CN104165591A - Method and system for fully automatic optical size detection of metal shell - Google Patents

Abstract

The invention provides a full-automatic optical size detection method and a system for a metal shell, which comprise an image management module, a data management module, a system management module and a main control module; the image management module comprises an image acquisition sub-module, an image enhancement sub-module, a feature identification sub-module, an image registration sub-module, an image fusion sub-module, an edge extraction sub-module, an image filtering sub-module and an identification control sub-module; the data management module comprises a data operation submodule, a data storage submodule and a data transmission submodule; the system management module comprises an I/O submodule and a system maintenance submodule; the main control module comprises an index detection submodule, a signal conversion submodule and a communication control submodule; the functional modules and the submodules are connected with each other through a data transmission bus or various conversion circuits and control circuits to realize data communication. The invention is a platform with high precision and high automation degree, and meets the industrial requirements of serving moulds, high and new technologies and the like.

Description

Method and system for fully automatic optical size detection of metal shell

technical field

The invention relates to the technical field of measurement and control, in particular to a method and system for fully automatic optical size detection of a metal shell.

Background technique

In modern industrial automation production, connector detection is usually a highly repetitive and intelligent work that can only be done with the naked eye, but sometimes, such as small dimensions need to be accurately and quickly measured, shape matching, color recognition, etc., People simply can't do it continuously and stably with the naked eye, and other physical sensors are also difficult to use. With the continuous miniaturization and high-density assembly trend of electronic technology, the inspection requirements for products are becoming more and more stringent, and the traditional visual inspection is far from meeting the requirements. With the development of advanced manufacturing technology and the development of optoelectronic technology products in the direction of high technology, high precision, high quality, high added value, miniaturization and integration, the corresponding precision detection technology should also adapt to this development. Precision testing technology should serve the advanced manufacturing industry and undertake quality and technical assurance.

Entering the 21st century, the technology of optoelectronics, information, electromechanical, and automobile industries continues to innovate. Various high-tech products, such as digital cameras, liquid crystals, and automobiles, quickly penetrate into every family, and various high-precision parts have become the key to products. , the demand for precision and ultra-precision machining of enterprises continues to expand; in addition, one of the current key development directions of mold processing is single-piece high-precision machining, that is, the demand for high-end molds is strong. The mold industry is developing rapidly. Driven by the automobile, plumbing, photoelectric and other industries, the demand for the mold industry is increasing day by day. Precision instrument components, optics

Medium and high-end molds such as lenses, small and medium-sized automotive castings, faucets, and LCD screens also require precise testing to ensure quality.

Therefore, how to realize the detection requirements based on various small and medium-sized precision products, such as precision electromechanical components, precision ceramic products, photoelectric components and optical lenses, etc. How to use high-precision linear motors, sensors and self-developed measurement and evaluation software as the core to realize the software and hardware control scheme, and finally realize a high-efficiency, high-precision, high-automation precision detection platform to meet the needs of photoelectric information, molds, high-tech, etc. Industrial demand is an urgent problem to be solved at present. To meet the above requirements, there are still many technical defects and the support of related software and hardware resources.

Contents of the invention

Aiming at the deficiencies in the prior art, the object of the present invention is to provide a method and system for fully automatic optical size detection of metal shells, which solve the above-mentioned problems.

The technical scheme adopted in the present invention is as follows: a fully automatic optical size detection method for a metal shell, including the device under test and the fixture with the device under test, a CCD camera is set on the detection track, and the The camera is connected to a computer with image processing function, which includes the following steps:

(1) A detection system is set, including an image acquisition module, a format conversion module, an image processing module and an identification control module, and each module is connected to each other by a data transmission line to realize data exchange;

(2) The image processing module includes an image enhancement submodule, a feature recognition submodule, an image registration submodule, an image fusion submodule, an edge extraction submodule and an image filtering submodule;

(3) The image acquisition module collects image data and converts it into recognizable format data, and transmits it to the image processing module;

(4) In the image processing module, each sub-module described in the above step (2) performs processing on the received image data in areas such as black and white edges, grayscale and binarization, and then converts it into parameter data that can carry out index detection;

(5) Perform index detection on the parameter data, judge whether it meets the standard within the tolerance range, and output control signals in real time while outputting the parameters.

Preferably, the step (3) further includes the following steps: synchronously collect the measured element from one direction (X-axis) through the optical fiber sensing principle during the image data collection process, and convert the format respectively.

Preferably, the step (4) also includes the following steps: the parameter data includes the size, angle, brightness, offset, color pigment value and position coordinate parameters of the measured element, and is converted into an actual parameter value.

Preferably, the step (4) further includes the following step: the accuracy of the parameter value must not be less than the ratio of the object image value, and the error of the accuracy must be negligible relative to the error range of the standard value.

Preferably, the step (5) also includes the following steps: when the parameter data is tested for indicators, the standard tested component is automatically sent out of the detection track through the optical fiber buffer principle, and the non-standard tested component is automatically alarmed and Stop inspection or automatically transfer it to the repair management line for repair.

