thus track the path;

[0106] 3-4: If the end point P end (the specific end point and the starting point are the same point) is added to the closed set, indicating that the best path has been found, then starting from the end point, the parent point is tracked in reverse to obtain the best path; it should be noted that if the risk assessment index KUi of a device at a point is updated during the inspection process, the updated risk assessment index KUi is substituted into the heuristic function G risk (i), and 3-3 is executed to dynamically adjust the inspection path and send it to the instrument identification control module;

[0107] The state of each monitoring device is determined by collecting and analyzing the instrument parameters (such as temperature, power, amplitude, noise value, etc.) of each monitoring device to generate a risk assessment index, and the inspection path is dynamically adjusted based on the working state (risk assessment index) of the monitoring device. This method discards the traditional fixed route method and can adjust the inspection priority according to the risk assessment index of the device. The state of the device is no longer fixed, but changes constantly during the inspection process, making the inspection path more flexible and intelligent. The state value and risk assessment index of the device are integrated into the dynamic path planning algorithm. When planning the inspection path, not only the spatial position (Euclidean distance) of the device is considered, but also the health risk (risk assessment index) of the device is included in the decision-making process. According to the definition of the weighted distance and the heuristic function, high-risk devices can be dynamically selected to optimize the inspection route, so that the robot can first reach the device location that needs urgent inspection, thereby improving the inspection efficiency and response speed, and realizing flexible adjustment of the inspection strategy according to the health state of the on-site device to cope with complex on-site changes.

[0108] The instrument identification control module controls the wheeled inspection robot to identify and control the instruments of each point device based on the received best inspection route. The specific identification and control process is as follows:

[0109] After receiving the optimal inspection path, the wheeled inspection robot starts to perform the inspection task according to the planned path. The navigation system of the robot uses sensors (such as laser radar, camera, IMU, etc.) to perceive the environment in real time, ensuring smooth movement according to the planned path. During the movement, the wheeled inspection robot performs real-time path tracking and uses obstacle detection algorithms (such as SLAM) for obstacle avoidance, ensuring the correctness of the inspection path and the efficiency of the inspection.

[0110] When the wheeled inspection robot approaches the target device point, it accurately locates the device instrument panel position through the visual recognition system (such as laser radar, RGBD camera) and positioning algorithm (such as visual SLAM, GPS positioning, etc.). Upon confirming the arrival at the target point, the wheeled inspection robot performs image acquisition (this image acquisition is the acquisition of one image at each monitoring time within a monitoring window) through sensors (such as cameras, infrared sensors), and identifies the image to extract the instrument panel parameters, including temperature, power, amplitude, and noise value. Thus, the temperature, power, amplitude, and noise values of the device at each point within the monitoring window can be obtained. It should be noted that the specific duration of the monitoring window is set by the person skilled in the art according to actual needs.

[0111] The temperature, power, amplitude, and noise values are compared and analyzed with the set warning thresholds (specifically temperature warning threshold, power warning threshold, amplitude warning value, and noise warning value). Specifically, the temperature, power, amplitude, and noise values at each monitoring time within the monitoring period are respectively compared with the temperature warning threshold, power warning threshold, amplitude warning value, and noise warning value to calculate the difference. The number of differences greater than zero is counted as the temperature warning number, power warning number, amplitude warning number, and noise warning number, respectively, and is denoted as N1, N2, N3, and N4. The corresponding difference greater than zero is then calculated to obtain the temperature warning mean, power warning mean, amplitude warning mean, and noise warning mean at each monitoring time, respectively, and is denoted as M1, M2, M3, and M4. N1, N2, N3, N4, M1, M2, M3, and M4 are normalized and their values are taken, and the values are calculated and analyzed according to the formula to obtain the warning value Y of each point device. The specific calculation formula is:

[0112]

