CN116038707B - Intelligent fault automatic diagnosis system based on data driving - Google Patents
Intelligent fault automatic diagnosis system based on data driving Download PDFInfo
- Publication number
- CN116038707B CN116038707B CN202310044907.7A CN202310044907A CN116038707B CN 116038707 B CN116038707 B CN 116038707B CN 202310044907 A CN202310044907 A CN 202310044907A CN 116038707 B CN116038707 B CN 116038707B
- Authority
- CN
- China
- Prior art keywords
- mechanical arm
- preset
- operation unit
- comparison
- threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J18/00—Arms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to the field of fault diagnosis, in particular to an intelligent fault automatic diagnosis system based on data driving.
Description
Technical Field
The invention relates to the field of fault diagnosis, in particular to an intelligent automatic fault diagnosis system based on data driving.
Background
With the progress of human, the robot is widely applied in the production process, the automation and the intellectualization of the production are improved, and in the actual production process, the robot can fail due to abrasion and other reasons caused by long-time operation, so that the robot has important significance for the failure diagnosis of the robot.
Chinese patent publication No.: CN113442168A, which discloses the following matters, the invention provides a robot fault diagnosis system, comprising: the data acquisition device is arranged on the robot body and used for acquiring current and position signals of the device, and acquiring acceleration and pose of the tail end execution part; the data transmission device is used for receiving the data signals acquired by the data acquisition device and outputting the data signals to the data transmission device; the terminal equipment comprises a fault type judging module carrying a machine learning model for supervising multiple classifications, and is used for receiving the characterization vibration signals of the robot obtained by the data fed back by the data transmission device, and extracting the multiple characteristics of the robot fault characteristics of the obtained characterization vibration signals to obtain high-dimensional original data characteristics; performing feature selection on the high-dimensional original data features; reducing the dimension of the high-dimension original data characteristics to low-dimension characteristics; and classifying the low-dimensional features to obtain a fault diagnosis result. The invention improves the accuracy of fault diagnosis and solves the problems of difficult state monitoring, slow response, and too high false alarm rate or false alarm rate of the existing device.
However, the prior art has the following problems:
in the prior art, the time interval for detecting the operation condition of the mechanical arm and the judgment precision for judging whether the abnormality occurs are not considered to be adjusted according to the operation parameters of the mechanical arm, and the fault diagnosis efficiency is improved on the premise of reducing the data operand.
Disclosure of Invention
In order to solve the problem that the time interval for detecting the operation condition of the mechanical arm and the judgment precision for judging whether the abnormality occurs are not considered according to the operation parameters of the mechanical arm in the prior art, so as to improve the fault diagnosis efficiency on the premise of reducing the data operand, the invention provides an intelligent fault automatic diagnosis system based on data driving, which comprises the following components:
the robot is arranged on the production line and comprises a data receiving unit and a mechanical arm, wherein the data receiving unit is used for receiving preset mechanical arm operation parameters and controlling the mechanical arm to execute corresponding actions according to the mechanical arm operation parameters;
the detection module comprises an image acquisition unit arranged at one side of the robot so as to acquire a depth image of the mechanical arm;
the data processing module comprises an image processing unit, an action analysis unit, a first operation unit and a second operation unit which are connected with each other,
the image processing unit is connected with the detection module and is used for generating actual node three-dimensional coordinates of the nodes of the mechanical arm based on the depth image;
the action analysis unit is connected with the data receiving unit and is used for determining the running track of the node of the mechanical arm based on the preset running parameters of the mechanical arm so as to analyze and acquire the track complex condition of each running track section;
the first operation unit is connected with the data receiving unit and is used for receiving the mechanical arm operation parameters corresponding to the operation track section of the first track complex condition, generating preset node three-dimensional coordinates of the nodes of the mechanical arm correspondingly, selecting preset node three-dimensional coordinates and actual node three-dimensional coordinates one by one according to preset coordinate point comparison intervals, comparing the preset node three-dimensional coordinates with actual node three-dimensional coordinates to determine offset, and judging whether the mechanical arm has deviation according to the comparison result of the offset and a preset deviation threshold;
the second operation unit is connected with the data receiving unit and is used for receiving the mechanical arm operation parameters corresponding to the operation track section of the second track complex condition, correspondingly generating preset node three-dimensional coordinates of the node of the mechanical arm, dividing the action type of the mechanical arm based on the mechanical arm operation parameters, adjusting the coordinate point comparison interval based on the corresponding action type, comparing the preset node three-dimensional coordinates with the actual node three-dimensional coordinates one by one at the adjusted coordinate point comparison interval, determining the offset based on the comparison result, and judging whether the mechanical arm has deviation according to the comparison result of the offset and the adjusted preset deviation threshold after adjusting the preset deviation threshold according to the divided action type.
