CN115648644A - Self-adaptive press fitting device and method based on vision - Google Patents
Self-adaptive press fitting device and method based on vision Download PDFInfo
- Publication number
- CN115648644A CN115648644A CN202211178412.5A CN202211178412A CN115648644A CN 115648644 A CN115648644 A CN 115648644A CN 202211178412 A CN202211178412 A CN 202211178412A CN 115648644 A CN115648644 A CN 115648644A
- Authority
- CN
- China
- Prior art keywords
- press
- fitting
- mounting
- feeding
- force
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 198
- 230000008569 process Effects 0.000 claims abstract description 165
- 238000006073 displacement reaction Methods 0.000 claims abstract description 97
- 230000002159 abnormal effect Effects 0.000 claims abstract description 52
- 238000010438 heat treatment Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 15
- 239000000463 material Substances 0.000 claims description 13
- 238000013135 deep learning Methods 0.000 claims description 12
- 230000002441 reversible effect Effects 0.000 claims description 5
- 239000000654 additive Substances 0.000 claims 1
- 230000000996 additive effect Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 23
- 238000012545 processing Methods 0.000 description 13
- 238000013473 artificial intelligence Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 241000282414 Homo sapiens Species 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000010801 machine learning Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 238000003825 pressing Methods 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000001965 increasing effect Effects 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000010720 hydraulic oil Substances 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Automatic Assembly (AREA)
Abstract
The invention relates to the technical field of press-mounting equipment, and provides a vision-based self-adaptive press-mounting device and a method, wherein a press-mounting process parameter and a reference press-mounting force-displacement curve are obtained by establishing a press-mounting parameter determination model, press-mounting is executed according to the press-mounting process parameter, and the press-mounting process is monitored in real time; comparing the real-time press-fitting force-displacement curve with a reference press-fitting force-displacement curve, and determining whether the press-fitting process is abnormal or not by acquiring a press-fitting image of the track pin in the press-fitting process; adjusting the press-mounting technological parameters in real time according to the abnormal data; the press fitting system is monitored in real time, and the probability of workpiece damage or personnel damage caused by overlarge pressure is greatly reduced; the intelligent decision-making press-fitting mode and the multidirectional analysis of press-fitting quality are realized, and the press-fitting method is suitable for the scene of the interference press-fitting of the rubber bushing with complex press-fitting conditions.
Description
Technical Field
The invention relates to the technical field of press-fitting equipment, in particular to a self-adaptive press-fitting device and method based on vision.
Background
The current mainstream press-fitting process uses a hydraulic oil cylinder or a servo electric cylinder as a power source, and executes press-fitting action according to a preset press-fitting in-place signal; wherein, the signal of pressure equipment in place realizes through mechanical spacing or servo good stroke of setting for. That is to say, the traditional press-fitting system carries out press-fitting according to the fixed technological parameters set in advance by a press, is a simplified mechanical execution flow, and has the following disadvantages:
because the traditional press-fitting process adopts fixed process parameters, the shaft diameters of the rubber bushings are randomly distributed within a certain error range; moreover, the change of temperature has great influence on the viscosity, elasticity and size of the rubber; therefore, if the same process parameters (such as overpressure displacement, back pressure displacement and press-fitting speed) are adopted for different working conditions, the phenomenon that the pressing-in size of the rubber bushing is not proper can be caused, and even the rubber bushing is broken down in a serious condition.
Therefore, a self-adaptive press-fitting device and method capable of adjusting press-fitting parameters in real time according to press-fitting quality are needed.
Disclosure of Invention
The invention provides a vision-based self-adaptive press fitting device and method, which aim to solve the technical problem that press fitting parameters cannot be adjusted in real time according to press fitting abnormity in the prior art.
In order to achieve the purpose, the invention provides a vision-based self-adaptive press-fitting device which comprises a feeding unit, a feeding image acquisition unit, a press-fitting image acquisition unit, a rubber bushing end face image acquisition unit and a control unit, wherein the feeding unit is arranged on the feeding unit; wherein,
the feeding unit is used for feeding the track pins one by one to the feeding unit and comprises a track pin feeding frame used for bearing the track pins;
the feeding unit is used for conveying the track pin to the press-fitting unit and comprises a feeding track, a heating plate arranged below the feeding track and a temperature sensor arranged on the heating plate;
the feeding image acquisition unit is used for acquiring an axle diameter image of the track pin in the feeding process and is arranged above the feeding track;
the press-mounting unit is used for press-mounting the rubber bushing on the track pin at the press-mounting position of the track pin and comprises a main piezoelectric cylinder and a back piezoelectric cylinder which are respectively arranged at two ends of the press-mounting position of the track pin; the press-fitting device also comprises a force sensor for acquiring press-fitting force and a displacement sensor for acquiring press-fitting displacement;
the press-fitting image acquisition unit is used for acquiring press-fitting images of the crawler pins in the press-fitting process and is arranged above the press-fitting positions of the crawler pins;
the rubber bushing end face image acquisition unit is used for acquiring the pressed rubber bushing end face image and sending the rubber bushing end face image to the control unit;
the control unit is used for receiving the shaft diameter image of the track pin acquired by the feeding image acquisition unit, the temperature acquired by the temperature sensor and the press-mounting image of the track pin acquired by the press-mounting image acquisition unit, determining press-mounting process parameters and controlling the main piezoelectric cylinder and the back piezoelectric cylinder to complete press-mounting work of the rubber bushing of the track pin according to the press-mounting process parameters; and judging whether the press fitting process is abnormal or not according to the press fitting image of the crawler pin and the pressed end face image of the rubber bushing, and adjusting the press fitting process parameters in real time according to abnormal data of the press fitting process.
Further, it is preferable that the rubber bushing end face image capturing unit includes a robot arm for adjusting a shooting angle of the rubber bushing end face of the crawler pin and a high-speed camera for shooting a rubber bushing end face image of the crawler shoe.