[0113] Wherein γ1, γ2, γ3, γ4 are respectively set proportional constant, the value is set by the person skilled in the art according to actual demand; the early warning value is compared with the set early warning threshold, if the early warning value is greater than or equal to the set early warning threshold, it indicates that the abnormal state of the equipment of the point is obvious, then the early warning signal is generated, and the position coordinates of the early warning point in the factory layout map are sent to the corresponding engineer;If the early warning value is less than the set early warning threshold, the equipment of the point is recorded as a monitoring equipment, and the dashboard parameters of the monitoring equipment in the monitoring window are sent to the server for saving, as the data basis for planning the next round of inspection path of the wheeled inspection robot;

[0114] The instrument parameters of each point equipment are obtained by receiving the optimal inspection route to control the dashboard identification of the wheeled inspection robot, which not only improves the pertinence of inspection, but also avoids unnecessary redundant inspection, provides adaptive path adjustment and monitoring function for the dashboard of the equipment, so that the robot can continuously and efficiently perform tasks in complex scenes;According to the instrument parameters of the dashboard, the equipment is analyzed and warned, and the equipment is triggered according to the warning;The equipment without triggering the warning is recorded as a monitoring equipment, and the corresponding instrument parameters are sent to the server for saving, as the data basis for planning the next round of inspection path of the wheeled inspection robot, which realizes rapid identification of abnormality and warning, and significantly improves the intelligent level of equipment management.

[0115] According to the embodiment of the application, as shown in Figure 2 The instrument panel identification control method based on the wheeled inspection robot is also provided, which comprises the following steps:

[0116] S1: the instrument parameters of each device are obtained by communicating with each wheeled inspection robot, and the specific instrument parameters include temperature, power, amplitude and noise value at each monitoring time in the monitoring window;

[0117] S2: the state of the monitoring equipment is analyzed based on the instrument parameters of each monitoring equipment to generate a risk assessment index, and the inspection route of the wheeled inspection robot is planned accordingly;Specifically:

[0118] S1: the instrument parameters of each device are obtained by communicating with the wheeled inspection robot, and the specific instrument parameters include temperature, power, amplitude and noise value at each monitoring time in the monitoring window;

[0119] S2: the state of each device is analyzed based on the instrument parameters at each monitoring time in the monitoring window to plan the inspection path of the wheeled robot;Specifically:

[0120] Step one: call the instrument parameters of each monitoring device, the specific instrument parameters include temperature, power, amplitude and noise value, the device corresponds to a set of standard parameters, the specific standard parameters include standard temperature interval, standard power interval;According to the instrument parameters and standard parameters, the state value of the monitoring device at each monitoring time is obtained by quantitative analysis;

[0121] Step two: take the monitoring time as the horizontal coordinate and the state value as the vertical coordinate to construct a two-dimensional rectangular coordinate system, input the state value into the coordinate system according to its corresponding monitoring time, and record the position of the state value in the coordinate system as the state point, and connect each state point in turn to obtain the state value line chart of the device;According to the state value line chart, the health trend state of the device is further analyzed to obtain the risk assessment index of the device;

[0122] Step three: the risk assessment value of several devices can be obtained, the plane layout of the plant area is obtained, and the instrument panel of each device is marked in the plane layout of the plant area according to its corresponding position, so as to obtain several point positions;The point closest to the initial position of the wheeled robot is taken as the starting point, so as to obtain the constraint condition of the inspection path: starting point-risk assessment value of each point position-starting point;According to the constraint condition of the inspection path, dynamic programming is generated to generate the best inspection route, and it is sent to the instrument identification control module;

[0123] S3: based on the received best inspection path, control the wheeled inspection robot to identify the instrument panel of each point position device to obtain the instrument parameters of each point position device, and perform early warning analysis on the device to determine whether to trigger the early warning.

[0124] The above is only an embodiment of the present application and is not used to limit the present application. For those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the scope of claims of the present application.