Further, the action analysis unit divides the running track into a plurality of running track sections on average, divides the running track sections into a plurality of sub-running track sections, calculates a complex characteristic parameter C according to a formula (1),
(1)
in the formula (1), K i Represents the slope, K, of the track midpoint of the ith sub-run track segment i-1 The slope of the track midpoint of the i-1 th sub-run track segment is represented, and n represents the number of sub-run track segments.
Further, the action analysis unit compares the complex characteristic parameter C with a preset first complexity comparison threshold C1, and analyzes and obtains the track complex condition of the moving track section according to the comparison result, wherein,
under a first parameter comparison result, the action analysis unit analyzes and obtains the moving track section as a first track complex condition;
under a second parameter comparison result, the action analysis unit analyzes and obtains that the moving track section is in a second track complex condition;
wherein, the first parameter comparison result is C < C1, and the second parameter comparison result is C not less than C1.
Further, the first operation unit selects three-dimensional coordinates of preset nodes one by one according to the coordinate point comparison interval and compares the three-dimensional coordinates with corresponding three-dimensional coordinates of actual nodes to calculate the offset M according to a formula (2),
(2)
in the formula (2), X0 represents an X-axis coordinate value of the three-dimensional coordinate of the selected preset node, Y0 represents a Y-axis coordinate value of the three-dimensional coordinate of the selected preset node, Z0 represents a Z-axis coordinate value of the three-dimensional coordinate of the selected preset node, X ' represents an X-axis coordinate value of the three-dimensional coordinate of the actual node, Y ' represents a Y-axis coordinate value of the three-dimensional coordinate of the actual node, and Z ' represents a Z-axis coordinate value of the three-dimensional coordinate of the actual node.
Further, the first operation unit compares the offset M with a preset deviation threshold M0, and determines whether the mechanical arm is deviated according to the comparison result, wherein,
under a first offset comparison condition, the first operation unit judges that the mechanical arm generates deviation;
under a second offset comparison condition, the first operation unit judges that the mechanical arm has no deviation;
wherein, the first offset comparison condition is M.gtoreq.M0, and the second offset comparison condition is M < M0.
Further, the second operation unit divides the action type of the mechanical arm according to the operation parameters of the mechanical arm, wherein the second operation unit calculates a complex characteristic parameter C according to a formula (1), compares the complex characteristic parameter C with a preset second complexity comparison threshold C2 and a third complexity comparison threshold C3, C1 is smaller than C2 and smaller than C3, divides the action type of the mechanical arm according to the comparison result, wherein,
under a third parameter comparison result, the second operation unit divides the action type of the mechanical arm into a first action type;
under a fourth parameter comparison result, the second operation unit divides the action type of the mechanical arm into a second action type;
under a fifth parameter comparison result, the second operation unit divides the action type of the mechanical arm into a third action type;
wherein, the third parameter comparison result is C1-C2, the fourth parameter comparison result is C2-C3, and the fifth parameter comparison result is C3-C3.
Further, the second operation unit determines an interval adjustment mode when the coordinate point comparison interval T0 is adjusted according to the action type of the mechanical arm, wherein,
the first interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a first coordinate point comparison interval value T1 according to a preset first interval adjustment parameter T1, and T1=T0+t1 is set;
the second interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a second coordinate point comparison interval value T2 according to a preset second interval adjustment parameter T2, and T2=T0+t2 is set;
the third interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a third coordinate point comparison interval value T3 according to a preset third interval adjustment parameter T3, and T3=T0+t3 is set;
the first interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a first action type, the second interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a second action type, and the third interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a third action type, T1 > T2 > T3, and T0 > T1 > T2 > T3.
Further, the second operation unit determines a threshold adjustment mode when adjusting the preset deviation threshold M0 according to the action type of the mechanical arm, wherein,
the first threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a first deviation threshold M1 according to a preset first threshold adjustment parameter M1, and m1=m0+m1 is set;
the second threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a second deviation threshold M2 according to a preset second threshold adjustment parameter M2, and m2=m0+m2 is set;
the third threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a third deviation threshold M3 according to a preset third threshold adjustment parameter M3, and m3=m0+m3 is set;
the first threshold adjustment mode needs to meet the action type of the mechanical arm as a first action type, the second threshold adjustment mode needs to meet the action type of the mechanical arm as a second action type, the third threshold adjustment mode needs to meet the action type of the mechanical arm as a third action type, M1 is more than M2 and more than M3, M0 is more than M1 and more than M2 and more than M3, and M0 represents an initial preset deviation threshold.
Further, the second operation unit selects preset node three-dimensional coordinates and actual node three-dimensional coordinates one by one according to the adjusted coordinate point comparison interval to compare, calculates an offset M according to a formula (2), compares the offset M with an ith deviation threshold Mi, i=1, 2,3, and judges whether the mechanical arm has deviation according to a comparison result,
under a third offset comparison condition, the second operation unit judges that the mechanical arm generates deviation;
under a fourth offset comparison condition, the second operation unit judges that the mechanical arm has no deviation;
wherein, the third offset comparison condition is M.gtoreq.Mi, and the fourth offset comparison condition is M < Mi.