Further, the preferable structure is that the control unit comprises a shaft diameter and assembly temperature data determining module, a process parameter determining module and a press-fitting executing module; wherein,
the shaft diameter and assembly temperature determining module is used for acquiring a shaft diameter image of the track pin in the feeding process so as to determine the shaft diameter of the track pin; the temperature acquisition device is used for acquiring the temperature of the heating plate as the assembly temperature;
the process parameter determining module is used for determining a model by using the press-mounting parameters according to the shaft diameter of the track pin, the assembly temperature and the material parameters of the track pin, and acquiring press-mounting process parameters and a reference press-mounting force-displacement curve;
the press-fitting execution module is used for carrying out forward press-fitting on the rubber bushing on the track pin by using the main piezoelectric cylinder according to press-fitting technological parameters when the track pin reaches a press-fitting station; meanwhile, the press-fitting force and the press-fitting stroke of the press-fitting unit and the press-fitting image of the crawler pin in the press-fitting process are collected; generating a real-time press-fitting force-displacement curve according to the press-fitting force and the press-fitting stroke;
judging whether the press mounting process is abnormal or not according to the judgment whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not; judging whether the press mounting process is damaged or not according to the press mounting image of the track pin in the press mounting process;
if the real-time press-fitting force-displacement curve is inconsistent with the reference press-fitting force-displacement curve and/or if the press-fitting process is damaged, judging that the press-fitting process is abnormal; sending information of abnormality in the press mounting process to a press mounting parameter feedback model, adjusting press mounting process parameters in real time, and recording abnormal data to a training set of the press mounting parameter determination model;
if the real-time press-mounting force-displacement curve is consistent with the reference press-mounting force-displacement curve and the press-mounting process is not damaged, judging that no abnormity exists in the press-mounting process, and continuing press-mounting according to press-mounting technological parameters until forward press-mounting is completed;
and (4) maintaining the pressure of the track pin through the main piezoelectric cylinder, and completing the press fitting work of the rubber bushing of the track pin after reversely press fitting the track pin by using the back piezoelectric cylinder.
Further, the preferable structure is that the press-fitting execution module further comprises a press-fitting quality judgment sub-module,
and the press fitting quality judging submodule is used for judging whether the press fitting quality is qualified or not according to the collected end face image of the rubber bushing.
Further, the preferable structure is that the control unit further comprises a press fitting parameter determination model iteration updating module, and the press fitting parameter determination model iteration updating module is used for inputting information for judging that the press fitting process is abnormal and/or information for judging that the press fitting process is abnormal according to the press fitting image of the crawler pin and the press fitted end face image of the rubber bushing, into a deep learning training database of the press fitting parameter determination model, and performing incremental iteration updating on the press fitting determination feedback model.
Further, the preferred structure is that a feeding track is arranged on the material rest on the track pin, the track pin is arranged in the feeding track in a sliding mode, and the arrangement direction of the feeding track is perpendicular to the conveying direction of the heating plate.
The invention also discloses a vision-based self-adaptive press mounting method, which comprises the steps of feeding the crawler pins one by one to the feeding crawler through the crawler pin feeding rack, and collecting the shaft diameter and the assembly temperature of the crawler pins; the feeding image acquisition unit is used for acquiring an axle diameter image of the track pin in the feeding process, and further determining the axle diameter of the track pin; collecting the temperature of the heating plate as an assembly temperature through a temperature sensor;
determining a model by using press-fitting parameters according to the shaft diameter of the track pin, the assembly temperature and the material parameters of the track pin, and acquiring press-fitting technological parameters and a reference press-fitting force-displacement curve;
when the crawler pin reaches the press-mounting station, the main piezoelectric cylinder is used for carrying out forward press-mounting on the rubber bushing on the crawler pin according to press-mounting technological parameters; meanwhile, the press-fitting force and the press-fitting stroke of the press-fitting unit and the press-fitting image of the crawler pin in the press-fitting process are collected; generating a real-time press-fitting force-displacement curve according to the press-fitting force and the press-fitting stroke;
judging whether the press mounting process is abnormal or not according to the judgment result that whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not; judging whether the press mounting process is damaged or not according to the press mounting image of the track pin in the press mounting process;
if the real-time press-mounting force-displacement curve is inconsistent with the reference press-mounting force-displacement curve and/or if the press-mounting process is damaged, judging that the press-mounting process is abnormal; sending information of abnormality in the press mounting process to a press mounting parameter feedback model, adjusting press mounting process parameters in real time, and recording abnormal data to a training set of the press mounting parameter determination model;
if the real-time press-mounting force-displacement curve is consistent with the reference press-mounting force-displacement curve and the press-mounting process is not damaged, judging that no abnormity exists in the press-mounting process, and continuing press-mounting according to press-mounting technological parameters until forward press-mounting is finished;
and the main piezoelectric cylinder is used for maintaining the pressure of the track pin, and the back piezoelectric cylinder is used for reversely pressing the track pin to complete the pressing work of the rubber bushing of the track pin.
Further, the preferable method comprises the steps of adjusting the angle of the end face of the rubber bushing of the crawler pin through a mechanical arm, and collecting images of the end face of the rubber bushing of the crawler plate by using a high-speed camera;
and judging whether the press fitting quality is qualified or not according to the acquired end face image of the rubber bushing.
Further, the preferable method is that information for judging that the press-fitting process is abnormal and/or information for judging that the press-fitting quality is unqualified is input into a deep learning training database of the press-fitting parameter determination model, and incremental iterative updating is carried out on the press-fitting parameter determination model to form the online press-fitting parameter determination model.
Further, the preferable method is that the press-fitting process parameters comprise press-fitting speed, overpressure displacement, back pressure displacement and pressure maintaining time.
The invention establishes the self-adaptive press mounting device and method based on vision and capable of incremental learning, and has the following beneficial effects:
1) The traditional press-fitting system only has the function of executing press-fitting actions and does not have the functions of analyzing press-fitting quality and adjusting in real time. The press mounting method comprises the steps of establishing a press mounting parameter determination model, obtaining press mounting technological parameters and a reference press mounting force-displacement curve, carrying out press mounting according to the press mounting technological parameters, and monitoring the press mounting process in real time; comparing the real-time press-fitting force-displacement curve with a reference press-fitting force-displacement curve, and determining whether the press-fitting process is abnormal or not by acquiring a press-fitting image of the track pin in the press-fitting process; adjusting the press-mounting technological parameters in real time according to the abnormal data;
2) The press mounting system aims at the problem that the traditional press mounting system does not have the functions of independently learning and self-updating the working data. When the behavior of poor press-fitting quality occurs, the problem that the adjustment can be only carried out by workers according to the production experience generally exists; according to the vision-based self-adaptive press-fitting device and method, the collection and recording of the working data of the press-fitting system are realized through the computer technology, the bottleneck of improving the press-fitting quality is captured through big data learning training by using the computer technology, and a decision model for further optimizing process parameters is obtained;
3) The press fitting system is monitored in real time, and the probability of workpiece damage or personnel damage caused by overlarge pressure is greatly reduced; the intelligent decision-making press-fitting mode and the multidirectional analysis of press-fitting quality are realized, and the press-fitting method is suitable for the scene of the interference press-fitting of the rubber bushing with complex press-fitting conditions.