A fully automatic optical size detection system for a metal shell, which includes an image management module, a data management module, a system management module, and a main control module; the image management module includes an image acquisition sub-module, an image enhancement sub-module, a feature recognition sub-module, an image configuration Quasi-module, image fusion sub-module, edge extraction sub-module, image filtering sub-module and identification control sub-module; the data management module includes a data operation sub-module, a data storage sub-module and a data transmission sub-module; the system management module It includes an I/O sub-module and a system maintenance sub-module; the main control module includes an indicator detection sub-module, a signal conversion sub-module and a communication control sub-module; the above-mentioned functional modules and sub-modules are connected through a data transmission bus or various conversion circuits and The control circuits are interconnected to realize data communication.

Preferably, the data management module also includes a data entry sub-module and a format conversion sub-module; the system management module also includes a data backup sub-module, a data restoration sub-module and a data deletion sub-module; the main control system also includes a data Call submodule, signal output submodule and signal identification submodule.

Preferably, the functional sub-modules of the image processing module can be arbitrarily combined and arranged according to needs, or can be deleted or added arbitrarily by setting free space scheduling authority.

Preferably, the image processing module is controlled hierarchically by the main program, which includes an image acquisition layer, an image processing layer and a parameter output layer.

The beneficial effects of the present invention include:

Based on the detection needs of various small and medium-sized precision products, such as precision electromechanical components, precision ceramic products, photoelectric components and optical lenses, etc.; combine the rapidity and repeatability of computers with the high degree of automation and abstraction of human vision Combined, the reliability of accuracy and speed is enhanced; the workload of traditional manual visual inspection is saved, and labor costs are reduced; high-precision linear motors, sensors and self-developed measurement and evaluation software are used as the core to realize the software and hardware control scheme, achieving high efficiency, It is an urgent need for a precision testing platform with high precision and high degree of automation to meet the needs of photoelectric information, molds, high-tech and other industries.

Description of drawings

Fig. 1 is a connection block diagram of detection system hardware modules of the present invention;

Fig. 2 is a connection block diagram of the sub-modules of the detection system image processing module of the present invention;

Fig. 3 is a software flowchart of the automatic optical dimension detection method of the present invention.

Detailed ways

The present invention will be described in detail below in combination with specific embodiments.

The fully automatic optical size detection method for metal shells, as shown in Figure 3, includes the device under test and the fixture with the device under test, a CCD camera is set on the detection track, and the camera is connected to the device through an external port. On a computer with image processing capabilities, it includes the following steps:

(1) A detection system is set, including an image acquisition module, a format conversion module, an image processing module and an identification control module, and each module is connected to each other by a data transmission line to realize data exchange;

(2) The image processing module includes an image enhancement submodule, a feature recognition submodule, an image registration submodule, an image fusion submodule, an edge extraction submodule and an image filtering submodule;

(3) The image acquisition module collects image data and converts it into recognizable format data, and transmits it to the image processing module;

(4) In the image processing module, each sub-module described in the above step (2) performs processing on the received image data in areas such as black and white edges, grayscale and binarization, and then converts it into parameter data that can carry out index detection;

(5) Perform index detection on the parameter data, judge whether it meets the standard within the tolerance range, and output control signals in real time while outputting the parameters.

The step (3) also includes the following steps: synchronously collect the measured element from one direction (X axis) through the principle of optical fiber sensing during the image data collection process, and convert the format respectively.

The step (4) also includes the following steps: the parameter data includes the size, angle, brightness, offset, color pigment value and position coordinate parameters of the measured element, and is converted into an actual parameter value according to the numerical ratio of the object image .

The step (4) also includes the following steps: the accuracy of the parameter value must not be less than the ratio of the object image value, and the error of the accuracy must be negligible relative to the error range of the standard value.

Said step (5) also comprises the following steps: when said parameter data is carried out index detection, conforms to the standard measured element to send out the detection track automatically through the principle of optical fiber buffering, and does not conform to the standard after the detection of the measured element is completed, automatically alarms and stops the detection or It is automatically transferred to the repair management line for repair.

Metal shell automatic optical size detection system, as shown in Figure 1 and 2, it includes image management module, data management module, system management module and main control module; said image management module includes image acquisition sub-module, image enhancement sub-module , feature recognition sub-module, image registration sub-module, image fusion sub-module, edge extraction sub-module, image filtering sub-module and recognition control sub-module; the data management module includes a data operation sub-module, a data storage sub-module and a data transmission Submodule; the system management module includes an I/O submodule and a system maintenance submodule; the main control module includes an index detection submodule, a signal conversion submodule and a communication control submodule; the above-mentioned functional modules and submodules pass data The transmission bus or various conversion circuits and control circuits are connected to each other to realize data communication.

The data management module also includes a data entry sub-module and a format conversion sub-module; the system management module also includes a data backup sub-module, a data reduction sub-module and a data deletion sub-module; the main control system also includes a data calling sub-module , a signal output sub-module and a signal identification sub-module.