Further, the first operation unit and the second operation unit are connected with an external warning unit, so that the warning unit gives out warning when the first operation unit and the second operation unit judge that the mechanical arm has deviation.
Compared with the prior art, the method comprises the steps of setting the robot, the detection module and the data processing module, wherein the data processing module receives the mechanical arm operation parameters of the operation track section of the first track complex condition, and conducts coordinate comparison one by one at preset coordinate point comparison intervals to determine the offset, so as to judge whether the mechanical arm is abnormal, and receives the mechanical arm operation parameters of the operation track section of the second track complex condition, and divides the action types of the mechanical arm, adjusts the coordinate point comparison intervals and preset deviation threshold according to the corresponding action types, conducts coordinate comparison one by one at the adjusted coordinate point comparison intervals, and compares the offset with the adjusted preset deviation threshold to judge whether the mechanical arm is abnormal.
In particular, in the invention, the data processing module calculates complex characteristic parameters of the running track sections of the nodes of the mechanical arm, the track complex condition of each running track section is judged according to the complex characteristic parameters, the complex characteristic parameters are calculated by the sum of slope change amounts of a plurality of adjacent sub-running track sections divided by the running track sections, in the actual situation, the larger the sum of the slope change amounts of the plurality of adjacent sub-running track sections is, the more bending change conditions of the running track sections are indicated, namely the more complex the mechanical arm running parameters for generating the running track sections are indicated, the complex condition of the mechanical arm running parameters is quantified scientifically through the complex characteristic parameters, the data operation is reliable, and the reliability of the whole system is improved. .
Particularly, in the invention, when the operation parameters of the mechanical arm are in a second complex track condition, the data processing module divides the action types of the mechanical arm according to the operation parameters of the mechanical arm, in the actual situation, when the operation parameters of the mechanical arm are more complex, the mechanical arm is easier to generate operation deviation in the actual operation process, so that the operation types of the mechanical arm are divided through the operation parameters of the mechanical arm in the second complex track condition, the complex condition of the operation parameters of the mechanical arm in the second complex track condition is further divided, coordinate point comparison intervals and preset deviation thresholds are correspondingly adjusted, and further, the coordinate point comparison intervals and the preset deviation thresholds are correspondingly adjusted, so that the data operation amount is reduced, the operation load of a system is reduced, the reliability of the system is ensured, the fault judgment precision is ensured, and the erroneous judgment is reduced on the premise that the reliability is ensured.
Particularly, in the invention, the data processing module adjusts the coordinate point comparison interval based on the corresponding action type, in the actual situation, the more complex the action type of the mechanical arm is, the greater the probability of the mechanical arm running deviation in the running process is, so that the coordinate point comparison interval during comparison needs to be reduced in order to avoid missing the judgment of the deviation in the running process of the mechanical arm, and the fault diagnosis effect is ensured.
Particularly, in the invention, the data processing module adjusts the preset deviation threshold according to the corresponding action type, in the actual situation, the deviation threshold when the deviation is determined for the more complex action type of the mechanical arm is smaller, when the deviation is higher than the deviation threshold, the mechanical arm is determined to have deviation, the accuracy of the determination is improved by reducing the deviation threshold, the condition that the mechanical arm has deviation in the operation process is found in time, and the operation effect of the whole operation track of the mechanical arm is ensured.