Drawings
Fig. 1 is a schematic structural diagram of a vision-based adaptive press-fitting device according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a control unit of a vision-based adaptive press-fitting device according to an embodiment of the present invention;
fig. 3 is a schematic diagram illustrating a principle of a vision-based adaptive press-fitting method according to an embodiment of the present invention;
wherein, 1, the caterpillar band pins are used for feeding a material frame; 2. a track pin; 3. a feeding image acquisition unit; 4. heating the plate; 5. pressing and mounting the image acquisition unit; 6. a main piezoelectric cylinder; 7. a mechanical arm; 8. a camera number 3; 9. a track shoe; 10. and returning the piezoelectric cylinder.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Artificial Intelligence (AI) is a theory, method, technique and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technique of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar to human intelligence. Artificial intelligence is the research of the design principle and the realization method of various intelligent machines, so that the machines have the functions of perception, reasoning and decision making.
The artificial intelligence technology is a comprehensive subject and relates to the field of extensive technology, namely the technology of a hardware level and the technology of a software level. The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
Computer Vision technology (CV) is a science for researching how to make a machine "see", and further refers to that a camera and a Computer are used to replace human eyes to perform machine Vision such as identification, tracking and measurement on a target, and further image processing is performed, so that the Computer processing becomes an image more suitable for human eyes to observe or is transmitted to an instrument to detect. As a scientific discipline, computer vision research-related theories and techniques attempt to build artificial intelligence systems that can capture information from images or multidimensional data. The computer vision technology generally includes technologies such as image processing, image Recognition, image semantic understanding, image retrieval, OCR (Optical Character Recognition), video processing, video semantic understanding, video content/behavior Recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, synchronous positioning, map construction, and the like, and also includes common biometric technologies such as face Recognition, fingerprint Recognition, and the like.
Machine Learning (ML) is a multi-domain cross discipline, and relates to a plurality of disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and the like. The special research on how a computer simulates or realizes the learning behavior of human beings so as to acquire new knowledge or skills and reorganize the existing knowledge structure to continuously improve the performance of the computer. Machine learning is the core of artificial intelligence, is the fundamental approach for computers to have intelligence, and is applied to all fields of artificial intelligence. Machine learning and deep learning generally include techniques such as artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, and teaching learning.
With the development of intelligent manufacturing technology, machine vision and computer technology are more and more widely applied to assembly. Machine vision simulates human vision ability by using an optical system, an industrial digital camera and an image processing tool, makes corresponding decisions, and finally completes specific actions through a command device. And the computer technology can synthesize the data of machine vision, a temperature sensor, a force sensor and a displacement sensor, monitor the assembly information in real time, predict the assembly quality and feed back the assembly process. The invention is a problem to be solved in need of intelligent press-fitting process control by using machine vision and computer technology.
According to the vision-based self-adaptive press-fitting device and method, the shaft diameter image of the track pin in the feeding process is obtained through machine vision, and a press-fitting reference force-displacement curve in the press-fitting process is fitted through a computer technology; the real-time press-fitting force-displacement curve in the actual press-fitting process is compared with the press-fitting reference force-displacement curve, the press-fitting image of the crawler pin in the press-fitting process is obtained through machine vision, whether the press-fitting process is normally carried out or not is judged, the real-time monitoring on the press-fitting system is realized, and the condition that the workpiece is damaged or the safety of the working environment is threatened due to overlarge pressure is avoided.
The press mounting system aims at the problem that the traditional press mounting system does not have the functions of independently learning and self-updating the working data. When the behavior of poor press-fitting quality occurs, the problem that the adjustment can be only carried out by workers according to the production experience generally exists; according to the vision-based self-adaptive press-fitting device and method, the collection and the recording of the working data of the press-fitting system are realized through the computer technology, the bottleneck of improving the press-fitting quality is captured through big data learning training by using the computer technology, and a decision model for further optimizing process parameters is obtained.
Example 1
Fig. 1 is a schematic structural diagram of a vision-based adaptive press-fitting device according to an embodiment of the present invention, and as shown in fig. 1,
a vision-based self-adaptive press-fitting device comprises a feeding unit, a feeding image acquisition unit, a press-fitting image acquisition unit, a rubber bushing end face image acquisition unit and a control unit; the feeding unit is used for feeding the track pins 2 one by one to the feeding unit and comprises a track pin feeding frame 1 used for bearing the track pins; the feeding unit is used for conveying the track pin to the press-fitting unit and comprises a feeding track, a heating plate 4 arranged below the feeding track and a temperature sensor arranged on the heating plate; the feeding image acquisition unit 3 is used for acquiring an axle diameter image of the track pin in the feeding process, and is arranged above the feeding track; the press-fitting unit is used for press-fitting the rubber bushing of the track pin at the press-fitting position of the track pin and comprises a main piezoelectric cylinder 6 and a back piezoelectric cylinder 10 which are respectively arranged at two ends of the press-fitting position of the track pin; the press-fitting device also comprises a force sensor for acquiring press-fitting force and a displacement sensor for acquiring press-fitting displacement; the press-fitting image acquisition unit 5 is used for acquiring press-fitting images of the track pins in the press-fitting process, and the press-fitting image acquisition unit 5 is arranged above the press-fitting positions of the track pins; the rubber bushing end face image acquisition unit is used for acquiring an end face image of the rubber bushing and sending the end face image of the rubber bushing to the control unit; comprises a mechanical arm 7 for adjusting the shooting angle of the rubber bushing end surface of the crawler pin and a high-speed camera 8 for shooting the rubber bushing end surface image of the crawler plate. A feeding track is arranged on the material rack 1 on the crawler pin, the crawler pin 2 is arranged in the feeding track in a sliding mode, and the arrangement direction of the feeding track is perpendicular to the conveying direction of the heating plate 4.