Claims

1. A dashboard recognition control system based on a wheeled inspection robot, characterized by, The utility model relates to a kind of intelligent planning module and instrument identification control module based on the server, wheel type inspection robot and device state monitoring system, comprising: Server, inspection intelligent planning module and instrument identification control module; Server is connected by communicating with wheeled inspection robot to obtain the instrument parameter of each device; Inspection intelligent planning module is based on the instrument parameter of each monitoring time in monitoring window to analyze and judge each device state to plan the inspection path of wheeled robot;Specifically: Step one: call the instrument parameter of each monitoring device, the specific instrument parameter includes temperature, power, amplitude and noise value, and the device corresponds a group of standard parameters, and the specific standard parameter includes standard temperature interval, standard power interval;Quantitative analysis is carried out according to instrument parameter and standard parameter to obtain the state value of monitoring device at each monitoring time; Step two: construct two-dimensional rectangular coordinate system with monitoring time as horizontal coordinate and state value as vertical coordinate, input state value into coordinate system according to its corresponding monitoring time, and record the position of state value in coordinate system as state point, and adopt line segment to connect each state point in turn to obtain the state value broken line graph of device;Further analysis is carried out on the health trend state of device according to state value broken line graph to obtain the risk assessment index of device, specifically: Two adjacent state points can constitute a state line segment, from which several state line segments can be segmented from the state value broken line graph, and the state values corresponding to the two endpoints of the state line segment are averaged to obtain a line segment value denoted as ; the slope of the state line segment is calculated by data fitting and denoted as ; The line segment values of each state line segment and slope are normalized and their values are obtained, and the values are calculated and analyzed according to a formula to obtain the risk evaluation index KU of the equipment; the specific calculation formula is: ， Wherein α1, α2 are respectively set proportion constant, and its specific value is set by the person skilled in the art according to actual demand, and J is positive integer, and J represents the total number of monitoring time; Step three: obtain the risk assessment value of several devices, obtain the plane layout of factory area, and mark the instrument panel of each device in the plane layout of factory area according to its corresponding position, so as to obtain several point positions;The point position closest to the initial position of wheeled robot is taken as starting point, so the constraint condition of inspection path is obtained: starting point-risk assessment value of each point position-starting point;Dynamic programming is generated according to the constraint condition of inspection path to generate the best inspection route, and it is sent to instrument identification control module; Instrument identification control module controls wheeled inspection robot to identify the instrument panel of the device of each point position based on the received best inspection path to obtain the instrument parameter of the device of each point position, and carries out early warning analysis on the device to determine whether to trigger early warning.

2. The instrument panel identification control system based on the wheeled inspection robot according to claim 1, characterized by, The specific process of quantitative analysis according to instrument parameter and standard parameter is as follows: Call the instrument parameter of each monitoring device, and the specific instrument parameter includes temperature, power, amplitude and noise value, and it is recorded as Tj, Pj, Dj and Zj respectively;Wherein j=1, 2, 3 …… J, J is positive integer, J represents the total number of monitoring time, and j represents the serial number of any one monitoring time;Each device corresponds a group of standard parameters, and the specific standard parameter includes standard temperature interval, standard power interval, and it is recorded as [HT1, HT2] and [HP1, HP2] respectively; Temperature Tj, power Pj, amplitude Dj, noise value Zj, standard temperature interval [HT1, HT2] and standard power interval [HP1, HP2] are normalized and the values are taken, and the values are calculated and analyzed by formula to obtain the state value Uj of device at each monitoring time, and the specific calculation formula is as follows: ， wherein a1, a2, a3, a4 are respectively set proportional constants, the values of which are set by the person skilled in the art according to the actual situation; dTj represents the shortest distance between the temperature Tj and the standard temperature interval [HT1, HT2], if the temperature Tj belongs to the standard temperature interval [HT1, HT2], then dTj = 0, if the temperature Tj is greater than the maximum value in the standard temperature interval [HT1, HT2], then dTj = Tj-HT2; if the temperature Tj is less than the minimum value in the standard temperature interval [HT1, HT2], then dTj = HT1-Tj; similarly, dPj represents the shortest distance between the power Pj and the standard temperature interval [HP1, HP2], if the power Pj belongs to the standard power interval [HP1, HP2], then dPj = 0, if the power Pj is greater than the maximum value in the standard power interval [HP1, HP2], then dPj = Pj-HP2; if the power Pj is less than the minimum value in the standard power interval [HP1, HP2], then dPj = HP1-Pj.