Drawings
FIG. 1 is a schematic diagram of an intelligent automatic fault diagnosis system based on data driving according to an embodiment of the invention;
fig. 2 is a schematic diagram of a data processing module according to an embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1 and 2, fig. 1 is a schematic structural diagram of an intelligent fault automatic diagnosis system based on data driving according to an embodiment of the invention, and fig. 2 is a schematic structural diagram of a data processing module according to an embodiment of the invention, where the intelligent fault automatic diagnosis system based on data driving of the invention includes:
the robot is arranged on the production line and comprises a data receiving unit and a mechanical arm, wherein the data receiving unit is used for receiving preset mechanical arm operation parameters and controlling the mechanical arm to execute corresponding actions according to the mechanical arm operation parameters;
the detection module comprises an image acquisition unit arranged at one side of the robot so as to acquire a depth image of the mechanical arm;
the data processing module comprises an image processing unit, an action analysis unit, a first operation unit and a second operation unit which are connected with each other,
the image processing unit is connected with the detection module and is used for generating actual node three-dimensional coordinates of the nodes of the mechanical arm based on the depth image;
the action analysis unit is connected with the data receiving unit and is used for determining the running track of the node of the mechanical arm based on the preset running parameters of the mechanical arm so as to analyze and acquire the track complex condition of each running track section;
the first operation unit is connected with the data receiving unit and is used for receiving the mechanical arm operation parameters corresponding to the operation track section of the first track complex condition, generating preset node three-dimensional coordinates of the nodes of the mechanical arm correspondingly, selecting preset node three-dimensional coordinates and actual node three-dimensional coordinates one by one according to preset coordinate point comparison intervals, comparing the preset node three-dimensional coordinates with actual node three-dimensional coordinates to determine offset, and judging whether the mechanical arm has deviation according to the comparison result of the offset and a preset deviation threshold;
the second operation unit is connected with the data receiving unit and is used for receiving the mechanical arm operation parameters corresponding to the operation track section of the second track complex condition, correspondingly generating preset node three-dimensional coordinates of the node of the mechanical arm, dividing the action type of the mechanical arm based on the mechanical arm operation parameters, adjusting the coordinate point comparison interval based on the corresponding action type, comparing the preset node three-dimensional coordinates with the actual node three-dimensional coordinates one by one at the adjusted coordinate point comparison interval, determining the offset based on the comparison result, and judging whether the mechanical arm has deviation according to the comparison result of the offset and the adjusted preset deviation threshold after adjusting the preset deviation threshold according to the divided action type.
Specifically, the specific form of the data receiving unit is not limited, and only the function of data receiving can be completed, and the description is omitted here.
Specifically, the specific form of the data detection module is not limited, and the data detection module can be a depth camera which only needs to have the function of shooting a depth image, and is not described herein.
Specifically, the specific form of the data processing module is not limited, and the data processing module can be an external computer, and only needs to complete the functions of data receiving, data processing and data sending, which are not described herein.
Specifically, the specific form of constructing the three-dimensional coordinates of the actual node based on the depth image in the image processing unit is not limited, and a related algorithm is pre-led in the image processing unit to construct the three-dimensional coordinates of the actual node based on the depth image, which is already mature prior art, and will not be described herein.
Specifically, the operation parameters of the mechanical arm are preset, the operation parameters can comprise preset node three-dimensional coordinates corresponding to the operation track of the mechanical arm node when the operation parameters are set, and the operation analysis unit can construct the operation track in a three-dimensional coordinate system based on the preset node three-dimensional coordinates to perform data operation.
Specifically, the coordinate point comparison interval of the invention can be a number interval, and the coordinate points are selected and compared in the number corresponding to the interval.
Specifically, the action analysis unit divides the running track into a plurality of running track sections on average, divides the running track sections into a plurality of sub-running track sections, calculates a complex characteristic parameter C according to a formula (1),
(1)
in the formula (1), K i Represents the slope, K, of the track midpoint of the ith sub-run track segment i-1 The slope of the track midpoint of the i-1 th sub-run track segment is represented, and n represents the number of sub-run track segments.
Specifically, the action analysis unit compares the complex characteristic parameter C with a preset first complexity comparison threshold C1, C1 is more than 0, and analyzes and obtains the track complex condition of the running track section according to the comparison result, wherein,
under a first parameter comparison result, the action analysis unit analyzes and obtains the moving track section as a first track complex condition;
under a second parameter comparison result, the action analysis unit analyzes and obtains that the moving track section is in a second track complex condition;
wherein, the first parameter comparison result is C < C1, and the second parameter comparison result is C not less than C1.
Specifically, in the invention, the data processing module calculates complex characteristic parameters of the running track sections of the nodes of the mechanical arm, the track complex condition of each running track section is judged according to the complex characteristic parameters, the complex characteristic parameters are calculated by the sum of slope change amounts of a plurality of adjacent sub-running track sections divided by the running track sections, in the actual situation, the larger the sum of the slope change amounts of the plurality of adjacent sub-running track sections is, the more bending change conditions of the running track sections are indicated, namely the more complex the mechanical arm running parameters for generating the running track sections are indicated, the complex condition of the mechanical arm running parameters is quantified scientifically through the complex characteristic parameters, the data operation is reliable, and the reliability of the whole system is improved.
Specifically, the first operation unit selects three-dimensional coordinates of preset nodes one by one according to the coordinate point comparison interval and compares the three-dimensional coordinates with corresponding three-dimensional coordinates of actual nodes to calculate the offset M according to a formula (2),
(2)
in the formula (2), X0 represents an X-axis coordinate value of the three-dimensional coordinate of the selected preset node, Y0 represents a Y-axis coordinate value of the three-dimensional coordinate of the selected preset node, Z0 represents a Z-axis coordinate value of the three-dimensional coordinate of the selected preset node, X ' represents an X-axis coordinate value of the three-dimensional coordinate of the actual node, Y ' represents a Y-axis coordinate value of the three-dimensional coordinate of the actual node, and Z ' represents a Z-axis coordinate value of the three-dimensional coordinate of the actual node.