That is, the overall press-fitting process is that the crawler belt pins in the feeding unit are fed onto the feeding unit one by one, and the feeding unit conveys the crawler belt pins 2 to the crawler belt pin press-fitting positions of the press-fitting unit; the main piezoelectric cylinder 6 and the back piezoelectric cylinder 10 which are arranged at two ends of the crawler belt pin press-mounting position are used for respectively carrying out forward press-mounting and reverse press-mounting on the crawler belt pin 2, and the rubber bushing press-mounting process of the crawler belt pin is completed.
The control unit is used for receiving the shaft diameter image of the track pin 2 acquired by the feeding image acquisition unit 3, the temperature acquired by the temperature sensor and the press-mounting image of the track pin acquired by the press-mounting image acquisition unit 5, determining press-mounting process parameters, and controlling the main piezoelectric cylinder 6 and the back piezoelectric cylinder 10 to complete the press-mounting work of the rubber bushing of the track pin according to the press-mounting process parameters; and judging whether the press fitting process is abnormal or not according to the press fitting image of the crawler pin and the end face image of the rubber bushing after press fitting, and adjusting the press fitting process parameters in real time according to abnormal data in the press fitting process.
The feeding image acquisition unit, the press-mounting image acquisition unit and the rubber bushing end face image acquisition unit are used for acquiring images of the whole feeding, press-mounting and press-mounting states of the track pin; the feeding image acquisition unit is used for acquiring an axle diameter image of the track pin 2 in the feeding process; acquiring an image of the press-fitting end face of the track pin 2 in the press-fitting process by using a press-fitting image acquisition unit; and acquiring the image of the end face of the rubber bushing of the crawler pin after the press mounting by using a rubber bushing end face image acquisition unit. In a specific implementation, in order to ensure the sharpness of the captured image, the unit performs image capture by a high-speed camera including a macro lens 7, and the frame rate of the high-speed camera is greater than or equal to 2000fps, such as an sscmos camera. And setting image acquisition devices in the feeding image acquisition unit, the press-mounting image acquisition unit and the rubber bushing end face image acquisition unit as a No. 1 camera, a No. 2 camera and a No. 3 camera.
Fig. 2 is a schematic diagram of a principle of a vision-based adaptive press-fitting device according to an embodiment of the present invention, and referring to fig. 2, after a track pin is loaded, a camera 1 acquires a top-down image of the track pin, and performs image processing by a control unit to calculate a shaft diameter of the track pin; while the field temperature is collected by the temperature sensor in the heating plate 4 as the assembly temperature. In a specific implementation process, if the temperature of the assembly environment is too low, the rubber material becomes brittle, and the assembly quality is affected. If the control unit in the vision-based adaptive press fitting device of the invention finds that the collected assembly temperature is lower than the preset standard temperature range, the heating plate 4 is required to heat the track pin.
And according to the obtained assembly temperature and shaft diameter data signals and the pre-obtained material parameters of the track pin, obtaining press-fitting process parameters and a press-fitting reference force-displacement curve by using a press-fitting parameter model, wherein the press-fitting process parameters comprise press-fitting speed, overpressure displacement, back-pressure displacement and pressure maintaining time. It should be noted that the press fitting parameter model is realized based on a convolutional neural network and a support vector machine classification optimization algorithm. In the press-fitting parameter model, the structure of the convolutional neural network may be, but is not limited to, a network structure of the convolutional neural network, which includes 1 input layer, 3 convolutional layers, 3 pooling layers, and 1 full-connection layer, and the above layers all use the Relu activation function. The press-fit parameter model may be, but is not limited to, an AGLNet model, a ResNe network model, a YOLOv4 model, a DBN network model, an LSTM model, etc.
After the press-fitting technological parameters are controlled, when the crawler pin 2 reaches the press-fitting station, the main piezoelectric cylinder 6 carries out forward press-fitting on the crawler pin 2. In the press mounting process, the control unit acquires press mounting force data and press mounting displacement data through a force sensor and a displacement sensor of a servo electric cylinder, so as to acquire a real-time press mounting force-displacement curve, compares the real-time press mounting force-displacement curve with a press mounting reference force-displacement curve, and judges whether a press mounting process signal is abnormal or not; meanwhile, the No. 2 camera takes a picture of the press-fitting process.
Judging whether a press-fitting process is damaged or not according to a press-fitting image of the crawler pin in the press-fitting process and judging whether a real-time press-fitting force-displacement signal is abnormal or not according to a real-time press-fitting force-displacement curve by a data processing module in the control unit, and comparing the real-time press-fitting force-displacement signal with a press-fitting reference force-displacement curve; if the press fitting parameters are all qualified, judging that the press fitting process is qualified, and continuously carrying out press fitting according to set press fitting technological parameters; if the unqualified data exist, the unqualified data need to be fed back. It should be noted that the feedback is divided into two parts, one of which is feedback to the feedback adjustment model, and the feedback adjustment model continues to press and mount the process parameters after reasonably adjusting the process parameters; the abnormal data is sent to a press-mounting parameter feedback adjustment model, real-time feedback adjustment is carried out on the press-mounting process, and the feedback model mainly plays a role in feedback adjustment abnormity; and secondly, recording abnormal data into a deep learning training database of the press fitting parameter model, and performing iterative updating on the press fitting parameter model, namely recording the abnormal data into a training set of the determined model to complete incremental updating of the determined model.
After the forward press-fitting is finished, the main piezoelectric cylinder 6 is used for maintaining the pressure of the track pin 2; the back pressure electric cylinder 10 carries out reverse press mounting on the track pin 2; after the integral press fitting is finished, the crawler pin with the rubber bushing pressed enters the crawler plate 9; the track shoe 9 on which the crawler pin 2 is loaded is turned over by the robot arm 7; shooting the end face (the end face of the rubber bushing) of the track shoe by a No. 3 industrial camera, and judging whether the press-fitting quality is qualified by a control unit; and if the press fitting quality is qualified, press fitting is finished, and if the press fitting quality is not qualified, data is recorded into a deep learning training database of the press fitting parameter model, and the press fitting parameter model is iteratively updated.