The various functional sub-modules of the image processing module can be adjusted and arranged in any combination according to needs, or can be deleted or added arbitrarily by setting the free space scheduling authority.

The image processing module is controlled by layers of the main program, which includes an image acquisition layer, an image processing layer and a parameter output layer.

Referring to Fig. 3, the working principle of the present invention is: the CCD camera captures the image, sends it into a computer or a dedicated image processing module, and achieves the purpose of discrimination through digital processing. Combining the rapidity and repeatability of computers with the high degree of automation and abstraction of human vision. Apply the machine vision system in the industrial field environment to enhance the reliability of accuracy and speed. Its executive power mechanism is equipped with a motor to drive the terminal material belt, and through optical fiber buffering, the material belt is connected to the high-speed punching machine belt detection track. The CCD senses through the optical fiber. According to the system requirements, a high-resolution camera is used to scan and take pictures of the production line. According to the detection requirements, The system sets up two cameras (X-axis and Y-axis) to detect the terminal size in two directions at the same time, take pictures synchronously, input the pictured images into the system host, analyze and process the two images through the application software, and judge the items of each component. Whether the index to be detected meets the standard within the tolerance requirement range, and a control signal is given in real time.

The above-mentioned implementation mode is only a preferred embodiment of the present invention, and is not used to limit the implementation and scope of rights of the present invention. All equivalent changes and modifications made according to the content described in the patent protection scope of the present invention application shall be included in The present invention is within the patent scope.

Claims (9)

1. The method for fully automatic optical size detection of metal shells, including the device under test and the fixture with the device under test, is characterized in that a CCD camera is set on the detection track, and the camera is connected to the On a computer with image processing capabilities, it includes the following steps: (1) A detection system is set, including an image acquisition module, a format conversion module, an image processing module and an identification control module, and each module is connected to each other by a data transmission line to realize data exchange; (2) The image processing module includes an image enhancement submodule, a feature recognition submodule, an image registration submodule, an image fusion submodule, an edge extraction submodule and an image filtering submodule; (3) The image acquisition module collects image data and converts it into recognizable format data, and transmits it to the image processing module; (4) In the image processing module, each sub-module described in the above step (2) performs processing on the received image data in areas such as black and white edges, grayscale and binarization, and then converts it into parameter data that can carry out index detection; (5) Perform index detection on the parameter data, judge whether it meets the standard within the tolerance range, and output control signals in real time while outputting the parameters. 2. The method for fully automatic optical size detection of metal shells according to claim 1, wherein said step (3) further comprises the following steps: during said image data acquisition process, said measured image is detected simultaneously by means of optical fiber sensing principle Elements are captured synchronously from one direction (X-axis) and their formats are converted individually. 3. The method for fully automatic optical size detection of metal casings according to claim 1, wherein the step (4) further comprises the following steps: the parameter data includes the size, angle, brightness, and offset of the measured element Quantity, color pigment value and position coordinate parameters, and convert them into actual parameter values according to the numerical ratio of the object image. 4. The metal shell automatic optical size detection method according to claim 1, characterized in that, the step (4) also includes the following steps: the accuracy of the parameter value must not be less than the object image value ratio, and the accuracy Degrees of error are negligible relative to the error range of the standard value. 5. The fully automatic optical size detection method for metal casings according to claim 1, wherein the step (5) further comprises the following steps: when the parameter data is subjected to index detection, the measured element conforming to the standard is buffered through an optical fiber The principle is to automatically send out the detection track. After the detection of the components that do not meet the standards is completed, it will automatically alarm and stop the detection or automatically transmit it to the repair management production line to wait for repair. 6. A fully automatic optical size detection system for metal shells, characterized in that it includes an image management module, a data management module, a system management module and a main control module; the image management module includes an image acquisition sub-module, an image enhancement sub-module, a feature Identification sub-module, image registration sub-module, image fusion sub-module, edge extraction sub-module, image filtering sub-module and identification control sub-module; the data management module includes a data operation sub-module, a data storage sub-module and a data transmission sub-module The system management module includes an I/O sub-module and a system maintenance sub-module; the main control module includes an index detection sub-module, a signal conversion sub-module and a communication control sub-module; Or various conversion circuits and control circuits are connected to each other to realize data communication. 7. The metal shell automatic optical size detection system according to claim 6, characterized in that, the data management module also includes a data entry sub-module and a format conversion sub-module; the system management module also includes a data backup sub-module . A data restoration sub-module and a data deletion sub-module; the main control system also includes a data call sub-module, a signal output sub-module and a signal identification sub-module. 8. The fully automatic optical size detection system for metal shells according to claim 6, characterized in that, the functional sub-modules of the image processing module can be arbitrarily combined and arranged according to needs, or can be deleted or added arbitrarily by setting free space scheduling authority . 9. The fully automatic optical dimension inspection system for metal shells according to claim 6, wherein the image processing module is controlled layer by layer by a main program, which includes an image acquisition layer, an image processing layer and a parameter output layer.