Material identification method, device and equipment and storage medium

Abstract

The embodiment of the invention provides a material identification method and device, equipment and a storage medium. The method comprises the steps that after a to-be-recognized material reaches a designated position, a mechanical arm is controlled to move to a preset shooting position, and an image collection module installed on the mechanical arm is controlled to collect a first image of the to-be-recognized material; determining the material type of the to-be-identified material through the first image; calling detection configuration information corresponding to the material type, wherein the detection configuration information comprises size data and image acquisition parameters of the to-be-identified material; controlling the mechanical arm to move from a preset shooting position to a target acquisition position matched with the to-be-identified material, and controlling the parameter of the image acquisition module to be adjusted into an image acquisition parameter so as to acquire a second image of the to-be-identified material; and obtaining a second image, and detecting whether the to-be-identified material is qualified based on the second image. High-precision image acquisition and quality inspection are performed on different types of materials, so that the production efficiency is effectively improved, the detection quality of products is guaranteed, and the operation cost of enterprises is reduced.

Description

Technical Field

[0001] The present application relates to the field of intelligent manufacturing, and specifically to a material identification method, device, equipment and storage medium. Background Art

[0002] Incoming material quality control is a critical checkpoint before the property rights of goods are transferred, which directly affects the loss of subsequent processing and the product experience of users. Large industrial production workshops have many types of incoming materials and large quantities. Most material inspections rely on manual sampling. The workload of full inspection and quality inspection is large, there are many inspection items, and the inspection time of manual inspection is long. It is difficult for quality inspectors to maintain their status and it is easy to miss inspections. The inspection standards of different workers are not unified, and the consistency of product quality is poor. Data is easily lost through manual recording, and data sharing and analysis cannot be achieved. Machine vision technology has the advantages of high efficiency and accuracy, non-contact, real-time monitoring, and high reliability, which can greatly improve production efficiency and reduce quality risks.

[0003] In the prior art, a fixed-station machine vision recognition system is usually used to set up a camera at a fixed position to collect images of materials and perform recognition. If there are multiple materials, the detection configuration, camera height, light brightness and other environmental parameters are manually changed. However, this adjustment method requires professional engineers to operate, and it takes a long time and is difficult to adjust various configurations for different material detection. It cannot meet the needs of massive component warehousing detection. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a material identification method, device, equipment and storage medium.

[0005] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a material identification method, comprising:

[0006] After the material to be identified arrives at the designated position, the robot arm is controlled to move to a preset shooting position, and the image acquisition module installed on the robot arm is controlled to acquire a first image of the material to be identified;

[0007] Determining the material type of the material to be identified through the first image;

[0008] Calling detection configuration information corresponding to the material type, the detection configuration information includes the size data and image acquisition parameters of the material to be identified;

[0009] Controlling the robotic arm to move from a preset shooting position to a target acquisition position matching the material to be identified, and controlling the parameters of the image acquisition module to be adjusted to the image acquisition parameters to acquire a second image of the material to be identified;

[0010] A second image is acquired, and based on the second image, it is detected whether the material to be identified is qualified.

[0011] In an embodiment of the present application, the detection configuration information also includes detection content for the material to be identified, obtaining a second image, and detecting whether the material to be identified is qualified based on the second image, including: obtaining the second image, calling the detection module corresponding to each detection content to detect whether each detection content of the material to be identified is qualified based on the second image; when all the detection contents are qualified, determining that the material to be identified is qualified; when there is at least one detection content that is unqualified, determining that the material to be identified is unqualified.

[0012] In an embodiment of the present application, the method further includes: when it is determined that the material to be identified is unqualified, transferring the material to be identified to a place where unqualified materials are placed; or when it is determined that the material to be identified is qualified, starting detection of the next material to be identified.

[0013] In an embodiment of the present application, the preset shooting position is the uppermost limit of the lifting module, and the robotic arm is lifted up and down by the lifting module.

[0014] In an embodiment of the present application, the method also includes: for any material, obtaining the optimal acquisition position set for the material; converting the optimal acquisition position into a position in the coordinate system where the robotic arm is located as the target acquisition position for the material; recording the acquisition movement path and the target acquisition position between the default initial position and the target acquisition position; the method also includes: after controlling the robotic arm to move from a preset shooting position to a target acquisition position matching the material to be identified, controlling the robotic arm to move from the target acquisition position to the default initial position according to the acquisition movement path, and controlling the image acquisition module to capture a second image of the material to be identified with the image acquisition parameters during the movement.

[0015] In an embodiment of the present application, the method also includes: obtaining the real-time position of the robotic arm while controlling the robotic arm to move from the target collection position to the default initial position according to the collection movement path; controlling the robotic arm according to the deviation data between the real-time position and the collection movement path so that the movement route of the robotic arm approaches the collection movement path.

[0016] In an embodiment of the present application, the method also includes: for any material, determining the inspection content for the material; determining the image inspection area for each inspection content and performing image annotation, and setting the inspection parameters for each inspection content; detecting whether the material to be identified is qualified based on the second image includes: verifying whether the image inspection area corresponding to each inspection content in the second image is qualified according to the inspection parameters of each inspection content, so as to detect whether the material to be identified is qualified.

[0017] In an embodiment of the present application, the method further includes: for any one of the detection contents, when it is determined that the detection content is unqualified, marking a position in the second image based on the image detection image corresponding to the detection content.

[0018] A second aspect of the present application provides a material identification device, comprising:

[0019] a memory configured to store instructions;

[0020] A processor is configured to call instructions from a memory and implement any of the above-mentioned material identification methods when executing the instructions.

[0021] A third aspect of the present application provides a material identification device, including:

[0022] A mechanical arm, on which an image acquisition module is installed, the image acquisition module is used to acquire a first image of a material to be identified;

[0023] A robot controller, used to control the movement of the robot based on instructions from the industrial computer;

[0024] The material identification device in the above embodiment includes the industrial computer.

[0025] In an embodiment of the present application, the equipment also includes: a lifting module, a robotic arm is installed on the lifting module to be lifted up and down through the lifting module, wherein the preset shooting position is the upper limit of the lifting module; and / or a defective product accommodating device for placing unqualified materials to be identified.

[0026] In an embodiment of the present application, the image acquisition module includes: an image acquisition device, used to acquire a first image of a material to be identified; and a light source, used to adjust the brightness of light during the shooting process of the image acquisition device.

[0027] In an embodiment of the present application, the image acquisition module also includes: a first bracket for installing the image acquisition device, and the first bracket is rotatable; a second bracket for installing the light source, and the first bracket is detachable and rotatable, wherein there are multiple light sources, and the first bracket is installed in the central area of ​​the multiple light sources.

[0028] In an embodiment of the present application, the device also includes: a conveyor belt, used to connect the production line, transport the material to be identified to a designated location, and / or transfer the material to be identified to a place where unqualified materials are placed when it is determined that the material to be identified is unqualified; and / or a display device, used to provide a human-computer interaction interface, so that the user can configure the image acquisition parameters and / or detection content for each material through the human-computer interaction interface, and display the detection results of the material.

[0029] In an embodiment of the present application, the device also includes: a cabinet, in which the industrial computer is installed; a heat dissipation device, installed on the outside of the cabinet, for dissipating heat for internal components in the cabinet; and / or a mobile component, installed at the bottom of the cabinet, for facilitating the movement of the cabinet.

[0030] In an embodiment of the present application, the device further includes: a button assembly installed on the outside of the cabinet, the button assembly includes a plurality of control buttons for the user to operate the material identification device.

[0031] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configure the processor to execute the above-mentioned material identification method.

[0032] In this solution, after the material to be identified reaches the designated position, the robot arm is controlled to move to the preset highest shooting position, and the image acquisition module installed on the robot arm is controlled to capture the first image of the material to be identified at this position, which can ensure that materials of almost all sizes can be successfully captured. After determining the material type of the material to be identified through the first image, the detection configuration information corresponding to the material type can be called, and the robot arm can be controlled to move from the preset shooting position to the target acquisition position matching the material to be identified. At the same time, the parameters of the image acquisition module are controlled to be adjusted to the image acquisition parameters, so that the second image of the material to be identified can be captured at the best shooting position matching the material. The second image can be obtained later, and whether the material to be identified is qualified can be detected based on the second image. In this solution, a high-precision camera is combined with a mechanical motion control system module, making full use of the high-precision, high-frame rate, and dynamic scanning characteristics of camera imaging technology, combined with the precise shooting position and adjustable lighting environment provided by the motion module, high-precision image acquisition and quality inspection can be performed for different types of materials, effectively improving production efficiency, ensuring product inspection quality, and reducing enterprise operating costs.

[0033] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0035] Figure 1 A schematic diagram of a material identification device according to an embodiment of the present application is shown schematically;

[0036] Figure 2 The following is a schematic diagram showing a flow chart of a material identification method according to an embodiment of the present application;

[0037] Figure 3 A schematic diagram of a material configuration process according to an embodiment of the present application is shown schematically;

[0038] Figure 4 The structural diagram of the material identification device according to a specific embodiment of the present application is schematically shown;

[0039] Figure 5 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application, and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0041] The material identification method provided in this application can be applied to Figure 1 The material identification device 100 shown in the figure. The material identification device 100 includes a mechanical arm 101, a mechanical arm controller 102 and a material identification device 103. An image acquisition module is installed on the mechanical arm 101, and the image acquisition module is used to acquire a first image of the material to be identified. The mechanical arm controller 102 is used to control the movement of the mechanical arm based on the instructions issued by the industrial computer. After the material to be identified arrives at the specified position, the material identification device 103 can control the mechanical arm 101 to move to a preset shooting position through the mechanical arm controller 102, and control the image acquisition module installed on the mechanical arm 101 to acquire a first image of the material to be identified, and after determining the material type of the material to be identified through the first image, call the detection configuration information corresponding to the material type, and control the mechanical arm 101 to move from the preset shooting position to the target acquisition position matching the size data through the mechanical arm controller 102, and control the parameters of the image acquisition module to be adjusted to the image acquisition parameters to acquire a second image of the material to be identified, and then obtain the second image, and detect whether the material to be identified is qualified based on the second image.

[0042] Figure 2 The following schematically shows a flow chart of a material identification method according to an embodiment of the present application. Figure 2 As shown, in one embodiment of the present application, a material identification method is provided. This embodiment mainly applies the method to the above Figure 1The material identification device 103 in the embodiment of the present invention is used as an example, wherein the material identification device 103 includes a memory and a processor. Specifically, the material identification method includes the following steps:

[0043] Step 202: After the material to be identified arrives at the designated position, the robot arm is controlled to move to a preset shooting position, and the image acquisition module installed on the robot arm is controlled to acquire a first image of the material to be identified.

[0044] Step 204: determine the material type of the material to be identified through the first image.

[0045] Step 206, calling the detection configuration information corresponding to the material type, the detection configuration information includes the size data of the material to be identified, the image acquisition parameters and the detection content.

[0046] Step 208, controlling the robot arm to move from the preset shooting position to the target acquisition position matching the size data, and controlling the parameters of the image acquisition module to be adjusted to the image acquisition parameters to acquire a second image of the material to be identified.

[0047] Step 210, acquiring a second image, and detecting whether the material to be identified is qualified based on the second image.

[0048] When the material is identified for storage, it can be first transported to the designated location by a conveyor belt or a transport device (AGV), etc. The preliminary preparation process of the material is not limited here, as long as the material reaches the designated location. For the convenience of description, the material currently being identified can be referred to as the material to be identified. After the material to be identified arrives at the designated location, the processor can control the mechanical arm to move to a preset shooting position, and then control the image acquisition module installed on the mechanical arm to capture the first image of the material to be identified. Specifically, when the processor controls the mechanical arm, it can indirectly control the mechanical arm through the mechanical arm controller. For example, the processor can send a corresponding control instruction to the mechanical arm controller, and then the mechanical arm controller can respond to the control instruction to control the mechanical arm to complete the corresponding operation. The mechanical arm can realize the up and down lifting operation through the lifting module. In this embodiment, the preset shooting position can be the upper limit of the lifting module, that is, the highest point that the mechanical arm can reach. When the mechanical arm reaches the highest point, the shooting field of the image acquisition module installed on the mechanical arm is the largest. That is to say, at this time, the image acquisition module on the mechanical arm can capture the largest area. After the processor controls the mechanical arm to move to the highest limit of the lifting module, it can further control the image acquisition module installed on the mechanical arm to start acquiring the material image of the material to be identified. When the image acquisition module acquires the image, the zoom lens included therein can automatically adjust the focal length, and the light source included therein can automatically adjust the brightness, so as to better acquire the material image of the material to be identified. For the convenience of distinguishing descriptions, the material image acquired by the image acquisition module when the mechanical arm is at the highest point at this time can be referred to as the first image.

[0049] Further, the processor can determine the material type of the material to be identified through the first image. Specifically, the processor can input the first image into the classification recognition model, and the classification recognition model can output the material code of the material to be identified, and then the material type of the material to be identified can be determined based on the material code. It is understandable that before the classification recognition model is put into actual use, the classification recognition model can be trained so that the model can identify the type of material. For the training process of the classification recognition model, reference can be made to the training method for the classification model in the prior art, which is not limited here.

[0050] After determining the material type of the material to be identified according to the first image, the processor can call the detection configuration information corresponding to the material type. Among them, the detection configuration information includes the size data, image acquisition parameters and detection content of the material to be identified. There can be multiple detection contents, and the detection contents involved can be different for different materials, which can be set by technicians according to actual needs. The processor can control the mechanical arm to move from a preset shooting position to a target acquisition position matching the size data through a mechanical arm controller. That is, after determining the material type of the material to be identified, the processor can control the mechanical arm to move from the highest point at the beginning to the target acquisition position matching the size data of the material to be identified. Then, the parameters of the image acquisition module can be controlled to be adjusted to the image acquisition parameters included in the detection configuration information corresponding to the material type of the material to be identified, that is, the parameters of the image acquisition module are adjusted to the parameters matching the material to be identified, and then the material image of the material to be identified can be collected. In order to facilitate the distinction and description, the material image collected by the image acquisition module when the mechanical arm is at the target acquisition position matching the size data of the material to be identified can be called the second image. Then, the processor can obtain the second image captured by the image acquisition module, and detect whether the material to be identified is qualified based on the second image.

[0051] In one embodiment, obtaining a second image and detecting whether the material to be identified is qualified based on the second image includes: obtaining the second image, calling the detection module corresponding to each detection content to detect whether each detection content of the material to be identified is qualified based on the second image; when all the detection contents are qualified, determining that the material to be identified is qualified; when there is at least one detection content that is unqualified, determining that the material to be identified is unqualified.

[0052] After acquiring the second image, the processor can call the detection module corresponding to each detection content, and then the detection module can detect whether each detection content of the material to be identified is qualified based on the second image. For example. Assume that the detection content includes appearance without impurities, appearance without scratches, etc. Then the detection module 1 that specifically detects stains can be called to detect whether there are stains on the external surface of the material to be identified based on the second image, and the detection module 2 that is specifically used to monitor whether there are scratches on the appearance can be called to detect whether there are scratches on the external surface of the material to be identified. If the detection module 1 for detecting stains determines that there are stains on the material to be identified, it can be determined that the appearance of the material to be identified has impurities, and the item of appearance without impurities is unqualified. If the detection module 2 for detecting scratches determines that there are no scratches on the material to be identified, then the item of appearance without impurities is qualified. In this case, there is at least one detection content that is unqualified, and at this time, it can be determined that the material to be identified is unqualified. In other words, the test results of all the detection contents of the material to be detected are required to be qualified before the material to be identified is considered qualified.

[0053] In one embodiment, the method further includes: if it is determined that the material to be identified is unqualified, transferring the material to be identified to a place where unqualified materials are placed; or if it is determined that the material to be identified is qualified, starting detection of the next material to be identified.

[0054] In this embodiment, if it is determined that the material to be identified is unqualified, the material to be identified that is detected as unqualified can be transferred to a place where unqualified materials are placed, such as a defective box, based on a conveyor belt or other transmission device. Conversely, if it is determined that the material to be identified is qualified, the material to be identified that is detected as qualified can also be transferred to a designated area, and the detection process for the next material to be identified can be started at the same time.

[0055] In one embodiment, the method further includes: for any material, obtaining the best acquisition position set for the material; converting the best acquisition position into a position in the coordinate system where the robot is located as the target acquisition position for the material; recording the acquisition movement path between the default initial position and the target acquisition position and the target acquisition position. The method further includes: after controlling the robot to move from the preset shooting position to the target acquisition position matching the material to be identified, controlling the robot to move from the target acquisition position to the default initial position according to the acquisition movement path, and controlling the image acquisition module to capture a second image of the material to be identified with the image acquisition parameters during the movement.

[0056] Before starting to identify materials for storage, you can complete the preliminary preparations. Figure 3As shown, for each material, the best acquisition position set for the material can be obtained first. The best acquisition position can be a position determined in advance, for example, the best shooting position for the material determined in advance by the technician according to the size of the material. Then, the processor can convert the best acquisition position into a position in the coordinate system where the robot arm is located, and use it as the target acquisition position for the material. Further, the processor can record the target acquisition position and the acquisition movement path of the robot arm from the default initial position to the target acquisition position. Subsequently, when the material is identified for warehousing, after the material type of the material to be identified is determined, the target acquisition position corresponding to the material to be identified can be determined. Therefore, the processor can first control the robot arm to move from the preset shooting position to the target acquisition position matching the material to be identified through the robot arm controller, and then control the parameters of the image acquisition module installed on the robot arm to be adjusted to the image acquisition parameters corresponding to the material to be identified, so that the second image of the material to be identified can be acquired by the image acquisition module after the parameters are adjusted.

[0057] In one embodiment, the method also includes: obtaining the real-time position of the robotic arm while controlling the robotic arm to move from the target acquisition position to the default initial position according to the acquisition movement path; controlling the robotic arm according to the deviation data between the real-time position and the acquisition movement path so that the movement route of the robotic arm approaches the acquisition movement path.

[0058] The processor can obtain the position of the robotic arm in real time when the robotic arm controller controls the robotic arm to move from the target collection position to the default initial position according to the collection movement path. Then, the deviation data between the real-time position of the robotic arm and the previously determined collection movement path is determined, and the robotic arm is controlled by the deviation data so that the movement route of the robotic arm is as close as possible to the predetermined collection movement path, so as to correct and control the movement path of the robotic arm.

[0059] In one embodiment, the method also includes: for any material, determining the inspection content for the material; determining the image inspection area for each inspection content and performing image annotation, and setting the inspection parameters for each inspection content; detecting whether the material to be identified is qualified based on the second image includes: verifying whether the image inspection area corresponding to each inspection content in the second image is qualified according to the inspection parameters of each inspection content, so as to detect whether the material to be identified is qualified.

[0060] For any material, the inspection content for the material can be formulated and determined in advance according to the inspection requirements for the material. It is understandable that if the inspection content is different, the region of interest (ROI) of the material image for the material will also be different. Therefore, for each inspection content, you can first determine the image inspection area corresponding to each inspection content, and then perform image annotation. At the same time, you can also set the inspection parameters for each inspection content, and then save them to the cloud for subsequent use. After all the settings are completed, if Figure 3 As shown in the figure, it can be determined that the detection function configuration process for the material is completed. If there are multiple materials, then for each material, you can execute the following Figure 3 The configuration process shown. For example, if the detection content is whether the size and appearance are scratch-free, then the detection parameters are also related to whether the appearance has scratches. Then, when the subsequent processor detects whether the material to be identified is qualified based on the second image, it can verify whether the image detection area corresponding to each detection content in the second image is qualified according to the detection parameters of each detection content, so as to detect whether the material to be identified is qualified. If at least one detection content is unqualified, the material to be identified is determined to be an unqualified material. On the contrary, if all the detection contents are qualified, then it can be determined that the material to be identified is a qualified material.

[0061] In one embodiment, the method further includes: for any one of the detection contents, when it is determined that the detection content is unqualified, marking a position in the second image according to the image detection image corresponding to the detection content.

[0062] During the process of warehousing identification of the material to be identified, if any of the detection contents is detected to be unqualified, the processor can mark the position in the second image according to the image detection image corresponding to the detection content. That is, the area detected as unqualified can be marked in the second image. For example, for unqualified positions, they can be marked with a red rectangular frame, and the unqualified information can be marked in red and displayed at the top of the display interface. For qualified positions, green rectangular frames can be used for marking, and then the detection information is displayed on the display interface according to the detection order of the detection content, and then the detection results are output, and the detection results include qualified and unqualified.

[0063] In this solution, after the material to be identified reaches the designated position, the robot arm is controlled to move to the preset highest shooting position, and the image acquisition module installed on the robot arm is controlled to capture the first image of the material to be identified at this position, which can ensure that materials of almost all sizes can be successfully captured. After determining the material type of the material to be identified through the first image, the detection configuration information corresponding to the material type can be called, and the robot arm can be controlled to move from the preset shooting position to the target acquisition position matching the material to be identified. At the same time, the parameters of the image acquisition module are controlled to be adjusted to the image acquisition parameters, so that the second image of the material to be identified can be captured at the best shooting position matching the material. The second image can be obtained later, and whether the material to be identified is qualified can be detected based on the second image. In this solution, a high-precision camera is combined with a mechanical motion control system module, making full use of the high-precision, high-frame rate, and dynamic scanning characteristics of camera imaging technology, combined with the precise shooting position and adjustable lighting environment provided by the motion module, high-precision image acquisition and quality inspection can be performed for different types of materials, effectively improving production efficiency, ensuring product inspection quality, and reducing enterprise operating costs.

[0064] In one embodiment, the material identification device 100 further includes: a lifting module, the mechanical arm is installed on the lifting module to be lifted up and down through the lifting module, wherein the preset shooting position is the highest limit of the lifting module. The material identification device 100 may also include a defective product receiving device for placing the unqualified materials to be identified.

[0065] In one embodiment, the image acquisition module installed on the robot arm 101 includes an image acquisition device and a light source. The image acquisition device is used to acquire a first image of the material to be identified. The light source is used to adjust the brightness of the light during the shooting process of the image acquisition device.

[0066] In one embodiment, the image acquisition module installed on the robot arm 101 further includes a first bracket and a second bracket. The first bracket is used to install the image acquisition device, and the first bracket is rotatable. The second bracket is used to install the light source, and the first bracket is detachable and rotatable. Furthermore, there are multiple light sources, and the first bracket is installed in the central area of ​​the multiple light sources.

[0067] In one embodiment, the material identification device 100 further includes a conveyor belt and / or a display device. The conveyor belt is used to connect the production line, convey the material to be identified to a designated location, and / or transfer the material to be identified to a location where the unqualified material is placed when the material to be identified is determined to be unqualified. The display device is used to provide a human-computer interaction interface, so that the user can configure the image acquisition parameters and / or detection content for each material through the human-computer interaction interface, and display the detection results of the material.

[0068] In one embodiment, the material identification device 100 further includes a cabinet, a heat dissipation device and / or a mobile component. The industrial computer is installed in the cabinet. The heat dissipation device is installed on the outside of the cabinet to dissipate heat for the internal components in the cabinet. The mobile component is installed at the bottom of the cabinet to facilitate the movement of the cabinet.

[0069] In one embodiment, the material identification device 100 further includes a button assembly, which is installed outside the cabinet. The button assembly includes a plurality of control buttons for the user to operate the material identification device.

[0070] In a specific embodiment, Figure 4 A material identification device is shown. The material identification device includes a frame 1, a lifting module 2, a mechanical arm 5, a mounting base 6, a cabinet platform 7, a belt conveyor 8, a belt disassembly module 9, a waste rejection module 10, a defective material frame 11, a light source 12, a camera 13, a display screen 14, an industrial computer 15, a light source controller 16, a robot controller 17 (i.e., a mechanical arm controller), a locking pulley 18, and a button area 19. The reference numeral 3 in the figure indicates the upper limit position of the lifting module 2, and the reference numeral 4 indicates the lower limit position of the lifting module 2.

[0071] Specifically, the frame 1 is mounted on the mounting base 6 for fixing the overall structure. The robot arm 5 is mounted on the lifting module 2, and the robot arm can be raised and lowered based on the lifting module 2, so that the range of motion of the robot arm can be increased and it is beneficial to retract after resetting. The upper limit position 3 of the lifting is the highest limit position of the robot arm, and the lower limit position 4 of the lifting is the lowest limit position of the robot arm. The lifting module 2 is mounted and fixed on the frame 1. The cabinet platform 7 is mounted on the mounting base 6. The cabinet platform 7 can be a system integrated electric control cabinet. Electrical components such as the industrial computer 15, the light source controller 16, and the robot controller 17 can all be installed in the cabinet platform 7. The upper surface of the cabinet platform 7 can be used as a material detection platform. The material can be placed on its upper surface for detection, which can be used for a quality detection environment for manual auxiliary loading and unloading.

[0072] The belt conveyor 8 is composed of a conveyor belt, a driving device, a supporting device, etc., and is supported by a belt disassembly module 9 above the cabinet platform. The conveyor belt is supported when it is running, and its main function is to connect the production line and to be used for material conveying and real-time detection platform. Among them, the belt disassembly module 9 is used to quickly dismantle the belt disassembly module 9 and the belt conveyor 8 when the detection environment does not need to be docked with the production line. The waste rejection module 10 is installed above the cabinet platform 7, slightly higher than the belt conveyor 8, and is used to reject unqualified materials detected above the conveyor belt. The rejected unqualified products are pushed into the unqualified material frame 11 for caching unqualified products. The light source 12 is installed on the light source bracket, and the camera 13 is installed on the camera bracket. The camera is at the center of the four strip light sources. The camera and the light source bracket can adjust the angle. The two brackets are stacked and installed at the end of the seventh-axis robot arm. The motion mechanism adopts a collaborative robot + seventh-axis control to achieve precision, accuracy, and lightness requirements, and extremely low energy consumption. Specifically, the light source 12 can be composed of four strip light sources in a square layout. The connection lines of the camera 13 and the light source 12 and the lifting structure control line are fixed on the robot arm 5 through the cashing tube, the light source 12 is connected to the light source controller 16, the light source serial port communication line is connected to the built-in industrial computer 15, the acquisition line of the camera 13 is connected to the industrial computer 15, and the collaborative robot is connected to the visual system communication line.

[0073] The display screen 14 can be a display touch screen, which is installed on the front side of the cabinet platform 7. The display and touch line connection lines of the display screen 14 are fixedly installed on the display touch screen bracket through the cashing tube, and are connected to the industrial computer 15, which is used to display the human-machine interaction interface of the detection system and operate the industrial computer 15. The light source controller 16 and the robot controller 17 are installed inside the cabinet platform 7. The industrial computer 15 is used for the efficient and stable operation of the visual detection system, and real-time processing and analysis of image data. The light source controller 16 is used to power the light source, control the brightness of the light source and control the lighting state of the light source; the robot controller 17 is used to control the movement and action of the industrial robot, and can also calculate and plan the path of the robot to ensure the precision and accuracy of the robot during the work process. The heat dissipation device can be a heat dissipation fan (not shown in the middle), which can be installed on the rear side of the cabinet platform for heat dissipation of internal electronic equipment. The moving component is a locking pulley 18, which can be a caster foot cup of the cabinet platform 7, which is convenient for moving the cabinet. The button area 19 includes a multi-button component, which is installed on the outside of the cabinet of the cabinet platform 7. Specifically, it can be installed above the cabinet platform 7, and the button assembly includes multiple control buttons such as start / stop, emergency stop, safety switch, etc., which are convenient for operators to operate.

[0074] Figure 2 FIG. 1 is a flow chart of a material identification method in one embodiment. It should be understood that although Figure 2The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0075] In one embodiment, a material identification device is provided, comprising:

[0076] a memory configured to store instructions; and

[0077] A processor is configured to call instructions from a memory and implement the material identification method according to any one of the above embodiments when executing the instructions.

[0078] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and the material identification method can be implemented by adjusting kernel parameters.

[0079] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0080] An embodiment of the present application provides a storage medium on which a program is stored, and when the program is executed by a processor, the above-mentioned material identification method is implemented.

[0081] An embodiment of the present application provides a processor, which is used to run a program, wherein the material identification method is executed when the program is run.

[0082] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a material identification method has been implemented.

[0083] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0084] An embodiment of the present application provides a computer (electronic) device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps of any of the above material identification methods are implemented.

[0085] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the material identification method steps.

[0086] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The present application is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0090] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0091] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0092] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0093] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0094] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A material identification method, characterized in that: The method comprises: After the material to be identified arrives at the designated position, the mechanical arm is controlled to move to a preset shooting position, and the image acquisition module installed on the mechanical arm is controlled to acquire a first image of the material to be identified; Determining the material type of the material to be identified through the first image; Calling detection configuration information corresponding to the material type, the detection configuration information including size data and image acquisition parameters of the material to be identified; Controlling the robotic arm to move from the preset shooting position to a target acquisition position matching the material to be identified, and controlling the parameters of the image acquisition module to be adjusted to the image acquisition parameters, so as to acquire a second image of the material to be identified; The second image is acquired, and based on the second image, it is detected whether the material to be identified is qualified.

2. The material identification method according to claim 1, characterized in that: The detection configuration information also includes detection content for the material to be identified, and the acquiring of the second image and detecting whether the material to be identified is qualified based on the second image includes: Acquire the second image, and call the detection module corresponding to each detection content to detect whether each detection content of the material to be identified is qualified based on the second image; When all the test contents are qualified, the material to be identified is determined to be qualified; In the case where at least one of the detection contents is unqualified, it is determined that the material to be identified is unqualified.

3. The material identification method according to claim 1, characterized in that: The method further comprises: If it is determined that the material to be identified is unqualified, the material to be identified is transferred to a place where unqualified materials are placed; or When it is determined that the material to be identified is qualified, the detection of the next material to be identified is initiated.

4. The material identification method according to claim 1, characterized in that: The preset shooting position is the uppermost limit position of the lifting module, and the mechanical arm is lifted up and down through the lifting module.

5. The material identification method according to claim 1, characterized in that: The method further comprises: For any material, obtaining the best collection position set for the material; Converting the optimal collection position into a position in the coordinate system where the robot arm is located as a target collection position for the material; Recording the collection movement path between the default initial position and the target collection position and the target collection position; The method further comprises: After controlling the robotic arm to move from the preset shooting position to the target acquisition position matching the material to be identified, the robotic arm is controlled to move from the target acquisition position to the default initial position according to the acquisition movement path, and during the movement, the image acquisition module is controlled to acquire a second image of the material to be identified with the image acquisition parameters.

6. The material identification method according to claim 5, characterized in that: The method further comprises: In the process of controlling the mechanical arm to move from the target acquisition position to the default initial position according to the acquisition movement path, obtaining the real-time position of the mechanical arm; The robot arm is controlled according to the deviation data between the real-time position and the acquisition movement path, so that the movement route of the robot arm approaches the acquisition movement path.

7. The material identification method according to claim 1, characterized in that: The method further comprises: For any material, determine the testing content for the material; Determine the image detection area for each detection content and perform image annotation, and set the detection parameters for each detection content; Detecting whether the material to be identified is qualified based on the second image includes: Whether the image detection area corresponding to each detection content in the second image is qualified is verified according to the detection parameters of each detection content, so as to detect whether the material to be identified is qualified.

8. The material identification method according to claim 7, characterized in that: The method further comprises: For any one of the detection contents, when it is determined that the detection content is unqualified, a position mark is performed in the second image according to an image detection image corresponding to the detection content.

9. A material identification device, characterized in that: include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the material identification method according to any one of claims 1 to 8 when executing the instructions.

10. A material identification device, characterized in that: The device comprises: A mechanical arm, wherein an image acquisition module is installed on the mechanical arm, and the image acquisition module is used to acquire a first image of a material to be identified; A robot arm controller, used to control the movement of the robot arm based on instructions issued by the industrial computer; According to the material identification device of claim 9, the material identification device includes the industrial computer.

11. The material identification device according to claim 10, characterized in that: The device also includes: A lifting module, the mechanical arm is installed on the lifting module to be lifted up and down by the lifting module, wherein the preset shooting position is the highest limit position of the lifting module; and / or The defective product holding device is used to place unqualified materials to be identified.

12. The material identification device according to claim 10, characterized in that: The image acquisition module comprises: An image acquisition device, used for acquiring a first image of the material to be identified; The light source is used to adjust the brightness of light during the shooting process of the image acquisition device.

13. The material identification device according to claim 12, characterized in that: The image acquisition module also includes: A first bracket, used for mounting the image acquisition device, and the first bracket is rotatable; The second bracket is used to install the light source, and the first bracket is detachable and rotatable, wherein there are multiple light sources, and the first bracket is installed in the central area of ​​the multiple light sources.

14. The material identification device according to claim 10, characterized in that: The device also includes: A conveyor belt is used to connect the production line, convey the material to be identified to a designated location, and / or if the material to be identified is determined to be unqualified, transfer the material to be identified to a location where unqualified materials are placed; and / or The display device is used to provide a human-computer interaction interface so that the user can configure the image acquisition parameters and / or detection content for each material through the human-computer interaction interface, and display the detection results of the material.

15. The material identification device according to claim 10, characterized in that: The device also includes: A cabinet, in which the industrial computer is installed; A heat dissipation device, installed outside the cabinet, for dissipating heat for internal components in the cabinet; and / or The moving assembly is installed at the bottom of the cabinet to facilitate the movement of the cabinet.

16. The material identification device according to claim 15, characterized in that: The device also includes: A button assembly is installed on the outside of the cabinet, and the button assembly includes a plurality of control buttons for a user to operate the material identification device.

17. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the material identification method according to any one of claims 1 to 8.

Images