Fig. 3 is a schematic structural diagram of a control unit of a vision-based adaptive press-fitting device according to an embodiment of the present invention, and referring to fig. 3,
the control unit 300 comprises a shaft diameter and assembly temperature data determining module 310, a process parameter determining module 320 and a press-fitting executing module 330; wherein,
the shaft diameter and assembly temperature determining module 310 is used for acquiring a shaft diameter image of the track pin in the feeding process, and further determining the shaft diameter of the track pin; for collecting the temperature at the heating plate as the assembly temperature.
And the process parameter determining module 320 is used for determining a model by using the press-fitting parameters according to the shaft diameter of the track pin, the assembly temperature and the material parameters of the track pin, and acquiring press-fitting process parameters and a reference press-fitting force-displacement curve.
The press-mounting execution module 330 is used for carrying out forward press-mounting on the rubber bushing on the track pin by using the main piezoelectric cylinder according to press-mounting process parameters when the track pin reaches a press-mounting station; meanwhile, the press-fitting force and the press-fitting stroke of the press-fitting unit and the press-fitting image of the crawler pin in the press-fitting process are collected; generating a real-time press-fitting force-displacement curve according to the press-fitting force and the press-fitting stroke; judging whether the press mounting process is abnormal or not according to the judgment result that whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not; judging whether the press mounting process is damaged or not according to the press mounting image of the track pin in the press mounting process; if the real-time press-fitting force-displacement curve is inconsistent with the reference press-fitting force-displacement curve and/or if the press-fitting process is damaged, judging that the press-fitting process is abnormal; sending information of abnormality in the press mounting process to a press mounting parameter feedback model, adjusting press mounting process parameters in real time, and recording abnormal data to a training set of the press mounting parameter determination model; if the real-time press-mounting force-displacement curve is consistent with the reference press-mounting force-displacement curve and the press-mounting process is not damaged, judging that no abnormity exists in the press-mounting process, and continuing press-mounting according to press-mounting technological parameters until forward press-mounting is finished; and the main piezoelectric cylinder is used for maintaining the pressure of the track pin, and the back piezoelectric cylinder is used for reversely pressing the track pin to complete the pressing work of the rubber bushing of the track pin.
The real-time press fitting force-displacement curve monitoring submodule is used for generating a real-time press fitting force-displacement curve according to the press fitting force and the press fitting stroke; and judging whether the press mounting process is abnormal or not according to the judgment of whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not.
The parameter feedback adjusting submodule (namely a feedback adjusting model) is used for sending information that the press-mounting process is abnormal to the press-mounting parameter feedback model, adjusting press-mounting process parameters in real time, and recording abnormal data to a training set of the press-mounting parameter determining model;
and the press mounting surface monitoring submodule is used for judging whether the press mounting process is damaged or not according to the acquired press mounting surface image of the track pin in the press mounting process.
The press-fitting execution module 330 further comprises a press-fitting quality judgment submodule, which is used for judging whether the press-fitting quality is qualified or not according to the collected end face image of the rubber bushing.
The control unit further comprises a press-fitting parameter determination model iteration updating module 340, wherein the press-fitting parameter determination model iteration updating module is used for judging the information that the press-fitting process is abnormal and/or judging the information that the press-fitting process is abnormal according to the press-fitting image of the crawler pin and the press-fitted end face image of the rubber bushing, inputting a deep learning training database of the press-fitting parameter determination model, and performing incremental iteration updating on the press-fitting parameter determination model.
In a particular embodiment, the control unit may be, but is not limited to being, a computer.
The functions of the control unit are performed by instructing the associated hardware by a computer program, which may be stored in a computer-readable storage medium, which when executed by a processor, may implement the steps of the above-described method embodiments. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic diskette, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signal, telecommunications signal, software distribution medium, etc. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.
Firstly, the self-adaptive press-fitting device based on vision is an intelligent self-adaptive press-fitting system, is different from the prior art that operators determine process parameters by means of experience and continuous modification and trial and error, and adopts the mode that the shaft diameter of a rubber bushing and the field temperature are used as input, press-fitting quality feedback is used as the basis, certain data analysis and comparison are carried out according to a press-fitting parameter mathematical model, an optimal press-fitting scheme is determined, and the defects of fixed and mechanized press-fitting modes in the traditional press-fitting system are overcome.
Secondly, the self-adaptive press-fitting device based on vision can dynamically adjust the press-fitting strategy in real time in the press-fitting process. And (3) feeding back the abnormal point in real time through the cooperative judgment of the image of the press-mounting surface and the force-displacement curve in the press-mounting process, and then adjusting the process parameters in real time by the servo electric cylinder according to the press-mounting feedback mathematical model. By the method, the vision-based self-adaptive press-fitting device becomes a closed-loop system with self-adaptive control characteristics. The defect that technological parameters cannot be adjusted once the press-fitting process starts in the traditional press-fitting system is overcome. And the technical effects of reducing the rejection rate and reducing the fault rate of the electric cylinder are achieved.
The self-adaptive press-fitting device based on vision is an autonomous iterative press-fitting system, a constructor does not need to determine a complete set of very accurate press-fitting strategy model at the beginning of press fitting, and the press-fitting system can be combined with feedback information and data to perform deep learning along with continuous collection and accumulation of data in the press-fitting process, explore random influence factors influencing the press-fitting quality, find bottlenecks and typical performance weaknesses of the system and perform deep optimization on a press-fitting parameter model.
The invention also discloses a vision-based self-adaptive press fitting method, which comprises the step S110 to the step S170.
S110, feeding the feeding tracks one by one through the track pin feeding frame, and collecting the shaft diameter and the assembly temperature of the track pins; the feeding image acquisition unit is used for acquiring an axle diameter image of the track pin in the feeding process, so that the axle diameter of the track pin is determined; the temperature at the heating plate is collected by a temperature sensor as the assembly temperature. It should be noted that, because the rubber bushing has a certain error during processing, and the rubber material is sensitive to temperature, the shaft diameter R of the rubber bushing fluctuates around the tolerance range, and therefore, the shaft diameter of the bushing needs to be measured in a non-contact manner.
S120, determining a model by using press-fitting parameters according to the shaft diameter of the track pin, the assembly temperature and the material parameters of the track pin, and acquiring press-fitting technological parameters and a reference press-fitting force-displacement curve; the press-fitting process parameters comprise press-fitting speed, overpressure displacement, back-pressure displacement and pressure maintaining time.
