Method and system for monitoring feeding state of intelligent feeding robot

Abstract

The invention discloses an intelligent feeding robot feeding state monitoring method and system, and the method comprises the steps: judging whether feeding data is consistent with feeding task data or not, collecting a feeding image of an intelligent feeding robot if the feeding data is consistent with the feeding task data, determining an actual feeding boundary through analysis, analyzing the center position difference between the actual feeding boundary and an expected feeding range, and determining the feeding state of the intelligent feeding robot; if a threshold value is exceeded, the robot carries out self calibration, whether a misalignment analysis signal is generated or not is judged according to the calibrated multi-time feeding condition, if the misalignment analysis signal is generated, the feeding state is further compared and analyzed, a time-torque change data construction sequence is obtained, cross correlation and correlation analysis are carried out, and the feeding state is determined; when the torque difference is related to the feeding center deviation, the torque difference corresponding to the position difference threshold value is obtained through fitting analysis and compared with the self-calibration limit of the robot, so that whether the robot is automatically calibrated or needs to be maintained is determined, and feeding accuracy and stable operation of the robot are facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of feeding monitoring, and particularly relates to a method and system for monitoring the feeding state of an intelligent feeding robot. Background Art

[0002] With the development of automation technology, some existing intelligent feeding robots have improved the automation level of feeding to a certain extent. However, there are still some deficiencies in the feeding state monitoring of feeding robots.

[0003] In the prior art, when it is detected that the judged feeding data is consistent with the feeding task data, there is a lack of effective means to accurately monitor and timely calibrate the deviation of the feeding center position. When feeding deviation occurs, it is impossible to quickly and accurately judge the degree of deviation and its impact on the subsequent feeding process, nor can the feeding information be uploaded to the database, which is not conducive to subsequent product traceability and product quality improvement.

[0004] In the prior art, there is a lack of in-depth analysis and effective utilization of the relationship between the torque change and the feeding center deviation of the robot in different feeding states. It is impossible to optimize the feeding process and timely discover potential mechanical failure hazards according to the torque change characteristics. There are deficiencies in the reliability of robot operation and the timeliness of maintenance, and it is difficult to meet the comprehensive requirements of modern industrial production for intelligent feeding equipment with high precision, high stability and easy maintainability.

[0005] Therefore, the present invention provides a method and system for monitoring the feeding state of an intelligent feeding robot. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for monitoring the feeding state of an intelligent feeding robot, so as to solve the problems in the prior art that there is a lack of in-depth analysis and effective utilization of the relationship between the torque change and the feeding center deviation of the robot in different feeding states, it is impossible to optimize the feeding process and timely discover potential mechanical failure hazards according to the torque change characteristics, there are deficiencies in the reliability of robot operation and the timeliness of maintenance, and it is difficult to meet the comprehensive requirements of modern industrial production for intelligent feeding equipment with high precision, high stability and easy maintainability.

[0007] In a first aspect, the present invention provides a method for monitoring the feeding state of an intelligent feeding robot, including:

[0008] Step 1: The feeding robot obtains actual feeding data and compares it with the feeding task data to judge whether the feeding data is consistent with the feeding task data;

[0009] Step 2: Analyze the feeding area of the intelligent feeding robot to determine a preliminary analysis area;

[0010] Step 3: Based on the preliminary analysis area, determine the actual feeding boundary of the intelligent feeding robot;

[0011] Step 4: Conduct a position analysis on the actual feeding boundary of the intelligent feeding robot to determine the feeding center deviation, judge whether the intelligent feeding robot needs to perform self-calibration, and analyze the feeding state after calibration to judge whether a misalignment analysis signal is generated;

[0012] Step 6: If a misalignment analysis signal is generated, conduct a comparison analysis on the feeding states of the individual expected feeding ranges of the intelligent feeding robot, and combine the time-torque change data during the feeding process to construct time-torque change sequences for the target feeding state and the feeding comparison state;

[0013] Step 9: Based on the time-torque change sequences, conduct cross-correlation analysis to obtain the torque difference corresponding to the maximum state time difference, and conduct a correlation analysis on the feeding center deviation and the torque difference in all expected feeding areas to determine whether the torque difference is correlated with the feeding center deviation;

[0014] Step 7: If the torque difference is correlated with the feeding center deviation, conduct a fitting analysis on the torque difference - feeding center deviation to determine whether the intelligent robot can reduce the feeding center deviation through self-calibration. If not, the intelligent feeding robot needs to be repaired.