Specifically, the first operation unit compares the offset M with a preset deviation threshold M0, M0 is larger than 0, and judges whether the mechanical arm deviates according to the comparison result, wherein,
under a first offset comparison condition, the first operation unit judges that the mechanical arm generates deviation;
under a second offset comparison condition, the first operation unit judges that the mechanical arm has no deviation;
wherein, the first offset comparison condition is M.gtoreq.M0, and the second offset comparison condition is M < M0.
Specifically, the second operation unit divides the action type of the mechanical arm according to the operation parameters of the mechanical arm, wherein the second operation unit calculates a complex characteristic parameter C according to a formula (1), compares the complex characteristic parameter C with a preset second complexity comparison threshold C2 and a third complexity comparison threshold C3, wherein 0 < C1 < C2 < C3, divides the action type of the mechanical arm according to the comparison result,
under a third parameter comparison result, the second operation unit divides the action type of the mechanical arm into a first action type;
under a fourth parameter comparison result, the second operation unit divides the action type of the mechanical arm into a second action type;
under a fifth parameter comparison result, the second operation unit divides the action type of the mechanical arm into a third action type;
wherein, the third parameter comparison result is C1-C2, the fourth parameter comparison result is C2-C3, and the fifth parameter comparison result is C3-C3.
Specifically, in the invention, when the operation parameters of the mechanical arm are in a second complex track condition, the data processing module divides the action types of the mechanical arm according to the operation parameters of the mechanical arm, in the actual situation, when the operation parameters of the mechanical arm are more complex, the mechanical arm is easier to generate operation deviation in the actual operation process, so that the operation types of the mechanical arm are divided through the operation parameters of the mechanical arm in the second complex track condition, the complex condition of the operation parameters of the mechanical arm in the second complex track condition is further divided, coordinate point comparison intervals and preset deviation thresholds are correspondingly adjusted, and further, the coordinate point comparison intervals and the preset deviation thresholds are correspondingly adjusted, so that the data operation amount is reduced, the operation load of a system is reduced, the reliability of the system is ensured, the fault judgment precision is ensured, and the erroneous judgment is reduced on the premise that the reliability is ensured.
Specifically, the second operation unit determines an interval adjustment mode when the coordinate point comparison interval T0 is adjusted according to the action type of the mechanical arm, wherein T0 is more than 0,
the first interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a first coordinate point comparison interval value T1 according to a preset first interval adjustment parameter T1, and T1=T0+t1 is set;
the second interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a second coordinate point comparison interval value T2 according to a preset second interval adjustment parameter T2, and T2=T0+t2 is set;
the third interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a third coordinate point comparison interval value T3 according to a preset third interval adjustment parameter T3, and T3=T0+t3 is set;
the first interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a first action type, the second interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a second action type, and the third interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a third action type, T1 > T2 > T3 > 5, T0 > T1 > T2 > T3, and T0 > 10.
Specifically, in the invention, the data processing module adjusts the coordinate point comparison interval based on the corresponding action type, in the actual situation, the more complex the action type of the mechanical arm is, the greater the probability of the mechanical arm running deviation in the running process is, in order to avoid missing the judgment of the deviation in the running process of the mechanical arm, the coordinate point comparison interval during comparison needs to be reduced, and the effect of fault diagnosis is ensured.
Specifically, the second operation unit determines a threshold adjustment mode when adjusting the preset deviation threshold M0 according to the action type of the mechanical arm, wherein M0 > 0,
the first threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a first deviation threshold M1 according to a preset first threshold adjustment parameter M1, and m1=m0+m1 is set;
the second threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a second deviation threshold M2 according to a preset second threshold adjustment parameter M2, and m2=m0+m2 is set;
the third threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a third deviation threshold M3 according to a preset third threshold adjustment parameter M3, and m3=m0+m3 is set;
the first threshold adjustment mode needs to meet the action type of the mechanical arm as a first action type, the second threshold adjustment mode needs to meet the action type of the mechanical arm as a second action type, the third threshold adjustment mode needs to meet the action type of the mechanical arm as a third action type, M1 is more than M2 is more than M3 is more than 0, M0 is more than M1 is more than M2 is more than M3 is more than 0, and M0 represents an initial preset deviation threshold.
Specifically, in the invention, the data processing module adjusts the preset deviation threshold according to the corresponding action type, in the actual situation, the deviation threshold when the deviation is determined for the more complex action type of the mechanical arm is smaller, when the deviation is higher than the deviation threshold, the mechanical arm is determined to have deviation, the accuracy of the determination is improved by reducing the deviation threshold, the condition that the mechanical arm has deviation in the running process is found in time, and the running effect of the whole running track of the mechanical arm is ensured.