S130, when the crawler pin reaches a press-mounting station, forward press-mounting the rubber bushing on the crawler pin by using a main piezoelectric cylinder according to press-mounting technological parameters; meanwhile, the press-fitting force and the press-fitting stroke of the press-fitting unit and the press-fitting image of the crawler pin in the press-fitting process are collected; and generating a real-time press fitting force-displacement curve according to the press fitting force and the press fitting stroke.
S140, judging whether the press mounting process is abnormal or not according to the judgment of whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not; and judging whether the press-fitting process is damaged or not according to the press-fitting image of the track pin in the press-fitting process.
If the real-time press-mounting force-displacement curve is inconsistent with the reference press-mounting force-displacement curve and/or if the press-mounting process is damaged, judging that the press-mounting process is abnormal; and sending the information of abnormity in the press mounting process to a press mounting parameter feedback model, adjusting the press mounting process parameters in real time, and recording abnormal data to a training set of the press mounting parameter determination model.
And if the real-time press-mounting force-displacement curve is consistent with the reference press-mounting force-displacement curve and the press-mounting process is not damaged, judging that no abnormity exists in the press-mounting process, and continuing press-mounting according to press-mounting technological parameters until forward press-mounting is finished.
S150, the pressure maintaining is carried out on the track pin through the main piezoelectric cylinder, and after the back piezoelectric cylinder is used for carrying out reverse press mounting on the track pin, the press mounting work of the rubber bushing of the track pin is completed.
S160, acquiring images of the end faces of the rubber bushings of the track plate by using a high-speed camera through the angle of the end faces of the rubber bushings of the track pin adjusted by the mechanical arm; and judging whether the press fitting quality is qualified or not according to the acquired end face image of the rubber bushing. The No. 3 camera is in a posture of obliquely shooting the rubber bushing, so that a visual blind area exists, and the track shoe needs to be turned over by the mechanical arm.
S170, inputting information for judging whether the press-fitting process is abnormal and/or information for judging whether the press-fitting quality is unqualified into a deep learning training database of the press-fitting parameter determination model, and performing incremental iteration updating on the press-fitting parameter determination model to form an online press-fitting parameter determination model.
Example 2
The preset press fitting temperature is 45 ℃, the maximum press fitting force is 3000N, the overflow length of the rubber bushing exceeds 1.5mm, or the rubber bushing is damaged, namely the rubber bushing is unqualified.
After the track pins are fed, a camera 1 is used for collecting shaft diameter images of the track pins in the feeding process, and a shaft diameter R is determined by a shaft diameter and assembly temperature determining module 310 of a control unit; detecting the assembly temperature by using a temperature sensor; if the temperature is lower than 45 ℃, heating to 45 ℃ by using a heating plate; if the temperature has reached 45 ℃, the assembly temperature is recorded as T.
The measured shaft diameter R and the assembly temperature T are used as variables and input into a pre-built-in press fitting parameter model algorithm, and press fitting parameters (overpressure displacement, back pressure displacement, press fitting speed and pressure maintaining time) of controlled quantity are output.
And the control unit drives the press-mounting unit to press-mount the servo electric cylinder according to the press-mounting parameters of the controlled quantity. In the press-fitting process, the real-time press-fitting force-displacement curve supervision submodule and the press-fitting surface supervision submodule of the press-fitting execution module 330 cooperatively monitor; when the maximum press-fitting force exceeds 3000N or the rubber bushing is detected to be damaged, an alarm is given, abnormal data are transmitted to a press-fitting feedback model of the control unit, and press-fitting quality can be improved by reducing press-fitting speed, or reducing overpressure displacement, increasing pressure maintaining time and the like; meanwhile, abnormal data are recorded in the server to form a processing data set, and a basis is provided for deep learning and optimization of a subsequent algorithm.
If the real-time press-fitting force-displacement curve supervision sub-module and the press-fitting surface supervision sub-module do not find abnormal data, the press-fitting process can be continued until the press-fitting action is completed.
Overturning the track shoe loaded with the track pin by using a mechanical arm, and acquiring an end face image of the rubber bushing;
if the press-fitting quality judgment submodule detects that the overflow length of the rubber bushing is less than 1.5mm, the press-fitting can be judged to be qualified; if the overflow length of the rubber bushing is larger than 1.5mm, the processing data of the time is transmitted to a server and recorded in a processing data set.
By adopting the vision-based self-adaptive press-fitting device and method, the press-fitting process parameters and the reference press-fitting force-displacement curve are obtained by establishing the press-fitting parameter determination model, press fitting is performed according to the press-fitting process parameters, and the press-fitting process is monitored in real time; comparing a real-time press-mounting force-displacement curve with a reference press-mounting force-displacement curve, and determining whether an abnormality exists in the press-mounting process by acquiring a press-mounting image of a track pin in the press-mounting process; adjusting the press-fitting technological parameters in real time according to the abnormal data; the real-time monitoring of the press-fitting system is realized, and the occurrence probability of workpiece damage or personnel damage caused by overlarge pressure is greatly reduced; the intelligent decision-making press-fitting mode and multi-azimuth analysis press-fitting quality are realized, and the method is suitable for a scene of interference press-fitting of the rubber bushing with complex press-fitting conditions.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A vision-based self-adaptive press-fitting device is characterized by comprising a feeding unit, a feeding image acquisition unit, a press-fitting image acquisition unit, a rubber bushing end face image acquisition unit and a control unit; wherein,
the feeding unit is used for feeding the track pins one by one to the feeding unit and comprises a track pin feeding frame used for bearing the track pins;
the feeding unit is used for conveying the track pin to the press-fitting unit and comprises a feeding track, a heating plate arranged below the feeding track and a temperature sensor arranged on the heating plate;
the feeding image acquisition unit is used for acquiring an axle diameter image of the track pin in the feeding process, and the feeding image acquisition unit is arranged above the feeding track;
the press-fitting unit is used for press-fitting the rubber bushing on the track pin at the press-fitting position of the track pin, and comprises a main piezoelectric cylinder and a back piezoelectric cylinder which are respectively arranged at two ends of the press-fitting position of the track pin, a force sensor for acquiring press-fitting force and a displacement sensor for acquiring press-fitting displacement;
the press-fitting image acquisition unit is used for acquiring press-fitting images of the track pin in the press-fitting process, and the press-fitting image acquisition unit is arranged above the press-fitting position of the track pin;
the rubber bushing end face image acquisition unit is used for acquiring the pressed rubber bushing end face image and sending the rubber bushing end face image to the control unit;
the control unit is used for receiving the shaft diameter image of the track pin acquired by the feeding image acquisition unit, the temperature acquired by the temperature sensor and the press-fitting image of the track pin acquired by the press-fitting image acquisition unit, determining press-fitting technological parameters, and controlling the main piezoelectric cylinder and the back piezoelectric cylinder to complete the press-fitting work of the rubber bushing of the track pin according to the press-fitting technological parameters; and judging whether the press fitting process is abnormal or not according to the press fitting image of the crawler pin and the end face image of the pressed rubber bushing, and adjusting the press fitting process parameters in real time according to abnormal data of the press fitting process.