[0015] In a second aspect, the present invention provides a monitoring system for the feeding state of an intelligent feeding robot, including:

[0016] Material association module: The feeding robot obtains actual feeding data and compares it with the feeding task data to judge whether the feeding data is consistent with the feeding task data;

[0017] Verification and acquisition module: Collect the feeding images of the intelligent feeding robot, conduct a comparison analysis on the feeding images to determine the area where the intelligent feeding robot feeds, and use it as the preliminary analysis area;

[0018] Boundary determination module: Based on the preliminary analysis area of the feeding of the intelligent feeding robot, use the region growing method to determine the actual feeding boundary of the intelligent feeding robot;

[0019] Misalignment analysis module: Conduct a position analysis on the actual feeding boundary of the intelligent feeding robot to determine the feeding center deviation, judge whether the intelligent feeding robot needs to perform self-calibration, and analyze the feeding state after calibration to judge whether a misalignment analysis signal is generated;

[0020] Torque analysis module: If a misalignment analysis signal is generated, compare and analyze the feeding status of a single expected feeding range of the intelligent feeding robot to obtain the target feeding status and the feeding comparison status, acquire the time-torque change data during the feeding process of the intelligent feeding robot, and construct the time-torque change sequences of the target feeding status and the feeding comparison status;

[0021] Cross-analysis module: Based on the time-torque change sequences of the target feeding status and the feeding comparison status, perform cross-correlation analysis to obtain the torque difference corresponding to the maximum state time difference, and perform a correlation analysis on the feeding center deviation and the torque difference within all expected feeding areas to determine whether the torque difference is correlated with the feeding center deviation;

[0022] Calibration discrimination module: If the torque difference is correlated with the feeding center deviation, perform a fitting analysis on the torque difference - feeding center deviation to determine whether the intelligent robot can reduce the feeding center deviation through its own calibration. If not, the intelligent feeding robot needs to be repaired;

[0023] Advantages of the present invention:

[0024] 1. The intelligent feeding robot automatically determines whether the feeding data is consistent with the feeding task data, reduces the manual intervention link, realizes the automatic connection of material receiving, material issuing, and feeding, reduces the waiting time caused by poor information communication, speeds up the production rhythm, uploads the feeding information to the database, and automatically establishes the material-product association relationship, providing data support for quality traceability, inventory management, and production data analysis;

[0025] 2. With the help of multiple sensors and verification mechanisms, collect the feeding images of the intelligent feeding robot, determine the actual feeding boundary, and judge whether the robot needs to start its own calibration by analyzing the numerical difference between the actual feeding boundary and the center position of the expected feeding range. If the feeding center deviation after self-calibration is analyzed to judge whether the feeding robot needs misalignment analysis, the probability of feeding errors is effectively reduced, the stability of product quality is ensured, and the unqualified products caused by feeding mistakes are reduced.

[0026] 3. Construct and analyze the time-torque change data during the feeding process, construct the time-torque change sequences of the target feeding status and the feeding comparison status, perform cross-correlation analysis and fitting analysis, and by establishing a close correlation model between the torque difference and the feeding center deviation, it is beneficial to timely discover potential fault hazards. At the same time, according to the comparison result of the self-calibration limit of the intelligent feeding robot, it is determined whether the robot performs automatic calibration or requires professional maintenance, improving the continuity of the production process. Description of the Drawings

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0028] Figure 1 is a flowchart of a method for monitoring the feeding state of an intelligent feeding robot provided in Embodiment 1 of the present invention;

[0029] Figure 2 is a schematic diagram of the modules of a system for monitoring the feeding state of an intelligent feeding robot provided in Embodiment 3 of the present invention;

[0030] Figure 3 is a schematic diagram of the structure of a computer device provided in Embodiment 4 of the present invention. Detailed implementation manners

[0031] To enable those skilled in the art to better understand the solutions of the present invention, the following clearly and completely describes the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] Embodiment 1