Specifically, the image processing unit sends the generated actual node three-dimensional coordinates of the nodes to the second operation unit under the complex condition of the second track, the second operation unit selects preset node three-dimensional coordinates and actual node three-dimensional coordinates one by one according to the adjusted coordinate point comparison interval for comparison, calculates an offset M according to a formula (2), compares the offset M with an i-th deviation threshold Mi, i=1, 2,3, judges whether the mechanical arm has deviation according to the comparison result, wherein,
under a third offset comparison condition, the second operation unit judges that the mechanical arm generates deviation;
under a fourth offset comparison condition, the second operation unit judges that the mechanical arm has no deviation;
wherein, the third offset comparison condition is M.gtoreq.Mi, and the fourth offset comparison condition is M < Mi.
Specifically, the first operation unit and the second operation unit are both connected with an external warning unit, so that the warning unit gives a warning when the first operation unit and the second operation unit judge that the mechanical arm has deviation.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
Claims (8)
1. An intelligent fault automatic diagnosis system based on data driving, comprising:
the robot is arranged on the production line and comprises a data receiving unit and a mechanical arm, wherein the data receiving unit is used for receiving preset mechanical arm operation parameters and controlling the mechanical arm to execute corresponding actions according to the mechanical arm operation parameters;
the detection module comprises an image acquisition unit arranged at one side of the robot so as to acquire a depth image of the mechanical arm;
the data processing module comprises an image processing unit, an action analysis unit, a first operation unit and a second operation unit which are connected with each other,
the image processing unit is connected with the detection module and is used for generating actual node three-dimensional coordinates of the nodes of the mechanical arm based on the depth image;
the action analysis unit is connected with the data receiving unit and is used for determining the running track of the node of the mechanical arm based on the preset running parameters of the mechanical arm so as to analyze and acquire the track complex condition of each running track section;
the first operation unit is connected with the data receiving unit and is used for receiving the operation parameters of the mechanical arm corresponding to the operation track section of the first track complex condition, correspondingly generating preset node three-dimensional coordinates of the node of the mechanical arm, selecting the preset node three-dimensional coordinates and the actual node three-dimensional coordinates one by one according to preset coordinate point comparison intervals, comparing the preset node three-dimensional coordinates with the actual node three-dimensional coordinates to determine an offset, and judging whether the mechanical arm has deviation according to the comparison result of the offset and a preset deviation threshold;
the second operation unit is connected with the data receiving unit and is used for receiving mechanical arm operation parameters corresponding to an operation track section of a second track complex condition, correspondingly generating preset node three-dimensional coordinates of a node of the mechanical arm, dividing action types of the mechanical arm based on the mechanical arm operation parameters, adjusting the coordinate point comparison interval based on the corresponding action types, comparing the preset node three-dimensional coordinates with actual node three-dimensional coordinates one by one at the adjusted coordinate point comparison interval, determining offset based on a comparison result, and judging whether the mechanical arm is deviated according to a comparison result of the offset and the adjusted preset deviation threshold after the preset deviation threshold is adjusted according to the divided action types;
the action analysis unit divides the running track into a plurality of running track sections on average, divides the running track sections into a plurality of sub-running track sections, calculates complex characteristic parameters C corresponding to the running track sections according to a formula (1),
(1)
in the formula (1), K i Represents the slope, K, of the track midpoint of the ith sub-run track segment i-1 The slope of the track midpoint of the i-1 th sub-running track segment is represented, and n represents the number of sub-running track segments;
the action analysis unit compares the complex characteristic parameter C with a preset first complexity comparison threshold C1, and analyzes and obtains the track complex condition of the moving track section according to the comparison result, wherein,
under a first parameter comparison result, the action analysis unit analyzes and obtains the moving track section as a first track complex condition;
under a second parameter comparison result, the action analysis unit analyzes and obtains that the moving track section is in a second track complex condition;
wherein, the first parameter comparison result is C < C1, and the second parameter comparison result is C not less than C1.
2. The intelligent automatic fault diagnosis system based on data driving according to claim 1, wherein the first operation unit selects three-dimensional coordinates of a preset node one by one according to a coordinate point comparison interval and compares the three-dimensional coordinates with corresponding three-dimensional coordinates of an actual node to calculate an offset M according to formula (2),
(2)
in the formula (2), X0 represents an X-axis coordinate value of the three-dimensional coordinate of the selected preset node, Y0 represents a Y-axis coordinate value of the three-dimensional coordinate of the selected preset node, Z0 represents a Z-axis coordinate value of the three-dimensional coordinate of the selected preset node, X ' represents an X-axis coordinate value of the three-dimensional coordinate of the actual node, Y ' represents a Y-axis coordinate value of the three-dimensional coordinate of the actual node, and Z ' represents a Z-axis coordinate value of the three-dimensional coordinate of the actual node.