3. The instrument panel identification control system based on the wheeled inspection robot according to claim 2, characterized by, The dynamic programming is generated according to the constraint condition of the inspection path to generate the optimal inspection route, and the specific steps are as follows: 3-1: Adopt heuristic function definition: starting point is recorded as , the straight line distance h(i) between the current point Pi and the target point , weighted distance ; 3-2: cost function definition: actual cost g(i), estimated cost h(i) and total cost f(i); 3-3: dynamic path planning according to the heuristic function and the cost function; 3-4: If end point If the best path is found, it is added to the closed set, and the best path is traced back from the end point to the start point and sent to the instrument identification control module.

4. The instrument panel identification control system based on the wheeled inspection robot according to claim 3, characterized by, The specific process of the heuristic function definition is as follows: 3-1-1: the starting point is recorded as and other points are recorded as Pi, where Pi represents any one point in the plant layout plan, i = 1, 2, 3 … I, I is a positive integer, I represents the number of all points excluding the starting point , and i represents any one of them; Specifically, generate the corresponding position coordinates according to its position in the plant layout plan, recorded as (xi, yi), and its corresponding risk assessment value is recorded as KUi; 3-1-2: the next point is recorded as the target point, and the instrument panel recognition path of the wheeled inspection robot is obtained by performing inspection path planning on the current point, specifically: The Euclidean distance calculation formula is used to obtain the current point Pi and the target point The straight-line distance between them is calculated using the Euclidean distance formula: ,in( ) is the position coordinate of the target point; 3-1-3: a heuristic function is defined to calculate the weighted distance, and the specific calculation formula of the weighted distance is as follows: ， wherein w is a weight coefficient for adjusting the influence degree of risk on path selection, and the specific value is set by the person skilled in the art; KUi is the risk assessment index of the equipment represented by the point i; h(i) is the straight line distance between the equipment and the target equipment.

5. The instrument panel identification control system based on the wheeled inspection robot according to claim 4, characterized by, The specific process of the cost function definition is as follows: 3-2-1: Actual cost g(i): from start point to current point Pi, the specific calculation formula is expressed as: ， Wherein, i is the position of the current point, indicates that we want to calculate the total cost from the starting point to the i-th point; k is the index used to accumulate the path cost, by accumulating the path cost of each point from 1 to i, the total cost from the starting point to the current point i is calculated; k-1 indicates the index of the previous point of the current point k; represents the weighted distance between points from k-1 to point k; 3-2-2: estimated cost h(i): heuristic estimated cost of the current point Pi to the target point, defined as g(i) calculated in the above 3-4; 3-2-3: Total cost f(i): The cost of the final selection is the sum of the actual cost and the heuristic estimated cost, and the specific total cost calculation formula is f(i)=g(i)+h(i) ; wherein g(i) is the actual cost from the starting point to the point Pi, h(i) is the heuristic estimated cost from the point Pi to the target point.

6. The instrument panel identification control system based on the wheeled inspection robot according to claim 5, characterized by, The specific process of the dynamic path planning according to the heuristic function and the cost function is as follows: 3-3-1: initialize an open set to store the points to be expanded, the starting point is added to the open set, initialize a closed set to store the points that have been visited; for the starting point is initialized to: g( ) = 0 and f( ) = ; 3-3-2: expand the point, specifically: Select the point with the minimum cost from the open set , that is, select , Indicates finding the point with the minimum total cost f(i) in the open set, Move to the closed set, for Each adjacent point , do the following: If has been in the closed set, then skip; compute the new cost from the start to with the formula: ; If not in the closed set, or the new cost is smaller, then update its cost and add it to the open set, the specific formula is: , update the parent point to , thus the path can be tracked.

7. The instrument panel identification control system based on the wheeled inspection robot according to claim 1, characterized by, Based on the received optimal inspection path, the wheeled inspection robot controls the instrument panel recognition of the equipment at each point, and the specific recognition process is as follows: After receiving the optimal inspection path, the wheeled inspection robot performs the inspection task according to the planned path, and the specific inspection task is to collect and recognize the data of the instrument panel of the equipment at each point of the optimal inspection path. The navigation system of the robot uses sensors to sense the environment in real time, and the wheeled inspection robot performs path tracking and obstacle avoidance in real time during movement. When the wheeled inspection robot approaches the target device point, the device instrument panel is accurately positioned through the visual recognition system and positioning algorithm. When the target point is reached, the wheeled inspection robot collects images through sensors and identifies the images to extract the instrument panel parameters, including temperature, power, amplitude, and noise values. Thus, the temperature, power, amplitude, and noise values of each point device within the monitoring window can be obtained.

8. The instrument panel identification control system based on the wheeled inspection robot according to claim 7, characterized by, The device is analyzed for early warning based on the instrument parameters of each point device to determine whether to trigger an early warning. The specific early warning analysis process is as follows: The temperature, power, amplitude, and noise values are compared and analyzed with the set early warning thresholds. Specifically, the temperature, power, amplitude, and noise values at each monitoring time within the monitoring period are respectively calculated with the temperature early warning threshold, power early warning threshold, amplitude early warning value, and noise early warning value. The number of differences greater than zero is counted as the temperature early warning number, power early warning number, amplitude early warning number, and noise early warning number. The corresponding differences greater than zero are then calculated to obtain the temperature early warning mean, power early warning mean, amplitude early warning mean, and noise early warning mean at each monitoring time. The temperature early warning number, power early warning number, amplitude early warning number, noise early warning number, temperature early warning mean, power early warning mean, amplitude early warning mean, and noise early warning mean are normalized and their values are taken. The values are calculated and analyzed to obtain the early warning value of each point device. The early warning value is compared with the set early warning threshold. If the early warning value is greater than or equal to the set early warning threshold, an early warning signal is generated, and the location coordinates of the early warning point on the plant layout map are sent to the corresponding engineer. If the early warning value is less than the set early warning threshold, the point device is recorded as a monitoring device, and the instrument panel parameters of the monitoring device within the monitoring window are sent to the server for saving, serving as the data basis for planning the next round of inspection path of the wheeled inspection robot.

9. A dashboard identification control method based on a wheeled inspection robot, characterized by The method is applied to the instrument panel identification control system based on the wheeled inspection robot as claimed in any one of claims 1-8, and comprises the following steps: S1: Obtain the instrument parameters of each device by communicating with the wheeled inspection robot. The specific instrument parameters include temperature, power, amplitude, and noise values at each monitoring time within the monitoring period. S2: Analyze and determine the state of each device based on the instrument parameters at each monitoring time within the monitoring window to plan the inspection path of the wheeled robot. Specifically: Step one: Retrieve the instrument parameters of each monitoring device, including temperature, power, amplitude, and noise values. Each device corresponds to a set of standard parameters, including standard temperature intervals and standard power intervals. Quantitative analysis based on instrument parameters and standard parameters obtains the state value of the monitoring device at each monitoring time. Step two: a two-dimensional rectangular coordinate system is constructed with the monitoring time as the horizontal coordinate and the state value as the vertical coordinate, the state value is input into the coordinate system according to the corresponding monitoring time, and the position of the state value in the coordinate system is recorded as a state point, the state value polyline diagram of the equipment is obtained by connecting the state points in turn with line segments; the health trend state of the equipment is further analyzed according to the state value polyline diagram to obtain the risk assessment index of the equipment; Step three: a plurality of risk assessment values of the equipment are obtained, a plan layout of the plant area is obtained, and the instrument panel of each equipment is marked in the plan layout of the plant area according to the corresponding position, thereby obtaining a plurality of point positions; the point position closest to the initial position of the wheeled robot is taken as the starting point, thereby obtaining the constraint condition of the inspection path: starting point-risk assessment value of each point position-starting point; a dynamic programming is generated according to the constraint condition of the inspection path to generate the best inspection route, and the best inspection route is sent to the instrument recognition control module; S3: based on the received best inspection path, the wheeled inspection robot is controlled to identify the instrument panel of each point position equipment to obtain the instrument parameters of each point position equipment, and the equipment is analyzed for early warning to determine whether to trigger the early warning.

Images