[0033] Figure 1 is a flowchart of a method for monitoring the feeding state of an intelligent feeding robot provided in Embodiment 1 of the present invention. The embodiments of the present invention are applicable to the situation of monitoring the feeding of an intelligent feeding robot. The method for monitoring the feeding state of an intelligent feeding robot can be executed by a system for monitoring the feeding state of an intelligent feeding robot, which can be implemented by software and / or hardware, and can be configured in a computer device. Optionally, the computer device can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0034] As Figure 1 shown, the method for monitoring the feeding state of an intelligent feeding robot provided in the embodiments of the present invention specifically includes the following steps:

[0035] Step 1: The feeding robot obtains actual feeding data and compares it with the feeding task data to determine whether the feeding data is consistent with the feeding task data;

[0036] In some embodiments, RFID tags are installed on the material tank and the material, and a QR code identification is printed as the identification mark for the actual feeding data. The Manufacturing Execution System (MES) sends a feeding instruction to the Warehouse Management System (WMS) through an integrated interface. After receiving the instruction, the WMS sends the feeding task data to the intelligent feeding robot;

[0037] Among them, the identification marks include: the material tank number, the material number, and the material batch. The feeding task data includes: the numbers of the material to be fed and the material tank, and the feeding amount;

[0038] The intelligent feeding machine receives the feeding task data, reads the identification marks on the material and the material tank, obtains the actual feeding data, and determines whether the actual feeding data is consistent with the feeding task data;

[0039] Step 2: If the actual feeding data is consistent with the feeding task data, collect the feeding image of the intelligent feeding robot, perform comparison and analysis on the feeding image, and determine the area where the intelligent feeding robot feeds as the preliminary analysis area;

[0040] If the actual feeding data is consistent with the feeding task data, the intelligent robot starts feeding and records the feeding information. The intelligent feeding robot uploads the production information to the database;

[0041] Among them, the feeding information includes: the production batch of the material, the feeding time, the material source, and the feeding amount;

[0042] If the material to be fed and the material tank are inconsistent with the material tank specified in the feeding task, a material inconsistency signal is generated to the WMS system;

[0043] In some embodiments, an industrial camera is installed at the end of the robotic arm of the intelligent feeding robot and above the feeding port. The industrial camera is connected to the control module using a CAN bus, and the industrial camera collects the feeding image of the intelligent feeding robot;

[0044] Based on the collected feeding image of the intelligent feeding robot, preprocess the feeding image to obtain a feeding comparison image;

[0045] Among them, the feeding comparison image includes: the image before the intelligent robot feeds and the image after feeding;

[0046] It should be noted that the preprocessing of the feeding image includes: image denoising and image enhancement; the bilateral filtering algorithm is used. The bilateral filtering algorithm calculates the similarity of the surrounding pixels in the feeding image, and can better retain the edges of the image while removing noise. Image enhancement is used to expand the gray range of the feeding image to make the light and dark contrast of the feeding image more obvious;

[0047] Based on the feeding ratio comparison image, use the matchTemplate and MinMaxLoc functions of the OpenCV library to perform a preliminary comparison on the feeding ratio comparison image, and preliminarily determine the area where the intelligent feeding robot feeds, which is used as the preliminary analysis area;

[0048] Step 3: Based on the preliminary analysis area of the feeding of the intelligent feeding robot, use the region growing method to determine the actual feeding boundary of the intelligent feeding robot;

[0049] Based on the preliminary analysis area, determine the seed coordinates of the region growing method through the center coordinate algorithm;

[0050] It should be noted that the matchTemplate function in the OpenCV library uses a specific area of the image before feeding as a template, slides on the image after feeding to calculate the similarity, and obtains a result matrix. Then, the MinMaxLoc function is used to find the best matching position in this matrix, determines the position corresponding to the maximum or minimum value according to the selected similarity calculation method, and determines a region based on this position and the template size, which is used as the preliminary analysis area. Among them, the preliminary analysis area is a regular figure. A coordinate system is established for the feeding ratio comparison image to determine the position coordinates of the preliminary analysis area.

