CN114801100A - Injection molding sorting unit - Google Patents

Abstract

The embodiment of this specification provides a sorting device for injection molded products, which includes a controller, a sample conveying channel, a quality detection unit, and a plurality of sample sorting channels. The sample conveying channel is used to transport the injection molded products produced by the injection molding machine to the quality inspection unit. The quality inspection unit is used to inspect the quality of injection molded products. Each sample sorting channel in the plurality of sample sorting channels is used to transport the injection-molded products that have completed the quality inspection to the corresponding storage space.

Description

A sorting device for injection molded products

technical field

This specification relates to the technical field of injection molding production, in particular to a sorting device for injection molding products.

Background technique

Injection molding is a common production method for industrial products. With the wide use of injection molding products, the rapid development of injection molding industry and the continuous strengthening of product competition, people have higher and higher requirements for the quality and performance of injection molding products. After the injection molding is completed, the production personnel need to judge the quality of the injection molded products to know whether there are defects in the injection molded products, such as short shots, shrinkage, bending, drape, cracks, scars and other abnormal conditions. In actual production, it is difficult for production personnel to directly judge the quality of injection molded products, and follow-up testing is required.

Therefore, it is necessary to propose a sorting device for injection molded products, which can reduce unnecessary labor input and improve the accuracy of quality inspection of injection molded products.

SUMMARY OF THE INVENTION

One of the embodiments of this specification provides a sorting device for injection molded products. The injection molding product sorting device includes: a controller, a sample conveying channel, a quality detection unit, and a plurality of sample sorting channels. The sample conveying channel is used for transporting the injection molded products produced by the injection molding machine to the quality inspection unit, and the quality inspection unit is used for inspecting the quality of the injection molded products, and each of the plurality of sample sorting channels Each sample sorting channel is used to transport the injection-molded product that has completed the quality inspection to the corresponding storage space.

In some embodiments, the quality inspection unit is provided with a camera device and a rotating stage. The rotary table is used for placing the injection-molded product, and the camera device is used for capturing product images of the injection-molded product at multiple angles for quality inspection based on the rotation of the rotary table.

In some embodiments, the quality detection unit is provided with a quality parameter detection device. The quality parameter testing equipment is used for testing the quality of the injection molded product.

In some embodiments, the controller is configured to count the product quantities of the injection molded products corresponding to various quality inspection results, and send early warning information to the injection molding machine or the production personnel terminal based on the statistical results of the product quantities.

Description of drawings

The present specification will be further described by way of example embodiments, which will be described in detail with reference to the accompanying drawings. These examples are not limiting, and in these examples, the same numbers refer to the same structures, wherein:

FIG. 1 is an application scenario diagram of the injection molding product sorting device according to some embodiments of the present specification;

FIG. 2 is an exemplary illustration of an injection molding product sorting device according to some embodiments of the present specification;

3 is an exemplary flowchart of determining whether an injection molded product is passed into a quality parameter detection device according to some embodiments of the present specification;

FIG. 4 is an exemplary flowchart of determining a region image according to some embodiments of the present specification;

FIG. 5 is a diagram illustrating an example of a function of a controller according to some embodiments of the present specification.

Detailed ways

In order to illustrate the technical solutions of the embodiments of the present specification more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present specification. For those of ordinary skill in the art, without creative efforts, the present specification can also be applied to the present specification according to these drawings. other similar situations. Unless obvious from the locale or otherwise specified, the same reference numbers in the figures represent the same structure or operation.

It is to be understood that "system", "device", "unit" and/or "module" as used herein is a method used to distinguish different components, elements, parts, parts or assemblies at different levels. However, other words may be replaced by other expressions if they serve the same purpose.

As shown in the specification and claims, unless the context clearly dictates otherwise, the words "a", "an", "an" and/or "the" are not intended to be specific in the singular and may include the plural. Generally speaking, the terms "comprising" and "comprising" only imply that the clearly identified steps and elements are included, and these steps and elements do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

Flowcharts are used in this specification to illustrate operations performed by a system according to an embodiment of this specification. It should be understood that the preceding or following operations are not necessarily performed in the exact order. Instead, the various steps can be processed in reverse order or simultaneously. At the same time, other actions can be added to these procedures, or a step or steps can be removed from these procedures.

The embodiment of this specification relates to a sorting device for injection molded products, which can be used for quality inspection and sorting of injection molded products. It should be noted that the sorting device for injection molded products in this embodiment can also be used for quality inspection of other products. And sorting, such as quality testing and sorting of other types of products such as food, electronic products, etc.

FIG. 1 is an application scenario diagram of a sorting device for injection molded products according to some embodiments of the present specification.

In some embodiments, the application scenario 100 of the injection molding product sorting apparatus may include the computing system 110 , the network 120 , the storage device 130 , the terminal 140 , the injection molding product sorting apparatus 150 , the injection molding machine 160 , and the material 170 .

Computing system 110 may process data and/or information retrieved from storage device 130 . For example, computing system 110 may obtain injection molded article sorting data from storage device 130 . In some embodiments, computing system 110 may process information and/or data related to injection molded article sorting apparatus 150 to perform one or more functions described herein. In some embodiments, computing system 110 may be a single server or a cluster of servers. Server farms may be centralized or distributed (eg, computing system 110 may be a distributed system). In some embodiments, computing system 110 may be local or remote. For example, computing system 110 accesses information and/or data stored in storage device 130 through network 120 . As another example, computing system 110 may connect directly to storage device 130 to access stored information and/or data. In some embodiments, computing system 110 may be implemented through a cloud platform. For example only, cloud platforms may include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, inter-cloud, multi-cloud, etc., or any combination thereof.

In some embodiments, computing system 110 may include one or more computing systems 110 (eg, single-core processors or multi-core processors). By way of example only, computing system 110 may include one or more hardware processors, such as a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction set processor (ASIP), a graphics processor (GPU), a physical Arithmetic Processor (PPU), Digital Signal Processor (DSP), Field Programmable Gate Array (FPGA), Programmable Logic Device (PLD), Controller, Microcontroller Unit, Reduced Instruction Set Computer (RISC), Microprocessor device, etc., or any combination thereof.

Network 120 may be used to facilitate the exchange of information and/or data. In some embodiments, one or more components in scene 100 may send and/or receive information and/or data to/from other components in scene 100 over network 120 . In some embodiments, network 120 may be any form of wired or wireless network or any combination thereof. By way of example only, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an internal network, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), a metropolitan area network (MAN), Public Switched Telephone Network (PSTN), Bluetooth network, Zigbee network, Near Field Communication (NFC) network, Global System for Mobile communications (GSM) network, Code Division Multiple Access (CDMA) network, Time Division Multiple Access (TDMA) network, Universal Packet Radio Service (GPRS) networks, Enhanced Data Rates for GSM Evolution (EDGE) networks, Wideband Code Division Multiple Access (WCDMA) networks, High Speed Downlink Packet Access (HSDPA) networks, Long Term Evolution (LTE) networks, User Datagram Protocol (UDP) network, Transmission Control Protocol/Internet Protocol (TCP/IP) network, Short Message Service (SMS) network, Wireless Application Protocol (WAP) network, Ultra Wideband (UWB) network, Mobile Communication (1G, 2G, 3G) , 4G, 5G) networks, Wi-Fi, Li-Fi, Narrowband Internet of Things (NB-IoT), etc., or any combination thereof.

In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points (eg, base stations and/or Internet exchange points) through which one or more components of scenario 100 may connect to network 120 to exchange data and / or information.

Storage device 130 may be used to store information and/or instructions. In some embodiments, storage device 130 may include mass memory, removable memory, random access memory (RAM), read only memory (ROM), the like, or any combination thereof. Exemplary mass storage may include magnetic disks, optical disks, solid state disks, and the like. Exemplary removable storage may include flash drives, floppy disks, optical disks, memory cards, compact disks, magnetic tapes, and the like. Exemplary random access memory may include dynamic RAM (DRAM), double rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM), zero capacitance RAM (Z-RAM), and the like. Exemplary read-only memories may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (PEROM), electronically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), Digital Universal Disk ROM, etc. In some embodiments, the storage device 130 may be implemented through a cloud platform. By way of example only, cloud platforms may include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, internal clouds, multi-tier clouds, etc., or any combination thereof.

In some embodiments, storage device 130 may be connected to network 120 to communicate with one or more components in scene 100 . One or more components in scenario 100 may access data or instructions stored in storage device 130 via network 120 . In some embodiments, storage device 130 may be directly connected or in communication with one or more components in scene 100 .

Terminal 140 may be a device or other entity directly related to injection molding product sorting data acquisition. In some embodiments, terminal 140 may be a terminal used by a user. For example, terminals used by production personnel, etc. In some embodiments, terminal 140 may be a requester of injection molded article sorting data acquisition. In some embodiments of this specification, "user" and "user terminal" may be used interchangeably. In some embodiments, the user may be an operator or user of the injection molded article sorting apparatus 150, such as a production person, a researcher, or the like. In some embodiments, terminal 140 may include mobile terminal 140-1, tablet computer 140-2, laptop computer 140-3, laptop computer 140-4, etc., or any combination thereof. In some embodiments, the mobile terminal 140-1 may include a smart phone, a smart paging device, etc., or other smart devices. In some embodiments, the terminal 140 may include other smart terminals, such as wearable smart terminals and the like. In some embodiments, the terminal 140 may receive the information uploaded by the injection molding product sorting device 150 through the network 120, such as injection molding product sorting data and the like.

The injection molding product sorting device 150 refers to a device for classifying and screening injection molding products. In some embodiments, the injection molding product sorting device 150 can classify and screen the injection molding products produced by the injection molding machine 160, and transport the sorted injection molding products to the corresponding storage space.

In some embodiments, the injection molded article sorting apparatus 150 may include a controller, a sample delivery channel, a quality detection unit, and a plurality of sample sorting channels. The sample delivery channel may be used to transport the injection molded articles produced by the injection molding machine 160 to the quality inspection unit. The quality inspection unit can be used to inspect the quality of injection molded products. Each sample sorting channel in the plurality of sample sorting channels can be used to transport the injection-molded products that have completed the quality inspection to the corresponding storage space. The controller may be used to receive and/or count information and/or data for injection molded articles to adjust and/or perform one or more functions related to the sorting of injection molded articles. For example, the controller may perform quality inspection on the injection molded product based on the image of the injection molded product. For another example, the controller can count the proportion of injection molded products with quality problems, and adjust the transmission frequency of injection molded products. For the description of the injection molding product sorting device 150, reference may be made to FIG. 2, which will not be repeated here.

The injection molding machine 160 may also be referred to as an injection molding machine or an injection molding machine, and is the main molding equipment for making thermoplastics or thermosetting plastics into various shapes of plastic products using plastic molding dies. Injection molding machines 160 may include, but are not limited to, vertical injection molding machines, horizontal injection molding machines, and all-electric injection molding machines. In some embodiments, the injection molding machine 160 may be composed of a fixed template, a movable template, a pull rod, a mold clamping cylinder, a linkage mechanism, a mold adjustment mechanism, a product exit mechanism, and the like.

The injection molding machine 160 may include a mold 160-1. The mold 160-1 refers to a device for obtaining a product after injecting thermoplastic or thermosetting plastic into the mold. In some embodiments, mold 160 - 1 may be located between uprights on injection molding machine 160 . In some embodiments, the mold 160-1 may be fixed on the injection molding machine 160 by screws, or may be fixed on the injection molding machine 160 by a pressing plate (eg, an automatic pressing plate).

Material 170 refers to an injection molding material for injection molding. The material 170 may include, but is not limited to, ABS plastic, polyamide 6, PBT, PC and other polymer materials. The material 170 can be selected according to the scope of application, for example, for automobiles (such as dashboards, wheel covers, etc.), refrigerators and telephone casings, ABS plastic (terpolymer of acrylonitrile, butadiene and styrene can be selected) thing). For another example, for structural components that need to have good mechanical strength, polyamide 6 can be selected.

It should be noted that the injection molded article sorting apparatus is provided for illustrative purposes only and is not intended to limit the scope of this application. For those skilled in the art, various modifications or changes can be made based on the description of this specification. For example, the injection molded article sorting apparatus may also include an information source. As another example, the injection molding product sorting device may implement similar or different functions on other equipment. However, such changes and modifications do not depart from the scope of this application.

FIG. 2 is an exemplary diagram of a sorting apparatus for injection molded articles according to some embodiments of the present specification.

As shown in FIG. 2 , the injection molding product sorting device 200 includes a controller 210 , a sample conveying channel 220 , a quality detection unit 230 , and a plurality of sample sorting channels 240 . Below is a detailed description of each section.

The controller 210 may be used for data processing. In some embodiments, the controller may include a processor and a storage medium. It can be understood that the storage medium stores corresponding programs and/or instructions, and when the processor reads the corresponding programs and/or instructions, the processor can acquire the data to be processed and perform corresponding processing on it. Further, the data to be processed may come from other components in the injection molding product sorting device (eg, a quality inspection unit, etc.).

In some embodiments, the controller may store a machine learning model, and when the controller performs data processing, the machine learning model (eg, the recognition model 220-1 in FIG. 2 ) may be invoked to process the data to be processed.

The sample delivery channel 220 may be used to transport the injection molded articles produced by the injection molding machine to the quality inspection unit. In some embodiments, the sample delivery channel can be any kind of item transport device, eg, a conveyor belt, a conveyor plate, and the like. For example, injection-molded articles produced by an injection-molding machine can be transported to a quality inspection unit by placing them on a conveyor belt.

Injection molding products refer to products obtained by injection molding raw materials such as resins. For example, the resin raw materials that are heated and melted can be fed into the mold cavity by high pressure through an injection molding machine, and the injection molding products can be obtained after cooling and solidifying. It can be understood that in the process of injection molding products being produced by injection molding machines, various quality problems (such as shrinkage cavities, shrinkage, non-conformity, etc.) saturation, burrs, etc.), so that the injection molding products cannot be used or the use effect is not good.

The quality inspection unit 230 can be used to inspect the quality of the injection molded product, and determine whether there is a quality problem in the injection molded product, or what kind of quality problem there is. In some embodiments, the quality inspection unit may include devices, equipment, and models for inspecting the quality of injection molded products. For example, the quality inspection unit may include a quality inspection instrument, an image analysis device, and an image recognition model.

In some embodiments, the quality inspection unit may be provided with a camera device 230-1 and a rotating stage 230-2. The rotary table is used to place the injection molded products, and the camera device is used to capture the product images of the injection molded products at multiple angles for quality inspection based on the rotation of the rotary table. It can be understood that, through the cooperation of the camera device and the rotary table, images of the injection molded product from multiple angles can be acquired, and then the quality of the injection molded product can be inspected through the images of the injection molded product.

In some embodiments, the camera device may be a camera. In some embodiments, the camera device may include at least two cameras, and through the at least two cameras, images of at least two angles of the injection molded product can be acquired based on at least two position directions.

In some embodiments, the rotary table may include a table surface that can be rotated, eg, a lateral rotary table, whose table surface is rotated in a horizontal direction, and a longitudinal rotary table, whose table surface is rotated in a vertical direction. It can be understood that the table top of the rotary table can be used to place the injection molded products, so that the injection molded products can be rotated horizontally or vertically on the table surface, so that the camera device can capture images of the injection molded products from various angles.

In some embodiments, the quality inspection unit may perform quality inspection through faces corresponding to multiple angles of the injection molded product. It can be understood that, according to the multiple angles actually required, the provided camera captures multiple angles of the injection molded product rotating on the rotary table. For example, a camera is used to photograph the injection molded product during rotation, and images from multiple angles such as front view, rear view, left view, and right view of the injection molded product are obtained.

In some embodiments, the quality inspection unit may be provided with a quality parameter inspection device, which is used to inspect the quality of the injection molded product.

Wherein, the quality parameter testing equipment may be a device or device for testing the quality parameters of injection molded products. In some embodiments, as shown in FIG. 2 , the quality parameter detection device 230-4 may include a density detection device 230-4-1 (for detecting the density of an injection molded product), a hardness detection device 230-4-2 ( For testing the hardness of injection molded products), scanning device 230-4-3 (for testing the appearance of injection molded products) and so on. Wherein, the density detection device may be a density meter; the hardness detection device may be a Shore hardness tester or a hardness tester; and the scanning device may be a scanning electron microscope (SEM, scanning electron microscope).

In some embodiments, the quality parameter corresponding to the injection molded product is detected by the quality parameter detection device by placing the injection molded product in the detection area of the quality parameter detection device. Quality parameters may include, for example, one or more of density parameters, hardness parameters, appearance shape, color, composition, and the like. For example, the injection molded product is placed in the detection area of the density meter to measure the density parameter of the injection molded product. For another example, the injection molded product is placed in the detection area of the hardness tester, and the hardness parameter of the injection molded product is measured based on the hardness tester. For another example, the injection-molded product is placed in the scanning area of the scanning electron microscope, and then the injection-molded product is scanned and inspected to obtain shape parameters, composition parameters, and the like.

In some embodiments, the quality detection unit further includes: a sample detection channel, and the sample detection channel is used for conveying the injection molded product of the rotary table to the quality parameter detection device.

The sample detection channel may be a device with an object transmission function. For example, conveyors such as conveyor belts.

In some embodiments, the sample detection channel may be connected to a rotating stage. It can be understood that after the injection molded products in the rotary table complete the image acquisition of multiple angles for quality inspection on the rotary table, the injection molded products can be transferred to the quality parameter inspection equipment (such as density meter, Hardness tester, scanning electron microscope) to test the corresponding quality parameters.

In some embodiments, the sample sorting channel is used to transport the injection-molded product that has completed the quality inspection to the corresponding storage space. In some embodiments, the sample sorting channel may be a device or device with an item transfer function. For example, conveyor belts, conveyor bars.

In some embodiments, the sample sorting channels may include a quality pass channel, a quality problem 1 channel, a quality problem 2 channel, ... a quality problem n channel. It can be understood that, as shown in FIG. 2 , the multiple sample sorting channels 240 include a sample sorting channel 240-1, a sample sorting channel 240-2, a sample sorting channel 240-3, a sample sorting channel 240-4, etc. , multiple samples can be transported to the corresponding storage space according to the quality inspection results when the quality inspection is completed. In some embodiments, each sample sorting channel conveys injection-molded products with the same quality inspection result. For example, the sample sorting channel 240-1 is used to transport injection-molded products with qualified quality to the corresponding storage space, and the sample sorting channel 240-2 can be used to transport the injection molded products with quality problem 1 to the corresponding storage space.

In some embodiments, the quality problems of injection molded products can be divided into various types based on specific product conditions. For example, quality problems of injection molded products may include appearance quality problems (such as burrs, weld lines, cracks, etc.), density quality problems ( If the density exceeds the specified range of the product), the hardness quality problem (such as the hardness exceeds the specified range of the product).

The corresponding storage space may be a storage location for storing injection-molded products corresponding to the detection results, for example, a location for storing injection-molded products with qualified quality, a space for storing injection-molded products with quality problem 1, and the like. It can be understood that each corresponding storage space stores injection molded products with the same quality inspection results. For example, space 1 stores all injection-molded products of qualified quality.

In some embodiments, through the controller 210 , the sample delivery channel 220 , the quality inspection unit 230 , and the multiple sample data channels 240 in FIG. 2 , a multi-directional quality inspection can be performed on the injection molded product, and based on the quality situation (For example, qualified quality, appearance problems, hardness problems, etc.) Classify and store injection molding products. Based on the quality inspection unit 230, a number of inspection parameters of the injection molded products can be conveniently obtained, and the quality inspection of the injection molded products can be performed. manage.

FIG. 3 is an example diagram of quality detection based on a recognition model according to some embodiments of the present specification.

In some embodiments, the controller may be configured to receive an image of the article and perform quality inspection of the injection molded article based on the recognition model. In some embodiments, the quality inspection based on the identification model can detect whether there is a certain type of quality problem in the injection molded product. Shrinkage cavities, weld lines, etc.), it is understandable that the quality inspection results can also be hardness quality problems, density quality problems, etc.

In some embodiments, as shown in FIG. 3 , the recognition model may include a first image recognition model.

In some embodiments, the quality problem of the injection-molded product can be detected through the first image recognition model based on one or more images (eg, images from multiple angles) of the injection-molded product. In some embodiments, based on the first image recognition model The detection results of quality problems obtained by the image recognition model can mainly be the detection results of appearance quality problems, such as cracks/fractures, shrinkage cavities, weld lines and other appearance quality problems in injection molded products.

In some embodiments, the first image recognition model may be a neural network model.

In some embodiments, the input of the first image recognition model may be an image of the injection molded product, for example, multiple angles (eg, front view, rear view, left view, right view) of the injection molded product obtained from a rotating table through a camera device )Image. The output of the first image recognition model may be the current quality situation of the injection molded product, for example, the quality is qualified, there is an appearance quality problem, and the like. In some embodiments, the first image recognition model may further specifically output the type of the existing appearance quality problem, for example, the first image recognition model may output specific problem type labels such as burrs and cracks.

In some embodiments, the first image recognition model may be trained based on sets of labeled training samples. Specifically, the labeled training samples are input into the first image recognition model, and the parameters of the first image recognition model are trained.

In some embodiments, a set of training samples may include images of historical injection molded articles from multiple angles (eg, front view, rear view, left view, right view). In some embodiments, the training samples can be obtained by photographing historical injection molded products on the rotary table by a camera device. In some embodiments, the training samples may also be obtained from stored historical images of historical injection molded products.

In some embodiments, the labels at the time of model training may be the types of quality problems of historical injection molded products (such as acceptable quality, shrinkage cavities, burrs, unsaturated molds, weld lines, silver lines, spray marks, scorch, warpage, Cracking/Breaking, etc.).

In some embodiments, the label may be obtained through manual labeling based on the detection result after the quality inspection of the historical injection molded products through the quality inspection unit, for example, the inspection result obtained by the scanning inspection device.

In some embodiments, the first image recognition model can be trained based on the above-mentioned samples through various methods to update model parameters. For example, training can be based on gradient descent.

In some embodiments, the training ends when the first image recognition model under training satisfies a preset condition. The preset condition may be that the result of the loss function converges or is smaller than a preset threshold, or the like.

According to the above description, the first image recognition model trained based on a large number of training samples can quickly obtain the quality inspection result of the injection molded product and the specific quality problem type by processing the image of the injection molded product. It can improve the efficiency of obtaining injection molded parts with questionable quality and improve the accuracy of problem detection.

In some embodiments, the controller may identify the color of the injection molded product, and based on the color identification result, control the light color when the camera is photographed.

The recognition result may be the actual color exhibited by the injection molded article itself, eg, red, blue, gray, etc.

The light color can be the color of the auxiliary light used by the camera when taking the image of the injection molded product. For example, the illumination color can be made red, yellow, white, etc. based on auxiliary lights.

In some embodiments, the light color can be controlled based on the controller. For example, if the required light color is yellow, the controller can send a control signal to a corresponding light source, such as a yellow light bead, to control it to be turned on.

In some embodiments, the controller may determine the illumination color based on a preset relationship between the injection molded product color and the illumination color. For example, when the injection molded product color is red, the illumination color may be determined to be yellow based on the preset relationship. It can be understood that by using the light color in the preset relationship to illuminate the injection molded product of the corresponding color, a clearer displayed image can be obtained.

The preset relationship may be a preset matching relationship between the color of the injection molded product and the color of the light. If the color of the aforementioned injection molded product is red, the color of the light is yellow. In some embodiments, the preset relationship may be preset manually according to the color matching relationship or historical experience.

Understandably, based on the color of the injection molded product, by adjusting the light color, the camera can obtain a clearer image of the injection molded product. For example, when the injection molded product is red, the controller can control the light color of the camera to be yellow, so that the obtained image of the injection molded product is clearer, and then the accuracy of the quality inspection result based on image recognition can be improved.

In some embodiments, as shown in FIG. 3 , the controller may recognize the color of the injection molded product through the second image recognition model. Specifically, the image of the injection molded product is input into the second image recognition model, and the color of the injection molded product output from the second image recognition model is acquired.

In some embodiments, the second image recognition model may be a neural network.

In some embodiments, the input to the second image recognition model may be an image of one or more angles of the injection molded article (eg, front view, rear view, left view, right view, etc.). Its output can be the color of the injection molded part.

In some embodiments, the second image recognition model may be obtained by training based on multiple sets of labeled training samples. The training samples for the second image recognition model may include images of historical injection molded articles. For example, a set of training samples is multiple images of historical injection molded parts. In some embodiments, the training samples may be obtained from images of the injection molded article obtained from the camera history. In some embodiments, training samples may also be obtained from stored images of historical injection molded articles.

In some embodiments, the sample labels may be manually marked colors of historical injection molded articles.

In some embodiments, the training method of the second image recognition model is similar to the first image recognition model. For the specific training method of the second image recognition model, refer to the relevant description of the training method of the first image recognition model.

The color of the injection molded product is recognized by the second image recognition model in the controller, and based on the color recognition result, the light color when the camera is photographed is controlled. The color of the injection molded product can be obtained quickly and accurately, and then the light color when the camera matched with the injection molded product is captured can be further accurately determined, so that a clearer image of the injection molded product can be obtained.

FIG. 4 is an exemplary flowchart of determining whether an injection molded product is passed into a quality parameter testing device according to some embodiments of the present specification.

In some embodiments, the controller may determine whether the injection molded article is input to the quality parameter detection device based on the first indicator of the image quality result of the injection molded article.

In some embodiments, the first indicator may be the reliability of a quality inspection result obtained by performing quality inspection on the injection molded product based on the image of the injection molded product. It is understandable that the first index can be used to determine the possibility that the current injection molded product has a quality problem in the quality inspection result, that is, the higher the reliability, the greater the possibility of the quality problem; the lower the reliability, the higher the possibility of the quality problem. The less chance of quality problems.

In some embodiments, the value interval of the reliability may be [0, 1]. For example, when the confidence value of the injection molded product having a shrinkage cavity problem is 0.1, it means that the possibility of the injection molded product having a shrinkage cavity appearance quality problem is 10%. For another example, when the reliability value of the burr problem in the injection-molded product is 0.8, it means that the possibility of the appearance quality problem of the burr in the injection-molded product is 80%.

In some embodiments, a first threshold can be set, and by comparing the first index with the first threshold, it is then judged whether to input the injection molded product into the corresponding quality parameter testing equipment for further quality testing, for example, it can be When the first index is greater than the first threshold, the injection molded product corresponding to the index is input into the quality parameter detection equipment for detecting the corresponding quality problem.

In some embodiments, the first threshold may be set based on the actual situation. For example, if the detection accuracy needs to be improved, the first threshold may be set smaller. As an example only, the first threshold can be set to 0.5. If the first index corresponding to the weld line problem in the injection-molded product A is 0.6, which is greater than the first threshold, it is determined that the injection-molded product A needs to be input into the scanning device for further scanning. detection.

In some embodiments, the first indicator of the quality result of the injection molded product can be determined in various ways. For example, the worker can set the reliability of the inspection result while performing quality inspection on the injection molded product based on historical experience, so as to obtain The first index corresponding to the corresponding detection result. For another example, if the quality inspection of the injection molded product is performed based on the machine learning model, the confidence level corresponding to the detection result can be output while outputting the detection result, and the confidence level can be used as the first index corresponding to the corresponding detection result.

In some embodiments, the reliability of the quality inspection by the image of the injection molded product is judged by the reliability of the quality image of the injection molded product, and it is further determined whether it is necessary to input the quality parameter inspection device to perform the quality inspection again. As a result, the current quality problems of the injection molded products can be obtained more accurately, and the missed inspection of the injection molded products that may have quality problems can be avoided.

In some embodiments, the first metric of the image quality result of the injection molded article may be determined based on the third metric of the image and the second metric based on the acquisition of the image recognition model.

In some embodiments, the third indicator may be the mass fraction of the image of the injection molded article. The quality score of the image can be used to represent image quality parameters such as sharpness and resolution of the image of the injection molded product. In some embodiments, the quality score of the image can be expressed based on a specific score, for example, the total score of the quality score of the image is 10 points, and scoring the image of the injection molded product based on the image quality (eg, 7 points) can The score serves as a third indicator of the image of the injection molded article.

In some embodiments, the acquisition method of the third index may be calculated by the definition and resolution of the image of the injection molded product. The sharpness may be a parameter reflecting the sharpness of the image of the injection-molded product.

In some embodiments, the image sharpness can be obtained in various ways, for example, the image sharpness can be obtained by using Labrass transform. Specifically, the Laplace transform can be performed on the image by using the Laplace operator with the same size as the image, and then the value of the sharpness of the current frame image of the image can be obtained by using the Laplace transform.

In some embodiments, the third index can be calculated by the following formula:

S=kD+mF+p

Among them, S is the quality score, D is the sharpness, F is the resolution, and k, m, and p are constants.

In some embodiments, the obtaining method of the third indicator may also be obtained through a scoring model. The scoring model may be a neural network.

In some embodiments, the input to the scoring model may be an image of an injection molded article. For example, the front view, rear view, left view, right view and other images of injection molded products. The output of the scoring model can be the quality score corresponding to the image of the injection molded product. For example, 8 points out of 10.

In some embodiments, the scoring model can be trained one or more times based on the labeled training samples, update the parameters of the scoring model during training until the loss function result converges or is smaller than a preset threshold, and finally ends the training.

The training samples may include images of historical injection molded products. For example, in the production of historical injection molded products, images from multiple angles obtained by a camera are used as training samples. In some embodiments, training samples may be obtained from stored historical data. The label may be the scoring result of the historical quality score, for example, the result of manually scoring the quality score corresponding to the collected images of the injection molded product.

The second indicator may be the confidence level corresponding to the quality recognition result output after processing the image of the injection molded product based on the recognition model. For example, the second indicator may be the confidence level corresponding to the recognition result output by the first image recognition model.

In some embodiments, the first image recognition model may be a multi-classification model. Based on the first image recognition model, the confidence levels corresponding to the multiple classification results may be obtained. For example, the first image recognition model may perform recognition processing on the input image, and obtain a confidence level that the image has a quality problem corresponding to each classification result.

As an example only, the labels corresponding to the classification results of the multi-classification model can be 1, 2, and 3. Among them, label 1 corresponds to a quality problem with burrs, label 2 corresponds to a quality problem with shrinkage holes, and label 3 corresponds to a quality problem with silver threads. For quality problems, the output of the first image recognition model can be a vector containing three vector elements, each of which corresponds to the confidence of the quality problems corresponding to labels 1, 2, and 3. For example, the first image recognition model is based on the input The result of the processing output of the image of the injection molded product A is (0.1, 0.15, 0.85), which means that the confidence level of the quality problem of the burr of the injection molded product A is 0.1, the confidence level of the quality problem of shrinkage cavity is 0.15, and there is silver The confidence level of the quality problem of silk is 0.85; finally, the quality problem corresponding to the maximum confidence level can be used as the final classification result, and the maximum confidence level is the second index that is finally used to calculate the first index, as in the previous example, it can be considered that The injection molded product A has a quality problem of silver wire, and 0.85 is used as the second index to calculate the first index.

In some embodiments, the first index corresponding to the image quality result of the injection molded product may be determined based on the third index of the image and the second index of the image recognition model, for example, it may be obtained by the following formula:

T=aC+bM+d

Among them, T is the first index, which means the reliability of the quality inspection result obtained by the quality inspection of the injection-molded product based on the image of the injection-molded product, and C is the second index, which means that the image of the injection-molded product is processed based on the recognition model. The confidence level corresponding to the output quality recognition result, M is the quality score, that is, the score based on the image quality, and a, b, and d are constants.

By determining the first index by the confidence of the first image recognition model and the quality score of the image of the injection molded product, the reliability of the quality inspection result obtained by the quality inspection of the injection molded product based on the image of the injection molded product can be determined more accurately, and errors can be avoided. Judgment issue.

FIG. 5 is a diagram illustrating an example of a function of a controller according to some embodiments of the present specification.

In some embodiments, the controller may be configured to count the product quantities of injection molded products corresponding to various quality inspection results, and send early warning information to the injection molding machine or production personnel terminal based on the statistical results of the product quantities.

In some embodiments, the statistical result may be the proportion of qualified products or unqualified products to the total number of products. The qualified products can be products without any kind of quality problems (eg, appearance quality problems, hardness quality problems, density quality problems, etc.).

In some embodiments, the number of injection molded products corresponding to various types of quality inspection results may be the number of injection molded products with one or more types of quality problems. Quality problems may include appearance quality problems, hardness quality problems, density quality problems, etc., wherein the number of injection molded products with appearance quality problems may include the total number of injection molded products with appearance problems such as weld lines, cracks, and cracks. The number of injection molded products with density quality problems may include the total number of injection molded products with density problems that do not meet industry standards (eg, the density is less than a preset value or greater than a preset value, etc.). The number of injection molded products with hardness quality problems may include the total number of injection molded products with hardness problems that do not meet industry standards (eg, hardness is less than a preset value or greater than a preset value, etc.).

In some embodiments, the early warning information may be information with a warning effect. For example, warning text, warning voice, warning picture, etc.

In some embodiments, the early warning information can be transmitted to the injection molding machine or the production personnel terminal, so as to prompt the production personnel of the current quality problems of the injection molded products. For the detailed description of the injection molding machine and the production personnel terminal, please refer to the related content in Figure 1.

In some embodiments, the controller counts the number of injection molded products corresponding to various quality inspection results, and sends early warning information to the injection molding machine or the production personnel terminal based on the statistical result of the number of products. The statistical method may include: when each product has multiple types of quality problems, the count corresponding to each type of quality problem increases. For example, the count is directly incremented by 1.

In some embodiments, the count increase value is related to the first indicator of quality results. For example, an indicator threshold is set. If the first indicator of a certain type of quality problem is greater than the indicator threshold, the corresponding count of the statistics of the type of quality problem is increased by 1, otherwise it is not increased. Understandably, when the first index of a certain type of quality problem is greater than the index threshold, it indicates that the injection molded product has a high reliability of the quality problem, that is, it is very likely that the quality problem exists, so the count needs to be increased.

In some embodiments, the count increment value can be determined according to the following formula:

m=hT+j

Among them, m is the count increment value, T is the first index, and h and j are both constants. It can be understood that m in this method may not be an integer.

Through the controller to count the number of injection molded products corresponding to various quality inspection results, and send early warning information to the injection molding machine or production personnel terminal based on the statistical results of the number of products, the number of injection molded products with each quality problem can be accurately determined, and Prompt the production personnel in time for the quality problems of the current injection molding products for abnormal early warning. At the same time, based on the statistical data of various quality problems, it can guide the direction of the abnormality, so that the abnormality can be dealt with more effectively.

In some embodiments, the controller may be configured to adjust the transmission frequency of injection molded articles transmitted to the quality parameter detection device based on the proportion of injection molded articles with quality problems.

In some embodiments, the proportion of injection-molded products with quality problems may be the proportion of injection-molded products with quality problems to the total number of products. It can be understood that the quality problem here can be any of the aforementioned quality problems, and the overall quality of the injection molded product can be judged accordingly.

In some embodiments, the transmission frequency may be the number of injection molded products transmitted to the quality parameter inspection device per unit time. For example, if 1 injection molded product is transmitted in 1 minute, the frequency is 1/min. For another example, if one injection molded product is transmitted every 30s, the frequency is 2/min.

In some embodiments, the transmission frequency may be adjusted according to the proportion of injection molded articles with quality problems, eg, the higher the proportion, the lower the transmission frequency. In order to reserve sufficient testing time for the quality parameter testing equipment.

In some embodiments, the method for adjusting the transmission frequency may be adjusted by setting a first proportional threshold and a second proportional threshold (wherein the first proportional threshold is smaller than the second proportional threshold). Further, if the proportion of the total number of products occupied by injection molded products with quality problems is less than the first proportion threshold, the maximum transmission frequency will not be adjusted; if the proportion is less than the second proportion threshold and greater than the first proportion threshold, then The transmission frequency can be reduced, such as adjusting the transmission frequency to 50% of the maximum transmission frequency.

In some embodiments, the method for adjusting the transmission frequency can be adjusted according to a formula method, for example, the value of the adjusted transmission frequency can be determined by the following formula:

为向上取整符号。Among them, f is the transmission frequency, p is the proportion of injection molded products with quality problems to the total number of products, e and g are constants,

is the round-up symbol.

In some embodiments, the controller may adjust the transmission frequency of the injection-molded articles transmitted to the quality parameter detection device based on the proportion of injection-molded articles with quality problems. Adjusting the transmission frequency can be based on adjusting the sample detection channel (eg, conveyor belt) as in FIG. 2 so that the conveyor belt transmits the injection molded articles to the quality parameter detection equipment at the specified transmission frequency.

Based on the proportion of injection molded products with quality problems, adjusting the transmission frequency of injection molded products transmitted to the quality parameter testing equipment can realize that when there are fewer injection molded products with quality problems, that is, when the production quality is relatively stable, the corresponding improvement based on the transmission frequency can be realized. The transmission frequency of injection molded products to the quality parameter testing equipment to improve the overall production and testing efficiency of injection molded products. Correspondingly, when the number of products with quality problems is large, the transmission frequency is correspondingly reduced to reserve for the quality parameter testing equipment. Sufficient inspection time to conduct adequate quality inspection of products.

In some embodiments, the controller may be configured to adjust the number of shooting angles of the camera device based on the proportion of the injection-molded products with appearance quality problems.

In some embodiments, the injection-molded product with appearance quality problems may be an injection-molded product with defects in appearance, for example, the appearance of the injection-molded product has weld lines, cracks, cracks, and the like. In some embodiments, the injection molded product with appearance quality problems can be obtained from the recognition result output by the first image recognition model, or obtained by a quality parameter detection device (eg, a scanning device).

In some embodiments, the ratio of the number of injection molded products with appearance problems to the total number of all injection molded products can be used as the proportion of injection molded products with appearance quality problems.

The number of shooting angles may be the number of different angles at which the camera shoots images of the injection molded product. For example, front view, rear view, left view, right view, top view, upward view, etc. It can be understood that when the number of injection-molded products with appearance quality problems is higher, more images of injection-molded products from different angles are required.

In some embodiments, the number of angles may be adjusted by setting a third proportional threshold and a fourth proportional threshold (where the third proportional threshold is smaller than the fourth proportional threshold).

Further, if the proportion of injection molded products with appearance quality problems is less than the third proportion threshold, set the number of shooting angles to the first preset value (such as 3); if the proportion is less than the fourth proportion threshold and greater than the third proportion threshold, Set the number of shooting angles to the second preset value (such as 4); if the ratio is greater than the fourth ratio threshold, set the number of shooting angles to the third preset value (such as 5), where the first preset value < The second preset value < the third preset value.

In some embodiments, the controller may adjust the number of shooting angles of the camera device according to any method for adjusting the number of shooting angles (such as the above-mentioned method of setting a threshold value) based on the proportion of injection molded products with appearance problems, The adjustment of the shooting angle can be realized based on the rotation of the rotary table, so that the different sides of the injection molded product are aligned with the camera device.

In some embodiments, the number of shooting angles is adjusted in real time based on the proportion of injection molded products with appearance problems, so that when there are many quality problems, the number of shooting angles is increased; when there are few quality problems, the number of shooting angles is decreased. As a result, image resources can be effectively utilized while ensuring the quality of injection molded products with appearance problems.

The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is merely an example, and does not constitute a limitation of the present specification. Although not explicitly described herein, various modifications, improvements, and corrections to this specification may occur to those skilled in the art. Such modifications, improvements, and corrections are suggested in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

Meanwhile, the present specification uses specific words to describe the embodiments of the present specification. Examples such as "one embodiment," "an embodiment," and/or "some embodiments" mean a certain feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places in this specification are not necessarily referring to the same embodiment . Furthermore, certain features, structures or characteristics of the one or more embodiments of this specification may be combined as appropriate.

Furthermore, unless explicitly stated in the claims, the order of processing elements and sequences described in this specification, the use of alphanumerics, or the use of other names is not intended to limit the order of the processes and methods of this specification. While the foregoing disclosure discusses by way of various examples some embodiments of the invention that are presently believed to be useful, it is to be understood that such details are for purposes of illustration only and that the appended claims are not limited to the disclosed embodiments, but rather The requirements are intended to cover all modifications and equivalent combinations falling within the spirit and scope of the embodiments of this specification. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described systems on existing servers or mobile devices.

Similarly, it should be noted that, in order to simplify the expressions disclosed in this specification and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, various features may sometimes be combined into one embodiment, in the drawings or descriptions thereof. However, this method of disclosure does not imply that the subject matter of the description requires more features than are recited in the claims. Indeed, there are fewer features of an embodiment than all of the features of a single embodiment disclosed above.

Some examples use numbers to describe quantities of ingredients and attributes, it should be understood that such numbers used to describe the examples, in some examples, use the modifiers "about", "approximately" or "substantially" to retouch. Unless stated otherwise, "about", "approximately" or "substantially" means that a variation of ±20% is allowed for the stated number. Accordingly, in some embodiments, the numerical parameters set forth in the specification and claims are approximations that can vary depending upon the desired characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and use a general digit reservation method. Notwithstanding that the numerical fields and parameters used in some embodiments of this specification to confirm the breadth of their ranges are approximations, in specific embodiments such numerical values are set as precisely as practicable.

For each patent, patent application, patent application publication, and other material, such as article, book, specification, publication, document, etc., cited in this specification, the entire contents of which are hereby incorporated by reference into this specification are hereby incorporated by reference. Application history documents that are inconsistent with or conflict with the contents of this specification are excluded, as are documents (currently or hereafter appended to this specification) limiting the broadest scope of the claims of this specification. It should be noted that, if there is any inconsistency or conflict between the descriptions, definitions and/or use of terms in the accompanying materials of this specification and the contents of this specification, the descriptions, definitions and/or use of terms in this specification shall prevail .

Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations are also possible within the scope of this specification. Accordingly, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to those expressly introduced and described in this specification.

Claims (4)

1. An injection molding product sorting device, characterized in that, comprising: a controller, a sample transport channel, a quality detection unit, a plurality of sample sorting channels, The sample conveying channel is used for transporting the injection molded products produced by the injection molding machine to the quality inspection unit, and the quality inspection unit is used for inspecting the quality of the injection molded products, and each of the plurality of sample sorting channels Each sample sorting channel is used to transport the injection-molded product that has completed the quality inspection to the corresponding storage space. 2 . The injection molding product sorting device according to claim 1 , wherein the quality inspection unit is provided with a camera device and a rotary table, the rotary table is used for placing the injection molding products, and the camera device is used for 2 . Based on the rotation of the turntable, product images of the injection-molded product at multiple angles are taken for quality inspection. 3 . The injection molding product sorting device according to claim 1 , wherein the quality detection unit is provided with a quality parameter detection device, and the quality parameter detection device is used to detect the quality of the injection molded product. 4 . 4. The injection molding product sorting device according to claim 1 or 3, wherein the controller is used to count the number of the injection molded products corresponding to various quality inspection results, and based on the statistics of the number of the products As a result, an early warning message is sent to the injection molding machine or the production personnel terminal.

Images