2. A vision-based adaptive press-fitting device according to claim 1,
the rubber bushing end face image acquisition unit comprises a mechanical arm and a high-speed camera, wherein the mechanical arm is used for adjusting the shooting angle of the rubber bushing end face of the crawler pin, and the high-speed camera is used for shooting the rubber bushing end face image of the crawler plate.
3. A vision based adaptive press fitting apparatus according to claim 1, wherein said control unit comprises a shaft diameter and fitting temperature data determining module, a process parameter determining module and a press fitting performing module; wherein,
the shaft diameter and assembly temperature determining module is used for acquiring a shaft diameter image of the track pin in the feeding process so as to determine the shaft diameter of the track pin; the temperature acquisition device is used for acquiring the temperature of the heating plate as the assembly temperature;
the process parameter determining module is used for determining a model by using press-mounting parameters according to the shaft diameter of the track pin, the assembly temperature and the material parameters of the track pin, and acquiring press-mounting process parameters and a reference press-mounting force-displacement curve;
the press-fitting execution module is used for carrying out forward press-fitting on the rubber bushing on the track pin by using the main piezoelectric cylinder according to the press-fitting process parameters when the track pin reaches the press-fitting station; meanwhile, the press-fitting force and the press-fitting stroke of the press-fitting unit and the press-fitting image of the crawler pin in the press-fitting process are collected; generating a real-time press fitting force-displacement curve according to the press fitting force and the press fitting stroke;
judging whether the press mounting process is abnormal or not according to the judgment whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not; judging whether the press-fitting process is damaged or not according to the press-fitting image of the track pin in the press-fitting process;
if the real-time press-mounting force-displacement curve is inconsistent with the reference press-mounting force-displacement curve and/or if the press-mounting process is damaged, judging that the press-mounting process is abnormal; sending the information that the press-mounting process is abnormal to a press-mounting parameter feedback model, adjusting press-mounting process parameters in real time, and recording abnormal data to a training set of the press-mounting parameter determination model;
if the real-time press-mounting force-displacement curve is consistent with the reference press-mounting force-displacement curve and the press-mounting process is not damaged, judging that no abnormity exists in the press-mounting process, and continuing press-mounting according to press-mounting technological parameters until forward press-mounting is finished;
and (3) maintaining the pressure of the track pin by the main piezoelectric cylinder, and performing reverse press mounting on the track pin by using a back piezoelectric cylinder to complete the press mounting work of the rubber bushing of the track pin.
4. A vision-based adaptive press-fitting device according to claim 3,
the press-fitting execution module also comprises a press-fitting quality judgment sub-module,
and the press fitting quality judgment submodule is used for judging whether the press fitting quality is qualified or not according to the acquired end face image of the rubber bushing.
5. A vision-based adaptive press-fitting device according to claim 3 or 4,
the control unit further comprises a press-fitting parameter determination model iteration updating module, wherein the press-fitting parameter determination model iteration updating module is used for judging the information that the press-fitting process is abnormal and/or inputting the information that the press-fitting process is abnormal according to the press-fitting image of the crawler pin and the press-fitted end face image of the rubber bushing into a deep learning training database of the press-fitting parameter determination model and performing incremental iteration updating on the press-fitting parameter determination model.
6. A vision-based adaptive press-fitting device according to claim 1,
the feeding track is arranged on the material rack on the crawler pin, the crawler pin is arranged in the feeding track in a sliding mode, and the arrangement direction of the feeding track is perpendicular to the conveying direction of the heating plate.
7. A self-adaptive press-fitting method based on vision is characterized in that,
feeding the feeding crawler belts one by one through the crawler belt pin feeding frame, and collecting the shaft diameter and the assembly temperature of the crawler belt pins; the feeding image acquisition unit is used for acquiring an axle diameter image of the track pin in the feeding process, and further determining the axle diameter of the track pin; collecting the temperature of the heating plate as an assembly temperature through a temperature sensor;
according to the shaft diameter of the track pin, the assembly temperature and the material parameters of the track pin, determining a model by using press-mounting parameters, and acquiring press-mounting process parameters and a reference press-mounting force-displacement curve;
when the crawler pin reaches a press-mounting station, forward press-mounting the rubber bushing on the crawler pin by using a main piezoelectric cylinder according to the press-mounting process parameters; meanwhile, the press-fitting force and the press-fitting stroke of the press-fitting unit and the press-fitting image of the crawler pin in the press-fitting process are collected; generating a real-time press-fitting force-displacement curve according to the press-fitting force and the press-fitting stroke;
judging whether the press mounting process is abnormal or not according to the judgment whether the real-time press mounting force-displacement curve is consistent with the reference press mounting force-displacement curve or not; judging whether the press mounting process is damaged or not according to the press mounting image of the track pin in the press mounting process;
if the real-time press-mounting force-displacement curve is inconsistent with the reference press-mounting force-displacement curve and/or if the press-mounting process is damaged, judging that the press-mounting process is abnormal; sending the information that the press mounting process is abnormal to a press mounting parameter feedback model, adjusting press mounting process parameters in real time, and recording abnormal data to a training set of a press mounting parameter determination model;
if the real-time press-mounting force-displacement curve is consistent with the reference press-mounting force-displacement curve and the press-mounting process is not damaged, judging that no abnormity exists in the press-mounting process, and continuing press-mounting according to press-mounting technological parameters until forward press-mounting is finished;
and (3) maintaining the pressure of the track pin by the main piezoelectric cylinder, and performing reverse press mounting on the track pin by using a back piezoelectric cylinder to complete the press mounting work of the rubber bushing of the track pin.