3. The intelligent automatic fault diagnosis system based on data driving according to claim 2, wherein the first arithmetic unit compares the offset M with a preset deviation threshold M0 and determines whether the deviation of the robot arm occurs according to the comparison result, wherein,
under a first offset comparison condition, the first operation unit judges that the mechanical arm generates deviation;
under a second offset comparison condition, the first operation unit judges that the mechanical arm has no deviation;
wherein, the first offset comparison condition is M.gtoreq.M0, and the second offset comparison condition is M < M0.
4. The intelligent automatic fault diagnosis system based on data driving according to claim 3, wherein the second operation unit divides the motion type of the mechanical arm according to the operation parameters of the mechanical arm, wherein the second operation unit calculates a complex characteristic parameter C corresponding to the operation track section according to formula (1), compares the complex characteristic parameter C with a preset second complexity comparison threshold C2 and a third complexity comparison threshold C3, C1 < C2 < C3, and divides the motion type of the mechanical arm according to the comparison result, wherein,
under a third parameter comparison result, the second operation unit divides the action type of the mechanical arm into a first action type;
under a fourth parameter comparison result, the second operation unit divides the action type of the mechanical arm into a second action type;
under a fifth parameter comparison result, the second operation unit divides the action type of the mechanical arm into a third action type;
wherein, the third parameter comparison result is C1-C2, the fourth parameter comparison result is C2-C3, and the fifth parameter comparison result is C3-C3.
5. The intelligent automatic fault diagnosis system according to claim 4, wherein the second arithmetic unit determines an interval adjustment manner when the coordinate point comparison interval T0 is adjusted according to the type of motion of the robot arm, wherein,
the first interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a first coordinate point comparison interval value T1 according to a preset first interval adjustment parameter T1, and T1=T0+t1 is set;
the second interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a second coordinate point comparison interval value T2 according to a preset second interval adjustment parameter T2, and T2=T0+t2 is set;
the third interval adjustment mode is that the second operation unit adjusts the coordinate point comparison interval to a third coordinate point comparison interval value T3 according to a preset third interval adjustment parameter T3, and T3=T0+t3 is set;
the first interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a first action type, the second interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a second action type, and the third interval adjustment mode needs to meet the requirement that the action type of the mechanical arm is a third action type, T1 > T2 > T3, and T0 > T1 > T2 > T3.
6. The intelligent automatic fault diagnosis system according to claim 5, wherein the second arithmetic unit determines a threshold adjustment mode when adjusting the preset deviation threshold M0 according to the type of motion of the robot arm, wherein,
the first threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a first deviation threshold M1 according to a preset first threshold adjustment parameter M1, and m1=m0+m1 is set;
the second threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a second deviation threshold M2 according to a preset second threshold adjustment parameter M2, and m2=m0+m2 is set;
the third threshold adjustment mode is that the second operation unit adjusts the preset deviation threshold to a third deviation threshold M3 according to a preset third threshold adjustment parameter M3, and m3=m0+m3 is set;
the first threshold adjustment mode needs to meet the action type of the mechanical arm as a first action type, the second threshold adjustment mode needs to meet the action type of the mechanical arm as a second action type, the third threshold adjustment mode needs to meet the action type of the mechanical arm as a third action type, M1 is more than M2 and more than M3, M0 is more than M1 and more than M2 and more than M3, and M0 represents an initial preset deviation threshold.
7. The intelligent automatic fault diagnosis system based on data driving according to claim 6, wherein the second operation unit selects preset node three-dimensional coordinates and actual node three-dimensional coordinates one by one according to the adjusted coordinate point comparison interval to compare, calculates an offset M according to formula (2), compares the offset M with an i-th deviation threshold value Mi, i=1, 2,3, and determines whether the deviation occurs to the robot arm according to the comparison result, wherein,
under a third offset comparison condition, the second operation unit judges that the mechanical arm generates deviation;
under a fourth offset comparison condition, the second operation unit judges that the mechanical arm has no deviation;
wherein, the third offset comparison condition is M.gtoreq.Mi, and the fourth offset comparison condition is M < Mi.