[0051] Obtain the preliminary analysis area, the gray value of each pixel point in the image and the gray value of adjacent pixel points;

[0052] Take the absolute value of the difference between the gray value of the adjacent pixel point and the gray value of the pixel point of the seed coordinates to obtain the adjacent gray difference;

[0053] Perform a ratio process on the adjacent gray difference and the gray value of the pixel point of the seed coordinates to obtain the adjacent gray ratio;

[0054] Compare the adjacent gray ratio with the preset adjacent gray ratio threshold. If the adjacent gray ratio of the adjacent pixel point is lower than the preset adjacent gray ratio threshold, it indicates that the gray values of the adjacent pixel point and the pixel point of the seed coordinates are similar, and the seed grows towards the adjacent pixel point;

[0055] If the adjacent gray ratio of the adjacent pixel point is higher than the preset adjacent gray ratio threshold, take the adjacent pixel point as the growth boundary point of the seed, and the seed stops growing at the growth boundary point;

[0056] Based on the growth boundary points, obtain all the growth boundary points of the preliminary analysis area, connect all the growth boundary points, and determine the growth boundary of the region growing method, that is, the actual feeding boundary of the intelligent robot;

[0057] The technical solution of this embodiment is as follows: The feeding robot obtains the actual feeding data, compares it with the feeding task data, and determines whether the feeding data is consistent with the feeding task data. If they are consistent, it collects the feeding image of the intelligent feeding robot, performs comparison and analysis on the feeding image, determines the area where the intelligent feeding robot feeds, and takes it as the preliminary analysis area. Based on the preliminary analysis area of the intelligent feeding robot's feeding, the region growing method is used to determine the actual feeding boundary of the intelligent feeding robot. Determining the actual feeding boundary of the intelligent feeding robot is beneficial to the subsequent monitoring of the feeding state of the intelligent feeding robot.

[0058] Embodiment 2

[0059] As Figure 1 shown, a method for monitoring the feeding state of an intelligent feeding robot further includes the following steps:

[0060] Step 4: Perform position analysis based on the actual feeding boundary of the intelligent feeding robot to determine the feeding center deviation d c , determine whether the intelligent feeding robot needs to perform self-calibration, and judge the feeding state of the intelligent feeding robot after calibration to determine whether a misalignment analysis signal is generated;

[0061] Based on the actual feeding boundary of the intelligent feeding robot, obtain the central position coordinates of the actual feeding range;

[0062] Specifically, take the area range within the actual feeding boundary as the actual feeding range and obtain the central coordinates of the actual feeding range;

[0063] Compare the central coordinates (X c , Y c ) of the actual feeding range with the central coordinates of the expected feeding range through numerical analysis to determine whether there is a deviation in the actual feeding position of the intelligent feeding machine;

[0064] It should be noted that the expected feeding range is determined by professional technicians in the field and the drawings of the production process, and the coordinates of the expected feeding range correspond to the coordinates of the actual feeding range;

[0065] Specifically, calculate the central coordinates (X t , Y t ) of the expected feeding range, and calculate the feeding center deviation d c ,

[0066] If the feeding center deviation d c is higher than the position difference threshold, it is considered that there is a deviation between the feeding center position and the expected feeding range, and the intelligent feeding robot performs self-calibration on the feeding process;

[0067] If the feeding center deviation dc If it is lower than the position difference threshold, it is considered that the deviation of the feeding center position from the expected feeding range is within the expected range, and it is still necessary to continuously monitor the change of the feeding center deviation d c ;

[0068] In some embodiments, if the feeding center deviation d c is higher than the position difference threshold, the intelligent feeding robot has a feeding calibration function, and the intelligent feeding robot can adjust its own torque and feeding angle to calibrate its own feeding;

[0069] Based on the intelligent feeding robot after its own calibration, obtain multiple feeding comparison images after the intelligent feeder is calibrated by itself, and obtain multiple feeding center deviations d c ;

[0070] Sum and average all the feeding center deviations d c to obtain the average center difference;

[0071] Perform a difference process on the average center difference and the position difference threshold, and then perform a ratio process on the obtained result and the position difference threshold to obtain the position deviation ratio;

[0072] Obtain the number of feeding times when the feeding center deviation d c is higher than the position difference threshold and the total number of feeding times during multiple feedings of the intelligent feeder;

[0073] It should be noted that for multiple feedings of the intelligent feeder, the number of feeding times when the feeding center deviation d c is higher than the position difference threshold is for the feeding analysis of the intelligent feeding robot in a single feeding area;

[0074] Perform a ratio process on the number of feeding times when the feeding center deviation d c is higher than the position difference threshold and the total number of feeding times to obtain the feeding misalignment ratio;

[0075] Based on the position deviation ratio and the feeding misalignment ratio, calculate the feeding misalignment value through the summation formula;

[0076] If the feeding misalignment value is higher than the misalignment threshold, it indicates that the feeding after the self-calibration of the intelligent feeding robot deviates from the expected range, and it is necessary to generate a misalignment analysis signal;

[0077] If the feeding misalignment value is lower than the misalignment threshold, it indicates that the feeding after the self-calibration of the intelligent feeding robot deviates within the expected range, and it is still necessary to continuously monitor the change of the feeding misalignment value;

[0078] It should be noted that the position deviation ratio reflects the degree of the average position deviation relative to the position difference threshold. When the position deviation ratio is high, it indicates that the degree of deviation of the feeding center position from the expected position is large. The feeding misalignment ratio reflects the proportion of the number of feeding times with the feeding center deviation higher than the position difference threshold in the total number of feeding times. When the feeding misalignment ratio is very high, for example, the feeding misalignment ratio Sz = 0.8, it means that the center position differences of most feedings (80%) are higher than the position difference threshold, which indicates that large deviations often occur in the feeding position and the stability of feeding is very poor;

[0079] Step Five: If a misalignment analysis signal is generated, compare and analyze the feeding states within a single expected feeding range to obtain the target feeding state and the feeding comparison state, obtain the time-torque change data during the feeding process of the intelligent feeding robot, and construct the time-torque change sequences of the target feeding state and the feeding comparison state;

[0080] Based on the misalignment analysis signal, obtain the feeding state within a single expected feeding range where the feeding center position of the intelligent feeding robot does not deviate from the expected feeding range, and mark it as the target feeding state;

[0081] Select the feeding state corresponding to the maximum value of the feeding center position difference d c in the feeding deviation sequence as the feeding comparison state;

[0082] Obtain the change data of the torque of the intelligent feeding robot during the feeding process corresponding to the target feeding state and the feeding comparison state, and construct the time-torque change sequences of the target feeding state and the feeding comparison state;

[0083] It should be noted that the change data of the torque of the intelligent feeding robot is obtained from the working log of the intelligent feeding robot;

[0084] Mark the time-torque change sequence of the target feeding state as M j (t) = {m 1 , m 2 ,... m z};

[0085] Mark the time-torque change sequence of the feeding comparison state as L j (t), L j (t) = {l 1 , l 2 ,... l z}, where j is the number of the time sampling point and z is the total number of the time sampling points;

[0086] For the time-torque change sequences M j (t), L j(t), perform normalization processing through the Min-Max normalization method;

[0087] Construct the time-torque change sequence M of the normalized target feeding state j ′, and construct the time-torque change sequence L of the normalized target feeding state j ′;

[0088] Step six: Based on the time-torque change sequences M j ′, L j ′ of the target feeding state and the feeding comparison state, perform cross-correlation analysis to obtain the torque difference corresponding to the maximum state time difference between the target feeding state and the feeding comparison state, and perform correlation analysis on the feeding center deviation and the torque difference within all expected feeding regions to determine whether the torque difference is correlated with the feeding center deviation;

[0089] Based on the time-torque change sequences M j ′, L j ′ of the target feeding state and the feeding comparison state, the cross-correlation function R ML (ψ), where ψ is the time difference between the target feeding state and the feeding comparison state, marked as the state time difference;

[0090] Through the cross-correlation function formula: Obtain the cross-correlation function R ML (ψ) at the state time difference, where T is the time mean of the time-torque change sequences M j ′, L j ′ of the target feeding state and the feeding comparison state;

[0091] Through the formula: ψ max = argmax ψ R ML (ψ) to obtain the state time difference ψ when R ML (ψ) reaches the maximum value max ;

[0092] It should be noted that R ML (ψ) is used to measure the correlation between the time-torque change sequence of the target feeding state and the time-torque change sequence of the feeding comparison state. At different state time differences, R ML (ψ) can reflect the similarity degree of the two sequences on the time axis;

[0093] Obtain the torque values of the time-torque change sequences of the target feeding state and the feeding comparison state corresponding to the maximum state time difference ψ max within a single expected feeding range, and perform difference processing on the torque values of the time-torque change sequences of the target feeding state and the feeding comparison state to obtain the torque difference;

[0094] Obtain the torque difference of all the feeding areas of the intelligent feeding robot, and construct a torque difference sequence in ascending order of the torque difference;

[0095] Mark the torque difference as Nc h , and the torque difference sequence is Nc = [nc 1 , nc 2 ,..., nc n , where h is the number of data elements and n is the maximum value of the numbers;

[0096] Obtain the feeding center deviation dc corresponding to the torque difference h , and construct a feeding deviation sequence Dc, Dc = [dc 1 , dc 2 ,..., dc n ;

[0097] Calculate the Pearson correlation coefficient r between the torque difference sequence and the feeding deviation sequence, and the value range of r is [-1, 1];

[0098] If the Pearson correlation coefficient between the torque difference sequence and the feeding deviation sequence is within the range of [0.8, 1], it is considered that the torque difference and the feeding center deviation are correlated; otherwise, they are not correlated;

[0099] Step 7: If the torque difference and the feeding center deviation are correlated, perform a fitting analysis on the torque difference - feeding center deviation to determine whether the intelligent robot can reduce the feeding center deviation through self - calibration. If not, the intelligent feeding robot needs to be repaired;

[0100] If the torque difference and the feeding center deviation are correlated, with the torque difference as the X - axis and the feeding center deviation as the Y - axis, establish a scatter plot of the torque difference - feeding center deviation in a two - dimensional rectangular coordinate system;

[0101] Use the least - squares method to fit the scatter plot of the torque difference - feeding center deviation, and draw a fitting line in the scatter plot of the torque difference - feeding center deviation;

[0102] Obtain the goodness of fit of the fitting line. If the goodness of fit is within the range of [0.75, 1], it is considered that the fitting effect of the fitting line meets the expectation; otherwise, it does not meet the expectation;

[0103] Taking the position difference threshold as a reference value, draw a reference line in the two - dimensional rectangular coordinate system, intersect it with the fitting line, and obtain the abscissa of the intersection point to get the torque difference corresponding to the position difference threshold;

[0104] If the torque difference corresponding to the position difference threshold does not exceed the torque automatic calibration limit of the intelligent feeding robot, the intelligent robot cannot reduce the feeding center deviation through its own calibration, and the intelligent feeding robot performs automatic calibration until the feeding center deviation of the intelligent feeding robot is lower than the position difference threshold;

[0105] If the torque difference corresponding to the position difference threshold exceeds the torque calibration limit of the intelligent feeding robot, and after multiple self-calibrations, the feeding center deviation of the intelligent feeding robot is still higher than the position difference threshold, the intelligent feeding robot needs to be repaired;

[0106] It should be noted that the self-calibration limit of the intelligent feeding robot is determined by the specification parameters of the intelligent feeding robot.

[0107] The technical solution of this embodiment is: based on the actual feeding boundary of the intelligent feeding robot, position analysis is performed to determine the feeding center deviation d c , determine whether the intelligent feeding robot needs to perform self-calibration, and judge the feeding state of the intelligent feeding robot after calibration, determine whether a misalignment analysis signal is generated. If a misalignment analysis signal is generated, compare and analyze the feeding states within a single expected feeding range to obtain the target feeding state and the feeding comparison state, obtain the time-torque change data during the feeding process of the intelligent feeding robot, and construct the time-torque change sequences M j ′, L j ′ of the target feeding state and the feeding comparison state. Based on the time-torque change sequences M j ′, L j ′ of the target feeding state and the feeding comparison state, perform cross-correlation analysis to obtain the torque difference corresponding to the maximum state time difference between the target feeding state and the feeding comparison state. In the area of all expected feedings, perform correlation analysis on the feeding deviation sequence and the torque difference sequence to determine whether the torque difference is correlated with the feeding center deviation. If the torque difference is correlated with the feeding center deviation, perform fitting analysis on the torque difference - feeding center deviation. If the torque difference corresponding to the position difference threshold does not exceed the self-calibration limit of the feeding robot, the intelligent feeding robot performs self-calibration until the feeding center deviation of the self-calibrated intelligent feeding robot is lower than the position difference threshold.

[0108] Embodiment III

[0109] As Figure 2 shown, an intelligent feeding robot feeding state monitoring system includes:

[0110] Material association module: The feeding robot obtains actual feeding data and compares it with the feeding task data to judge whether the feeding data is consistent with the feeding task data;

[0111] Verification and acquisition module: Acquire the feeding images of the intelligent feeding robot, perform comparison and analysis on the feeding images, and determine the feeding area of the intelligent feeding robot as the preliminary analysis area;

[0112] Boundary determination module: Based on the preliminary analysis area of the feeding of the intelligent feeding robot, use the region growing method to determine the actual feeding boundary of the intelligent feeding robot;

[0113] Misalignment analysis module: Perform position analysis on the actual feeding boundary of the intelligent feeding robot to determine the feeding center deviation d c , determine whether the intelligent feeding robot needs to perform self-calibration, and analyze the feeding state after calibration to determine whether a misalignment analysis signal is generated;

[0114] Torque analysis module: If a misalignment analysis signal is generated, perform comparison and analysis on the feeding states of individual expected feeding ranges of the intelligent feeding robot to obtain the target feeding state and the feeding comparison state, obtain the time-torque change data during the feeding process of the intelligent feeding robot, and construct the time-torque change sequences of the target feeding state and the feeding comparison state;

[0115] Cross-analysis module: Based on the time-torque change sequences of the target feeding state and the feeding comparison state, and perform cross-correlation analysis to obtain the torque difference corresponding to the maximum state time difference, and perform correlation analysis on the feeding center deviation and the torque difference within all expected feeding areas to determine whether the torque difference is correlated with the feeding center deviation;

[0116] Calibration discrimination module: If the torque difference is correlated with the feeding center deviation, perform fitting analysis on the torque difference - feeding center deviation to determine whether the intelligent robot can reduce the feeding center deviation through self-calibration. If not, the intelligent feeding robot needs to be repaired;

[0117] Embodiment 4

[0118] Refer to Figure 3 , the embodiment of the present invention also provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements an intelligent feeding robot feeding state monitoring method as described in any one of the above methods.

[0119] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand, Figure 3The computer device 3 is only an example and does not limit the computer device 3. It may include more or fewer components than those shown in the figure, or combine some components, or different components. For example, it may also include input and output devices, network access devices, etc.

[0120] The so-called processor 301 may be a central processing unit (CPU). This processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0121] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In some other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk equipped on the computer device 3, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or will be output.

[0122] Embodiment Five

[0123] The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements an intelligent feeding robot feeding state monitoring method as described in any one of the above methods.

[0124] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the method of the above embodiment in the present application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0125] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0126] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0127] In the embodiments disclosed in the present application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0128] The unit described as a separating component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed over multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0129] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0130] The above has described in detail an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A method for monitoring feeding status of an intelligent feeding robot, characterized in that: The steps include: Obtain misalignment analysis signals, compare and analyze the feeding status of a single expected feeding range of the intelligent feeding robot, and combine the time-torque change data during the feeding process to construct the time-torque change sequence of the target feeding status and the feeding comparison status; Based on the time-torque change sequence, a cross-correlation analysis is performed to obtain the torque difference corresponding to the maximum state time difference. A correlation analysis is performed on the torque difference in combination with the feeding center deviation of all expected feeding areas to determine whether the torque difference is correlated with the feeding center deviation. If the torque difference is correlated with the feeding center deviation, a fitting analysis of the torque difference-feeding center deviation is performed to determine whether the intelligent robot can reduce the feeding center deviation through self-calibration.

2. The method for monitoring feeding status of an intelligent feeding robot according to claim 1, characterized in that: The misalignment analysis signal is generated in the following manner: Obtain actual feeding data and determine whether the feeding data is consistent with the feeding task data. If they are consistent, determine the preliminary analysis area for the intelligent robot to feed; Based on the preliminary analysis area, determine the actual feeding boundary of the intelligent feeding robot; Perform position analysis on the actual feeding boundary of the intelligent feeding robot, determine the feeding center deviation, judge whether the intelligent feeding robot needs to calibrate itself, and analyze the feeding status after calibration to obtain the feeding misalignment value. Generate a misalignment analysis signal based on the feeding misalignment value.

3. The method for monitoring feeding status of an intelligent feeding robot according to claim 2, characterized in that: The actual feeding boundary is obtained as follows: Based on the preliminary analysis area, the region growing method is used to determine the actual feeding boundary.

4. The method for monitoring feeding status of an intelligent feeding robot according to claim 2, characterized in that: The method for obtaining the feeding misalignment value is as follows: Based on the self-calibrated intelligent feeding robot, the feeding center deviation of the intelligent feeding machine after multiple feedings; All feeding center deviations are summed and averaged to obtain the center difference mean; Perform difference processing on the center difference mean and the position difference threshold, and then perform ratio processing on the result and the position difference threshold to obtain the position deviation ratio; The feeding times when the feeding center deviation is higher than the position difference threshold are compared with the total feeding times to obtain the feeding misalignment ratio; Based on the position deviation ratio and the feeding misalignment ratio, the feeding misalignment value is obtained by summing them up.

5. The method for monitoring feeding status of an intelligent feeding robot according to claim 1, characterized in that: The method for obtaining the time-torque variation sequence of the target feeding state and the feeding comparison state is as follows: Obtain the torque change data of the intelligent feeding robot during the feeding process corresponding to the target feeding state and the feeding comparison state of the intelligent feeding robot, and construct the time-torque change sequence of the target feeding state and the feeding comparison state; The time-torque change sequence of the target feeding state and the feeding comparison state is normalized to construct the time-torque change sequence of the target feeding state.

6. The method for monitoring feeding status of an intelligent feeding robot according to claim 5, characterized in that: The target feeding state is obtained as follows: Obtain the feeding state in which the feeding center position of the intelligent feeding robot does not deviate from the expected feeding range within a single expected feeding range, and mark it as the target feeding state.

7. The method for monitoring feeding status of an intelligent feeding robot according to claim 1, characterized in that: The method for judging whether the torque difference is correlated with the feeding center deviation is as follows: Sort the torque differences of all feeding areas and construct a torque difference sequence; Obtain the feeding center deviation corresponding to the torque difference and construct a feeding deviation sequence; Calculate the Pearson correlation coefficient r between the torque difference series and the feeding deviation series; If the Pearson correlation coefficient of the torque difference sequence and the feeding deviation sequence is within the expected range, it is considered that the torque difference is correlated with the feeding center deviation.

8. The method for monitoring feeding status of an intelligent feeding robot according to claim 7, characterized in that: The method for obtaining the torque difference corresponding to the maximum value of the state time difference between the target feeding state and the feeding comparison state is: Based on the time-torque change sequence of the target feeding state and the feeding comparison state, a cross-correlation analysis is performed to obtain the torque value of the target feeding state and the feeding comparison state time-torque change sequence corresponding to the maximum state time difference within a single expected feeding range; The torque values ​​of the target feeding state and the feeding comparison state time-torque change sequence are subjected to difference processing to obtain the torque difference.

9. The method for monitoring feeding status of an intelligent feeding robot according to claim 1, characterized in that: The method for judging whether the intelligent robot can reduce the feeding center deviation through self-calibration is as follows: The fitting straight line is analyzed with the position difference threshold to obtain the torque difference corresponding to the position difference threshold; If the torque difference corresponding to the position difference threshold exceeds the torque calibration limit of the intelligent feeding robot, and after multiple self-calibrations, the feeding center deviation of the intelligent feeding robot is still higher than the position difference threshold, the intelligent robot cannot reduce the feeding center deviation through self-calibration.

10. An intelligent feeding robot feeding status monitoring system, used to implement an intelligent feeding robot feeding status monitoring method according to any one of claims 1 to 9, characterized in that: include: Torque analysis module: If the misalignment analysis signal is generated, the feeding state of a single expected feeding range of the intelligent feeding robot is compared and analyzed, and the time-torque change sequence of the target feeding state and the feeding comparison state is constructed in combination with the time-torque change data during the feeding process; Cross-analysis module: Based on the time-torque change sequence, cross-correlation analysis is performed to obtain the torque difference corresponding to the maximum state time difference, and correlation analysis is performed on the feeding center deviation and the torque difference to determine whether the torque difference is correlated with the feeding center deviation; Calibration judgment module: If there is a correlation, a fitting analysis is performed on the torque difference-feeding center deviation to determine whether the intelligent robot can reduce the feeding center deviation through its own calibration. If not, the intelligent feeding robot needs to be repaired.

Images