8. A vision based adaptive press-fitting method according to claim 7,
also comprises a step of adding a new type of additive,
adjusting the angle of the end face of the rubber bushing of the crawler pin through a mechanical arm, and acquiring an image of the end face of the rubber bushing of the crawler plate by using a high-speed camera;
and judging whether the press fitting quality is qualified or not according to the acquired end face image of the rubber bushing.
9. A vision-based adaptive press-fitting method according to claim 7 or 8,
and inputting information for judging whether the press fitting process is abnormal and/or information for judging that the press fitting quality is unqualified into a deep learning training database of the press fitting parameter determination model, and performing incremental iteration updating on the press fitting parameter determination model to form an online press fitting parameter determination model.
10. A vision-based adaptive press-fitting method according to claim 7,
the press-fitting process parameters comprise press-fitting speed, overpressure displacement, back pressure displacement and pressure maintaining time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211178412.5A CN115648644B (en) | 2022-09-26 | 2022-09-26 | Self-adaptive press fitting device and method based on vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211178412.5A CN115648644B (en) | 2022-09-26 | 2022-09-26 | Self-adaptive press fitting device and method based on vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115648644A true CN115648644A (en) | 2023-01-31 |
| CN115648644B CN115648644B (en) | 2024-04-09 |
Family
ID=84984633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211178412.5A Active CN115648644B (en) | 2022-09-26 | 2022-09-26 | Self-adaptive press fitting device and method based on vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115648644B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117182524A (en) * | 2023-10-26 | 2023-12-08 | 芜湖戎征达伺服驱动技术有限公司 | Intelligent press-fitting equipment and method for auxiliary frame bushing of automobile |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001203224A (en) * | 2000-01-19 | 2001-07-27 | Sony Corp | Resin-sealing device |
| CN109986323A (en) * | 2019-04-01 | 2019-07-09 | 南京睿易智能科技有限公司 | A kind of screw automatic charging device flexible and method |
| CN111469427A (en) * | 2020-04-22 | 2020-07-31 | 合肥研泰自动化设备有限公司 | Visual servo assembly machine |
| CN113400661A (en) * | 2021-06-29 | 2021-09-17 | 明瑞达(苏州)人工智能科技有限公司 | Machine vision-based precise mounting system and method |
| CN113650309A (en) * | 2021-08-19 | 2021-11-16 | 江苏银环新材料科技有限公司 | Visual processing-based assembly equipment and method for heat-preservation steel truss floor bearing plate |
-
2022
- 2022-09-26 CN CN202211178412.5A patent/CN115648644B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001203224A (en) * | 2000-01-19 | 2001-07-27 | Sony Corp | Resin-sealing device |
| CN109986323A (en) * | 2019-04-01 | 2019-07-09 | 南京睿易智能科技有限公司 | A kind of screw automatic charging device flexible and method |
| CN111469427A (en) * | 2020-04-22 | 2020-07-31 | 合肥研泰自动化设备有限公司 | Visual servo assembly machine |
| CN113400661A (en) * | 2021-06-29 | 2021-09-17 | 明瑞达(苏州)人工智能科技有限公司 | Machine vision-based precise mounting system and method |
| CN113650309A (en) * | 2021-08-19 | 2021-11-16 | 江苏银环新材料科技有限公司 | Visual processing-based assembly equipment and method for heat-preservation steel truss floor bearing plate |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117182524A (en) * | 2023-10-26 | 2023-12-08 | 芜湖戎征达伺服驱动技术有限公司 | Intelligent press-fitting equipment and method for auxiliary frame bushing of automobile |
| CN117182524B (en) * | 2023-10-26 | 2024-02-27 | 芜湖戎征达伺服驱动技术有限公司 | Intelligent press-fitting equipment and method for auxiliary frame bushing of automobile |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115648644B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112356841B (en) | Vehicle control method and device based on brain-computer interaction | |
| Iravani-Tabrizipour et al. | An image-based feature tracking algorithm for real-time measurement of clad height | |
| CN109782707A (en) | A kind of industry spot monitoring method suitable for industry internet | |
| CN113762240B (en) | Cladding layer geometric feature prediction method and system based on deep learning | |
| DE102017010799A1 (en) | A machine learning apparatus and robot system for learning a machining order of a laser machining robot and machine learning method therefor | |
| CN115648644B (en) | Self-adaptive press fitting device and method based on vision | |
| CN116088419B (en) | Numerical control machine tool processing control method, system and related equipment based on parameter optimization | |
| CN112183313A (en) | SlowFast-based power operation field action identification method | |
| CN115994308B (en) | Numerical control machine tool fault identification method, system, equipment and medium based on meta learning | |
| CN111948994A (en) | Industrial production line closed-loop automatic quality control method based on data integration and correlation analysis | |
| CN117495205B (en) | Industrial Internet experiment system and method | |
| CN112801959B (en) | Auxiliary assembly system based on visual feature recognition | |
| CN110533107B (en) | Gradient enhancement type Softmax classifier system, training signal generation method and application thereof | |
| CN108548472B (en) | Automatic measuring device of six-equal-division window hole ball cage retainer | |
| CN114266286A (en) | Online detection method and device for welding process information | |
| CN113077423B (en) | Laser selective melting pool image analysis system based on convolutional neural network | |
| Tang et al. | Visual navigation control for agricultural robot using serial BP neural network | |
| CN111062364A (en) | Deep learning-based assembly operation monitoring method and device | |
| Acosta et al. | Machine learning in intelligent manufacturing system for optimization of production costs and overall effectiveness of equipment in fabrication models | |
| CN117331802A (en) | Middle-station data monitoring and analyzing system based on industrial Internet | |
| CN111125879B (en) | Digital twin method and device for numerical control skin stretch forming machine | |
| CN117234165A (en) | Automatic pipeline control system and control method based on computer vision | |
| CN116475651A (en) | Intelligent edge control method for welding overhaul and intelligent welding equipment | |
| CN110108510B (en) | Intelligent detection system and method for automobile electronic product based on embedded system | |
| CN114048600B (en) | Digital twin-driven multi-model fusion industrial system anomaly detection method |
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 |