8. The data-driven intelligent automatic fault diagnosis system according to claim 1, wherein the first operation unit and the second operation unit are connected with an external warning unit, so that the warning unit gives a warning when the first operation unit and the second operation unit determine that the mechanical arm is deviated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310044907.7A CN116038707B (en) | 2023-01-30 | 2023-01-30 | Intelligent fault automatic diagnosis system based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310044907.7A CN116038707B (en) | 2023-01-30 | 2023-01-30 | Intelligent fault automatic diagnosis system based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116038707A CN116038707A (en) | 2023-05-02 |
| CN116038707B true CN116038707B (en) | 2023-08-04 |
Family
ID=86127055
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310044907.7A Active CN116038707B (en) | 2023-01-30 | 2023-01-30 | Intelligent fault automatic diagnosis system based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116038707B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116277161B (en) * | 2023-05-25 | 2023-12-08 | 山东理工职业学院 | Mechanical arm dynamic deviation monitoring system based on three-dimensional model coordinates |
| CN117435998B (en) * | 2023-12-21 | 2024-03-08 | 天津博优智能科技有限公司 | Fault detection method of intelligent robot |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2322897A1 (en) * | 2009-11-11 | 2011-05-18 | Günther Battenberg | Method and device for measuring workpieces comprising a optical and mechanical coordinate measuring machine |
| CN111890371A (en) * | 2019-03-29 | 2020-11-06 | 牧今科技 | Method for verifying and updating calibration information for robot control and control system |
| JP6849262B1 (en) * | 2020-05-28 | 2021-03-24 | リンクウィズ株式会社 | Information processing method, information processing system, program |
| CN112706164A (en) * | 2020-12-18 | 2021-04-27 | 深圳市大富智慧健康科技有限公司 | Automatic correction method, device and equipment for initial pose of mechanical arm and storage medium |
| CN114029961A (en) * | 2021-12-16 | 2022-02-11 | 滁州学院 | Robot control method and system for high-precision transmission of mechanical arm |
| KR20220072331A (en) * | 2020-11-25 | 2022-06-02 | 아이둡 주식회사 | Hand eye calibration system and method |
| CN115464651A (en) * | 2022-09-22 | 2022-12-13 | 江苏睿博启创人工智能科技有限公司 | Six groups of robot object grasping system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102004026813A1 (en) * | 2004-06-02 | 2005-12-29 | Kuka Roboter Gmbh | Method and device for controlling handling devices |
-
2023
- 2023-01-30 CN CN202310044907.7A patent/CN116038707B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2322897A1 (en) * | 2009-11-11 | 2011-05-18 | Günther Battenberg | Method and device for measuring workpieces comprising a optical and mechanical coordinate measuring machine |
| CN111890371A (en) * | 2019-03-29 | 2020-11-06 | 牧今科技 | Method for verifying and updating calibration information for robot control and control system |
| JP6849262B1 (en) * | 2020-05-28 | 2021-03-24 | リンクウィズ株式会社 | Information processing method, information processing system, program |
| KR20220072331A (en) * | 2020-11-25 | 2022-06-02 | 아이둡 주식회사 | Hand eye calibration system and method |
| CN112706164A (en) * | 2020-12-18 | 2021-04-27 | 深圳市大富智慧健康科技有限公司 | Automatic correction method, device and equipment for initial pose of mechanical arm and storage medium |
| CN114029961A (en) * | 2021-12-16 | 2022-02-11 | 滁州学院 | Robot control method and system for high-precision transmission of mechanical arm |
| CN115464651A (en) * | 2022-09-22 | 2022-12-13 | 江苏睿博启创人工智能科技有限公司 | Six groups of robot object grasping system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116038707A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116038707B (en) | Intelligent fault automatic diagnosis system based on data driving | |
| CN108227634B (en) | Machine learning device, CNC device, and machine learning method | |
| US8838324B2 (en) | Monitoring and diagnosing device for working machine | |
| CN110394688B (en) | Machine tool state monitoring method based on edge calculation | |
| CN108732972B (en) | Intelligent data acquisition system for multiple robots | |
| CN109397703A (en) | A kind of fault detection method and device | |
| CN101910798B (en) | Rotary encoder comprising internal error control and method therefor | |
| CN116277161B (en) | Mechanical arm dynamic deviation monitoring system based on three-dimensional model coordinates | |
| KR20190080489A (en) | System and method for monitoring robot motion | |
| CN110290018A (en) | Information processing unit, machine learning device and system | |
| CN116621044B (en) | Intelligent auxiliary driving system and method for monorail crane | |
| JP2020155114A (en) | System and method for abnormality detection in time-varying system operation and computer-readable storage medium | |
| CN116645010A (en) | Chemical industry safety in production inspection system | |
| CN117032004A (en) | Industrial production automatic control platform based on Internet of things | |
| CN105302123A (en) | Online data monitoring method | |
| CN116902536A (en) | Intelligent deviation rectifying system of belt conveyor | |
| CN106042004B (en) | A kind of wear abrasion alarming device and method | |
| CN113298194B (en) | Data fusion method and system based on multiple sensors and storage medium | |
| CN116872206A (en) | Robot fault detection method and system based on industrial Internet | |
| CN114227701B (en) | Robot fault prediction method based on production data | |
| JP7396361B2 (en) | Abnormality determination device and abnormality determination method | |
| CN109814499A (en) | Noise producing cause estimating device | |
| CN114313307B (en) | Unmanned aerial vehicle control plane fault alarm method and device based on machine learning | |
| CN117584157B (en) | Circulation type guiding control system of industrial robot module | |
| CN109029937A (en) | A kind of mechanical arm track method for monitoring abnormality based on data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |