CN115592226A

CN115592226A - Production and quality inspection integrated method and system for vacuum cups

Info

Publication number: CN115592226A
Application number: CN202210486457.2A
Authority: CN
Inventors: 刘红星
Original assignee: Suzhou Chuhan Vacuum Technology Co ltd
Current assignee: Suzhou Chuhan Vacuum Technology Co ltd
Priority date: 2021-08-03
Filing date: 2021-08-03
Publication date: 2023-01-13
Anticipated expiration: 2041-08-03
Also published as: CN114799396B; CN113600951B; CN114799396A; CN115592226B; CN113600951A

Abstract

The embodiment of the specification provides a production and quality inspection integrated method and system for a vacuum cup, and the method comprises the following steps: placing an inner container of the vacuum cup in an outer container, and welding the joint of the inner container and the cup opening of the outer container to obtain a device to be processed; placing a device to be processed on an objective table in a feeding area of a vacuum brazing furnace, and sequentially conveying the device to a vacuum chamber, a preheating chamber, a heating chamber and a cooling chamber of the vacuum brazing furnace for processing; the processed device to be processed is sent out from the discharging area, and a processed finished product is obtained; determining key quality inspection finished products and standard finished products in the processed finished products; extracting standard finished products and important quality inspection finished products through a mechanical arm, and placing the standard finished products and the important quality inspection finished products in a shooting position of a discharging area for shooting; extracting image characteristics of a standard finished product and a key quality inspection finished product through a convolutional neural network model; and inputting the image characteristics of the standard finished product and the key quality inspection finished product into the deep neural network model, and determining the quality inspection score of the key quality inspection finished product.

Description

Production and quality inspection integrated method and system for vacuum cups

Description of the cases

The application is a divisional application which is provided by Chinese application with the application date of 2021, 08 and 03 months and the application number of 2021108875529, and the invention name of the method and the system for generating the vacuum cup based on the vacuum brazing furnace.

Technical Field

The specification relates to the field of production of vacuum cups, in particular to a production and quality inspection integrated method and system for a vacuum cup.

Background

Along with the increasing daily life demand of people, the thermos cup can effectively reduce the heat dissipation and realize the heat preservation purpose with its characteristics that can reduce hot water in the cup and external environment heat transfer speed. Wherein, the good and bad heat preservation effect of the thermos cup is the key for the public to select the thermos cup. During batch production, even if the vacuum brazing furnace belongs to the same batch of products, the actual production process parameters of each product are different due to the design problem of the vacuum brazing furnace and the position and other problems of different vacuum cups during processing in the vacuum brazing furnace, so that the quality of the produced vacuum cups is difficult to ensure.

In view of this, it is desirable to provide a method for producing a vacuum cup based on a vacuum brazing furnace, which is convenient for improving the quality of the produced vacuum cup.

Disclosure of Invention

One of the embodiments of the present specification provides a method for integrating production and quality inspection of a vacuum cup, wherein the vacuum cup is produced in a vacuum brazing furnace, the vacuum brazing furnace comprises a feeding area, a vacuum chamber, a preheating chamber, a heating chamber, a cooling chamber and a discharging area, and the method comprises the following steps: placing an inner container of the vacuum cup in an outer container, and welding a cup opening connecting part of the inner container and the outer container to obtain a device to be processed; placing the device to be processed on an object stage of the feeding area, and sequentially conveying the device to be processed to the vacuum chamber, the preheating chamber, the heating chamber and the cooling chamber for processing; the processed device to be processed is sent out from the discharging area, and a processed finished product is obtained; wherein, the space between the inner container and the outer container of the processed finished product is vacuum; determining key quality inspection finished products and standard finished products in the processed finished products; extracting the standard finished product and the key quality inspection finished product through the mechanical arm, and placing the standard finished product and the key quality inspection finished product in a shooting position of the discharging area for shooting; extracting image characteristics of the standard finished product and the key quality inspection finished product through a convolutional neural network model; inputting the image characteristics of the standard finished product and the key quality inspection finished product into a deep neural network model, and determining the quality inspection score of the key quality inspection finished product.

One of the embodiments of this specification provides a thermos cup production quality control integration system, the thermos cup is produced in vacuum brazing furnace, vacuum brazing furnace includes feed zone, vacuum chamber, preheating chamber, heating chamber, cooling chamber and ejection of compact district, the system includes: the vacuum brazing furnace comprises a feeding area, a vacuum chamber, a preheating chamber, a heating chamber, a cooling chamber and a discharging area, and the system comprises: the first processing module is used for placing the inner container of the vacuum cup in the outer container and welding the joint of the cup mouths of the inner container and the outer container to obtain a device to be processed; the second processing module is used for placing the device to be processed on the object stage of the feeding area and sequentially conveying the device to be processed to the vacuum chamber, the preheating chamber, the heating chamber and the cooling chamber for processing; the third processing module is used for sending the processed device to be processed out of the discharging area to obtain a processed finished product; wherein, the space between the inner container and the outer container of the finished product is vacuum; the quality inspection module is used for determining key quality inspection finished products and standard finished products in the processed finished products; extracting the standard finished products and the key quality inspection finished products through the mechanical arm, and placing the standard finished products and the key quality inspection finished products in a shooting position of the discharging area for shooting; extracting image characteristics of the standard finished product and the key quality inspection finished product through a convolutional neural network model; inputting the image characteristics of the standard finished product and the key quality inspection finished product into a deep neural network model, and determining the quality inspection score of the key quality inspection finished product.

One of the embodiments of the present specification provides an integrated device for production and quality inspection of a vacuum cup, which includes at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the method as described in any of the above embodiments.

One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions which, when executed by a processor, implement a method as in any one of the above embodiments.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is an exemplary schematic view of a vacuum brazing furnace according to some embodiments herein;

FIG. 2 is an exemplary flow diagram for producing a vacuum cup based on a vacuum brazing furnace according to some embodiments described herein;

FIG. 3 is an exemplary flow diagram illustrating obtaining quality inspection results according to some embodiments of the present description;

FIG. 4 is an exemplary flow chart illustrating the determination of key quality control end products and standard end products according to some embodiments of the present disclosure;

FIG. 5 is an exemplary illustration of a device to be processed placed on a stage according to some embodiments of the disclosure;

FIG. 6 is an exemplary flow diagram illustrating obtaining a quality inspection score according to some embodiments of the present description;

fig. 7 is yet another exemplary flow chart for obtaining a quality test score according to some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or stated otherwise, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system," "device," "unit," and/or "module" as used herein is a method for distinguishing between different components, elements, parts, portions, or assemblies of different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.

FIG. 1 is an exemplary schematic view of a vacuum brazing furnace, according to some embodiments herein.

In some embodiments, the vacuum cup may be created based on a vacuum brazing furnace.

A vacuum brazing furnace is a device capable of brazing materials under vacuum conditions. As shown in FIG. 1, the vacuum brazing furnace 100 may include a feed zone 110, a vacuum chamber 120, a preheat chamber 130, a heating chamber 140, a cooling chamber 150, and a discharge zone 160.

The feeding zone 110 refers to a region of the vacuum brazing furnace 100 for receiving a material to be processed. Such as a vacuum cup to be processed, or other devices, etc. In some embodiments, the feed zone 110 may include a stage (not shown). The material to be processed may be placed on a stage and moved into the vacuum brazing furnace 100 by the stage.

The vacuum chamber 120 refers to an area of the vacuum brazing furnace 100 that can be used for evacuating a material to be processed. The vacuum level of the vacuum chamber 120 can be adjusted according to the properties of the product to be processed.

The preheating chamber 130 refers to an area of the vacuum brazing furnace 100 that can be used for preheating a material to be processed. The temperature, vacuum level of the preheating chamber 130 and the preheating time period in the preheating chamber may be adjusted according to the properties of a specific product to be processed.

The heating chamber 140 refers to an area of the vacuum brazing furnace 100 that can be used to heat a material to be processed. The temperature, vacuum degree and heating time of the heating chamber 140 can be adjusted according to the properties of the product to be processed.

The cooling chamber 150 refers to an area of the vacuum brazing furnace 100 that may be used to cool the material. In some embodiments, the cooling chamber 150 may be provided with a camera (not shown). The camera may take a picture of the items in the cooling zone to obtain an image and/or video of the processed device.

The discharge zone 160 is a zone where the finished product is discharged after the material is processed in the vacuum brazing furnace.

FIG. 2 is an exemplary flow diagram for creating a vacuum cup based on a vacuum brazing furnace in accordance with some embodiments described herein. As shown in fig. 2, the process 200 includes the following steps:

in step 210, the inner container of the vacuum cup is placed in the outer container, and the joint of the inner container and the cup opening of the outer container is welded to obtain a device to be processed. In some embodiments, step 210 may be performed by a first processing module.

The liner of the vacuum cup refers to a structure for containing fluid substances (such as water, tea and the like) in the vacuum cup. The outer liner of the vacuum cup refers to a structure outside the vacuum cup for isolating air. In some embodiments, the bottom of the outer container of the vacuum cup may include a through hole, and the through hole may be used for placing the sealing solder after vacuum pumping. The inner container and the outer container of the vacuum cup can be directly processed by a processing machine tool or can be purchased. The device to be processed is a vacuum cup material to be placed in a vacuum brazing furnace for vacuum treatment.

In step 220, the device to be processed is placed on the stage of the feeding area and is sequentially sent to the vacuum chamber, the preheating chamber, the heating chamber and the cooling chamber for processing. In some embodiments, step 220 may be performed by a second processing module.

In some embodiments, the devices to be processed may be sequentially transferred to a vacuum chamber, a pre-heating chamber, a heating chamber, and a cooling chamber for processing. In some embodiments, the devices to be processed may be processed in other orders as well. For example, the device to be processed may be sequentially transferred to a preheating chamber, a heating chamber, a vacuum chamber, and a cooling chamber for processing.

In some embodiments, the device to be processed may be transferred to the vacuum chamber by moving the stage, transferred to the preheating chamber after the vacuum chamber is processed, transferred to the heating chamber after the preheating chamber is preheated, and transferred to the cooling chamber for cooling after the heating chamber is heated.

In some embodiments, the stage may be a mobile stage. For example, a moving structure (e.g., a roller, a conveyor, etc.) is provided for the stage, and the device to be processed is sequentially fed into the vacuum chamber, the preheating chamber, the heating chamber, and the cooling chamber by moving the stage for processing.

In some embodiments, the device to be processed may be performed only once per treatment. For example, the device to be processed may be sequentially transferred to the vacuum chamber, the preheating chamber, the heating chamber, and the cooling chamber for processing, and in this case, the device to be processed is processed only once in the vacuum chamber, the preheating chamber, the heating chamber, and the cooling chamber. In some embodiments, the device to be processed may be processed multiple times in one process. For example, the device to be processed may be sequentially transferred to the vacuum chamber, the preheating chamber, the heating chamber, the vacuum chamber, and the cooling chamber for processing, in which case the device to be processed is processed only once in the preheating chamber, the heating chamber, and the cooling chamber, and is processed twice in the vacuum chamber.

In some embodiments, a device to be processed is first fed into a vacuum chamber and the vacuum in the vacuum chamber is pumped to a first vacuum value.

The first vacuum value may refer to a value of vacuum to be processed in the vacuum chamberThe vacuum degree of the device for vacuum treatment. In some embodiments, the first vacuum value may be a range of values. For example, the first vacuum value may be 5X10 ^-2 ～5X10 ^-3 Pa. In some embodiments, the first vacuum value may be a fixed value. For example, the first vacuum value may be 5X10 ^-2 Pa. In some embodiments, the first vacuum value may vary depending on the size, volume, material, etc. of the device to be processed. For example, the capacity of the device to be processed is 500ml, and the first vacuum value may be 5X10 ^-2 Pa. As another example, the device to be processed may have a capacity of 1000ml and the first vacuum value may be 5X10 ^-3 Pa。

In some embodiments, the device to be processed after vacuum processing by the vacuum chamber may be transferred to a preheating chamber, and the preheating chamber is heated to a first temperature value, and the degree of vacuum of the preheating chamber is pumped to a second vacuum value.

The first temperature value may refer to a final temperature at which the device to be processed is heated in the preheating chamber. In some embodiments, the first temperature value may be a range of values. For example, the first temperature value may be 280 to 380 ℃. In some embodiments, the first temperature value may be a fixed value. For example, the first temperature value may be 280 ℃ or 300 ℃. In some embodiments, the first temperature value may also vary according to the size, capacity, material, etc. of the device to be processed. For example, the material of the device to be processed is 316 stainless steel, and the first temperature value may be 280 ℃. For another example, the material of the device to be processed is 304 stainless steel, and the first temperature value may be 300 ℃.

The second vacuum value refers to the vacuum degree of the device to be processed in the preheating chamber. Similar to the first vacuum value, the second vacuum value may be a range value or a fixed value. The second vacuum value may also vary depending on the size, volume, material, etc. of the device to be processed.

In some embodiments, the device to be processed, which has been subjected to vacuum processing from the vacuum chamber, may be transferred to a preheating chamber, which is then directly heated to a first temperature value, and the vacuum level of the preheating chamber is pumped to a second vacuum value. For example, the workpiece to be processed can be conveyed out of the vacuum chamberThe device is sent to a preheating chamber, then the temperature of the preheating chamber is directly heated to 280-380 ℃, and the vacuum degree is pumped to 5X10 ^-3 ～5X10 ^-4 Pa。

In some embodiments, the device to be processed, which has been vacuum-treated from the vacuum chamber, may be transferred to a preheating chamber, which is then heated to a third temperature value, and the vacuum of the preheating chamber is pumped to a second vacuum value; and then heating the preheating chamber from the third temperature value to the first temperature value, and preserving the heat at the first temperature value for a second time. The second time length is the time length of the heat preservation of the device to be processed in the preheating chamber. The second duration may be a range of values. For example, the second time period may be 20min to 40min. In some embodiments, the second duration may be a fixed value. For example, the second time period may be 30min. In some embodiments, the second duration may also vary depending on the size, capacity, material, etc. of the device to be processed. For example, the size of the device to be processed is 6 × 15cm, and the second time period may be 30min. For another example, the material of the device to be processed is 7 × 16cm, and the second time period may be 40min.

In some embodiments, the third temperature value is less than the first temperature value. The third temperature value is the intermediate temperature value reached by the device to be processed in the preheating chamber. The third temperature value may be a range value or a fixed value, similar to the first temperature value. The third temperature value can also be changed according to the size, capacity, material and the like of the device to be processed.

For example, the device to be processed, which is vacuum-treated from the vacuum chamber, may be transferred to a preheating chamber, and then the preheating chamber is heated to 160 to 250 ℃, and the degree of vacuum of the preheating chamber is adjusted to 5X10 ^-3 ～5X10 ^-4 Pa, heating the preheating chamber to 280-380 ℃, and preserving the temperature for 20-40 min.

In some embodiments, the vacuum level of the heating chamber may be adjusted to a third vacuum value, and the temperature may be heated to a second temperature value and held at the second temperature value for a first duration. In some embodiments, the third vacuum value is less than the second vacuum value, and the second temperature value is greater than the first temperature value.

The third vacuum value refers to the vacuum degree of the device to be processed in the heating chamber. The third vacuum value may be a range value or a fixed value, similar to the first vacuum value. The magnitude of the second vacuum value may also vary depending on the size, capacity, material, etc. of the device to be processed.

The second temperature value is the temperature reached by the component to be processed in the heating chamber. The second temperature value may be a range value or a fixed value, similar to the first temperature value. The second temperature value can also be changed according to the size, capacity, material and the like of the device to be processed.

The first time period is the time period of heat preservation of the device to be processed in the heating chamber. The first time period may be a range value or a fixed value, similar to the second time period. The size of the first time period can also be changed according to the size, capacity, material and the like of the device to be processed.

For example, the device to be processed, which is preheated in the preheating chamber, may be introduced into the heating chamber, and the degree of vacuum in the heating chamber may be adjusted to 5 × 10 ^-1 ～5X10 ^-2 Pa, raising the temperature of the heating chamber to 500-600 ℃, and keeping the temperature for 50-70 min.

In some embodiments, the device to be processed, which has been heated by the heating chamber, may be fed into the cooling chamber to be cooled. The cooling environment in the cooling chamber may be a vacuum environment. For example, the device to be processed is in a vacuum of 5X10 ^-2 ～5X10 ^-3 Cooling is carried out in a cooling chamber of Pa.

In some embodiments, the first duration may be associated with the second duration. For example, the length of time of the first duration may vary as the length of time of the second duration varies. The second duration is increased and the first duration is correspondingly increased or decreased.

In step 230, the processed device to be processed can be sent out from the discharging area to obtain a processed finished product. In some embodiments, step 230 may be performed by a third processing module.

The processed finished product refers to the vacuum cup which is subjected to vacuum treatment in a vacuum brazing furnace. In some embodiments, a vacuum is provided between the inner container and the outer container of the finished product.

In some embodiments, the space between the inner container and the outer container of the finished product is vacuumized, and the through hole of the outer container can be sealed by welding materials.

In some embodiments, the finished part may be removed from the discharge zone by a conveyor or the like.

The vacuum brazing furnace is utilized to generate the vacuum cup, so that each link in the vacuum brazing furnace can be controlled, each environment variable in the production of the vacuum cup can be conveniently controlled, and for example, the vacuum cup can be processed in a vacuum chamber, a preheating chamber and a heating chamber according to different temperatures and vacuum degrees. The production method of the vacuum cup can not only improve the quality and the heat preservation effect of the produced vacuum cup, but also improve the production efficiency and speed of the vacuum cup.

Fig. 3 is an exemplary flow diagram illustrating obtaining quality inspection results according to some embodiments of the present description. As shown in fig. 3, the process 300 includes the following steps:

in step 310, key quality inspection finished products and standard finished products in the processed finished products are determined based on the relevant information of the devices to be processed and the distribution data of the heating zones in the preheating chamber and the heating chamber.

The related information of the device to be processed refers to various types of information related to the device to be processed. In some embodiments, the information of the device to be processed may be temperature information of the device to be processed. For example, the temperature of the device to be processed after cooling is 40 ℃. In some embodiments, the information related to the device to be processed may also include the size, capacity, material, or any other information related to the device to be processed.

The heating zone refers to a structure for heating in the preheating chamber and the heating chamber. The distribution data of the heating zones refers to the distribution data of the heating zones in the preheating chamber and the heating chamber, and can be determined according to the preset heating zone structure. The distribution data of the heating zones may include the number, size, location, temperature of heating, or any other relevant data of the heating zones. For example, the distribution data of the heating zone in the preheating chamber may be that the heating temperature of the heating zone is 200 ℃, the size of the heating zone is 10 × 5cm, and the distance from the heating zone to the device to be processed is 15cm.

The key quality inspection finished product refers to a finished product which is subjected to key quality inspection according to the calculated requirement in the processed finished product. And detecting whether the key quality inspection finished product meets the quality requirement. In some embodiments, the quality requirement may be predetermined. The standard finished product refers to a finished product with better quality obtained by calculation in the processed finished product. The specific key quality inspection finished product and standard finished product are determined and described in detail in FIG. 4 and its related description.

In step 320, the image of the key finished product and the image of the standard finished product are used as the input of an image recognition model to obtain a quality inspection result.

In some embodiments, the images may be automatically captured (e.g., images and/or videos captured) by a camera disposed in the vacuum brazing furnace to obtain images of the key quality inspection product and images of the standard product. In some embodiments, the key quality inspection finished product and the standard finished product may be manually photographed to obtain an image of the key quality inspection finished product and an image of the standard finished product.

In some embodiments, the image recognition model may perform image recognition on the input image of the key finished product and the input image of the standard finished product to obtain a quality inspection result. For example, image recognition may be implemented based on a neural network model. The parameters of the neural network model can be obtained by training. In some embodiments, the image of the key quality inspection finished product and the image of the standard finished product may be preprocessed prior to image recognition. For example, the preprocessing may be size or resolution adjustment, and removal of motion artifacts when the work product is moved, and the like.

The quality inspection result refers to a judgment result of the image recognition model on the key quality inspection finished product. For example, whether the quality-critical finished product meets the quality requirement or not.

The production and the detection process of the vacuum cup are combined, so that the quality inspection result of the vacuum cup can be obtained more quickly and accurately. The machine learning model is introduced to detect the finished product, so that the detection efficiency is improved, the participation of personnel is reduced, and the cost is reduced.

FIG. 4 is an exemplary flow chart illustrating the determination of key quality control artifacts and standard artifacts according to some embodiments of the present description. As shown in fig. 4, the process 400 includes the following steps:

in step 410, the actual temperature of the device to be processed as it enters the cooling chamber is obtained.

In some embodiments, a thermodynamic diagram of the device to be processed may be acquired by a thermal infrared imager in the cooling chamber. The thermal infrared imager is an instrument which converts temperature distribution data of an object into a visual image by using an infrared thermal imaging technology. The thermodynamic diagram of the object can be acquired through the thermal infrared imager. The thermodynamic diagram refers to an image representing the temperature distribution data of an article.

In some embodiments, the actual temperature of the device to be processed may be determined by the thermodynamic diagram.

In some embodiments, the temperature shown in the thermodynamic diagram may be taken directly as the actual temperature of the device to be processed. For example, if the temperature of the device to be processed is measured by a thermal infrared imager to be 40 ℃, the actual temperature of the device to be processed may be 40 ℃.

In some embodiments, the actual temperature of the device to be processed may be obtained based on a distance between the thermal infrared imager and the device to be processed. Specifically, the actual temperature of the device to be processed can be obtained by calculating the distance between the infrared thermal imager and the device to be processed and the temperature displayed in the thermodynamic diagram. The distance between the thermal infrared imager and the device to be processed can be determined through the preset positions of the thermal infrared imager and the device to be processed. The actual temperature of the specific device to be processed can be determined by equation (1):

T(t)＝T(t ₀ )-K _d T(t ₀ ) (1)

wherein T (T) is the actual temperature of the device to be processed, T (T) ₀ ) For the temperature shown in the thermodynamic diagram for the component to be processed, K _d For the temperature loss coefficient when the distance between the infrared thermal imager and the device to be processed is d, K _d May vary depending on the variation of d. For example, in the case of a liquid,the temperature of the device to be processed shown in the thermodynamic diagram was 40 ℃, and the temperature loss coefficient was 0.01 when the distance between the infrared thermal imager and the device to be processed was 10 cm. At this time, the actual temperature of the device to be processed was 39.6 ℃.

In step 420, a feature matrix is constructed based on the actual temperature of the device to be processed. The elements in the feature matrix correspond to the devices to be processed one by one, and the element positions in the feature matrix correspond to the grid positions of the devices to be processed on the objective table one by one. For example, as shown in FIG. 5, the devices 520-1, 520-2, 520-3, and 520-4 to be processed are placed in the grids on the stage 510, respectively, and the actual temperatures of the devices 520-1, 520-2, 520-3, and 520-4 to be processed are 38 deg.C, 39 deg.C, 40 deg.C, and 41 deg.C, respectively, whereby a feature matrix can be constructed as

In step 430, the distribution data of the feature matrix, the preheating chamber and the heating zone in the heating chamber are input into a judgment model, and the quality risk degree of the device to be processed is determined.

The quality risk degree refers to the risk degree that the quality of the device to be processed does not meet the quality requirement. In some embodiments, the quality risk may be a matrix, where the elements in the matrix correspond to the quality risk of the device to be processed one by one, and the positions of the elements in the matrix correspond to the grid positions of the device to be processed on the stage one by one.

Illustratively, the decision model may be based on a feature matrix

The distribution data of the heating zone in the preheating chamber is input with the temperature of 160 ℃, the size of 10 x10 cm and the distance of 15cm from the device to be processed, the distribution data of the heating zone in the heating chamber is input with the temperature of 20 ℃, the size of 20 x10 cm and the distance of 10cm from the device to be processed, and the like, and the output quality risk degree can be

In some embodiments, the decision model may include, but is not limited to, a support vector machine model, a Logistic regression model, a naive bayes classification model, a gaussian distributed bayes classification model, a decision tree model, a random forest model, a KNN classification model, and a neural network model.

In some embodiments, the decision model may be trained based on historical data. The historical data includes historical feature matrices, historical distribution data of heating zones in preheating chambers and heating chambers.

In some embodiments, historical distribution data of a plurality of historical feature matrices, heating zones in pre-heating chambers, and heating zones in heating chambers may be used as training samples. The identification of the training sample may be a historical quality risk level. In some embodiments, the historical quality risk level may be determined based on historical devices to be processed. In some implementations, the identifier of the training sample may be obtained by manual labeling, or may be obtained by labeling in other manners, which is not limited in this specification.

Specifically, a training sample with an identifier is input into an initial judgment model, parameters of the initial judgment model are updated through training, and when the trained model meets preset conditions, the training is finished, and the trained judgment model is obtained.

In step 440, the key quality inspection end product and the standard end product are determined based on the quality risk degree.

In some embodiments, the key quality inspection finished product threshold and the standard finished product threshold in the quality risk degree may be preset. Wherein the threshold value of the key quality inspection finished product is higher than the threshold value of the standard finished product. And if the quality risk degree of the device to be processed is higher than the threshold value of the key quality inspection finished product, the device to be processed is the key quality inspection finished product. And if the quality risk degree of the device to be processed is lower than the threshold value of the standard finished product, the device to be processed is the standard finished product. For example, if the critical quality inspection finished product threshold and the standard finished product threshold in the quality risk are 80 and 60, respectively, and the quality risk of the device to be processed is 75, the device to be processed is neither the critical quality inspection finished product nor the standard finished product.

The embodiment at least has the following technical effects: (1) All processed finished products are screened firstly, and then key quality inspection products are determined, so that the detection accuracy can be ensured on the basis of ensuring the detection efficiency; (2) The standard finished products are screened and determined from the same batch of processed finished products, so that the variable between key quality inspection finished products and processed finished products is reduced, and the detection accuracy is improved.

Fig. 6 is an exemplary flow diagram illustrating obtaining a quality inspection score according to some embodiments of the present description. As shown in fig. 5, the process 600 includes the following steps:

in step 610, the key quality inspection finished product is extracted by a mechanical arm and placed in a shooting position of the discharging area for shooting.

The robot arm is a mechanical structure for extracting a finished product to be processed and/or a processed finished product. In some embodiments, the robotic arm may be mounted on a vacuum brazing furnace. In some embodiments, the robotic arm may exist independently of the vacuum brazing furnace.

In some embodiments, the robotic arm may extract all key quality control items. In some embodiments, the robotic arm may randomly pick a key quality control product. In some embodiments, the key quality inspection finished products may be sorted in a positive sequence according to the quality risk degree, and the mechanical arm may extract the first or the first few key quality inspection finished products. In some embodiments, the camera may be used to take pictures, and the video camera may be used to take video or other shooting devices to shoot the key quality inspection products.

In step 620, the quality inspection score of the key quality inspection finished product is determined based on the captured image of the key quality inspection finished product. The quality inspection score refers to the quality inspection score of the key quality inspection finished product. In some embodiments, the quality inspection score of the key finished product quality inspection can be manually determined according to the condition of the key finished product quality inspection reflected by the image based on the shot image of the key finished product quality inspection.

In some embodiments, the quality control score of the key quality control finished product may be determined by performing image recognition on the captured image of the key quality control finished product. Specifically, the image of the key quality inspection finished product can be shot for image recognition, and data of the key quality inspection finished product in the image can be obtained. For example, image recognition may be implemented based on a neural network model. The parameters of the neural network model can be obtained by training. In some embodiments, the captured image of the key quality inspection product may be pre-processed prior to image recognition. For example, the pre-processing may be size or resolution adjustment, removal of motion artifacts, and the like.

FIG. 7 is yet another exemplary flow chart illustrating obtaining a quality control score according to some embodiments of the present description. As shown in fig. 7, the process 700 includes the following steps:

in step 710, the key quality inspection finished product is extracted by a mechanical arm and placed in a shooting position of the discharging area for shooting. It should be understood that the specific implementation of step 710 is consistent with step 610, and will not be described herein.

In step 720, the standard finished product is extracted by the mechanical arm and placed in a shooting position of the discharging area for shooting.

In some embodiments, the robotic arm may extract all of the standard finished goods. In some embodiments, the robotic arm may randomly pick up a standard finished product. In some embodiments, the standard finished products may be sorted in a reverse order according to the quality risk degree, and the mechanical arm may extract the first standard finished product or the first few standard finished products. In some embodiments, a camera may be used to take a photograph, a video camera may be used to take a video, or other camera may be used to take a photograph of a standard finished product.

In step 730, the image features of the standard finished product and the key quality inspection finished product are extracted through a convolutional neural network model. Specifically, the image of the key quality inspection finished product and the image of the standard finished product which are shot can be input into a convolutional neural network model, and the image characteristics of the standard finished product and the key quality inspection finished product are output. In some embodiments, the image features of the standard finished goods and the key quality inspection finished goods may include, but are not limited to, cracks, glistenings, printed patterns, etc. on the standard finished goods and the key quality inspection finished goods.

In some embodiments, the convolutional neural network may be trained separately. In some embodiments, the convolutional neural network model may be trained based on a large number of training samples with identifications. Specifically, the training sample with the identifier is input into a convolutional neural network model, and the parameters of the convolutional neural network model are updated through training. The training sample can be an image of a standard finished product and an image of a key quality inspection finished product with image characteristics. The training labels may be image features. The training samples and the training labels can be obtained from images of the standard finished products and the key quality inspection finished products which are shot in history.

In step 740, the image features of the standard finished product and the key quality inspection finished product are input into a deep neural network model to determine the quality inspection score of the key quality inspection finished product. Specifically, the image characteristics of the standard finished product and the key quality inspection finished product output by the convolutional neural network model can be input into the deep neural network model, and the quality inspection score of the key quality inspection finished product is determined.

In some embodiments, the deep neural network model is trained separately. The deep neural network model can be obtained based on image feature training of historical standard finished products and key quality inspection finished products. The image characteristics of the historical standard finished products and the key quality inspection finished products can be obtained based on images of the historical standard finished products and the key quality inspection finished products.

In some embodiments, the image features of a plurality of standard finished goods and key quality inspection finished goods may be used as training samples. The label of the training sample may be a quality check score. In some embodiments, the label may be obtained by manual labeling. In some embodiments, the quality control score may be determined based on image features in images of historically taken standard and key quality control finishes. Specifically, a training sample with a label is input into the initial deep neural network model, parameters of the initial deep neural network model are updated through training, when the trained model meets preset conditions, the training is finished, and the trained deep neural network model is obtained.

In some embodiments, the convolutional neural network model and the deep neural network model may be jointly trained to obtain: the convolutional neural network model and the deep neural network model can be jointly trained based on training samples, and parameters are synchronously updated. Specifically, the output of the initial convolutional neural network model is used as the input of the initial deep neural network model, and machine learning training is performed on the initial deep neural network model to obtain a trained deep neural network model.

In some embodiments, the training-sample-based joint training comprises: acquiring training samples, wherein the training samples are images of standard finished products with image characteristics and key quality inspection finished products; and synchronously updating the parameters of the initial deep neural network model based on the result output by the initial convolutional neural network model by using the training sample initial convolutional neural network model to obtain a trained convolutional neural network model and a trained deep neural network model.

In the joint training, the contents and the obtaining manners of the training samples and the sample labels of the convolutional neural network model are the same as those of the training samples and the sample labels of the convolutional neural network model in the independent training, and for specific description, reference is made to the corresponding description contents of the independent training convolutional neural network model in the present specification, and details are not repeated here.

In the joint training, the training sample of the deep neural network model can be synchronized with the result output by the initial convolutional neural network model, and the training sample of the deep neural network model can be obtained by training the convolutional neural network model. The content and the obtaining mode of the labels of the training samples of the deep neural network model are the same as those of the labels of the training samples of the deep neural network model in the independent training, and for specific description, reference is made to the corresponding description content of the independent training of the deep neural network model in the present specification, and details are not repeated here.

In some embodiments, the confidence of the quality inspection score of the key quality inspection finished product may be determined based on the quality risk degree and the quality inspection score of the device to be processed.

In some embodiments, a confidence interval for the quality check score may be set, and a confidence for the quality check score may be determined based on the confidence interval. For example, assuming that there are 100 finished quality inspection products with emphasis, weights may be assigned to the quality risk degree and the quality inspection score (for example, the weight of the quality risk degree is 0.5, and the weight of the quality inspection score is 0.5), and the quality risk degree and the quality inspection score are summed by weighting, and for example, the quality risk degree is 0.8, and the quality inspection score is 0.7, which may be summed to obtain 0.8 + 0.5+0.7 + 0.5=0.75. The confidence interval may be divided based on the quality risk and quality check score of a plurality of historical finished products and the actual quality check result of the product, for example, assuming a confidence interval of 0.8-1.0. And (3) performing sampling quality inspection on the key quality inspection finished products selected from the current batch, and determining that the confidence of the quality inspection score is 95% if 95 weighted summation results fall between 0.8 and 1.0 when 100 key quality inspection finished products are sampled.

In some embodiments, it may be determined whether to perform a manual quality check based on the magnitude of the confidence level. The manual quality inspection refers to the manual quality inspection of key quality inspection finished products. Specifically, a confidence threshold may be set. If the confidence coefficient of the key quality inspection finished product is greater than the confidence coefficient threshold value, manual quality inspection is not performed on the key quality inspection finished product, and if the confidence coefficient of the key quality inspection finished product is less than the confidence coefficient threshold value, manual quality inspection needs to be performed on the key quality inspection finished product. For example, if the confidence threshold is 95% and the confidence of the key quality inspection product is 80%, the key quality inspection product needs to be subjected to manual quality inspection.

The above embodiment has at least the following technical effects: (1) After the key quality inspection finished products and the standard finished products are determined, the key quality inspection finished products and the standard finished products can be shot independently through the mechanical arm, the characteristics of the key quality inspection finished products and the standard finished products can be more completely embodied through the independently shot images, and the detection accuracy is improved; (2) The convolutional neural network model and the deep neural network model are jointly trained, so that the problem that labels are difficult to obtain when the deep neural network model is trained independently can be solved, and the accuracy of the deep neural network model can be improved; (3) The data obtained by the primary detection of the key quality inspection product is evaluated again by introducing confidence coefficient, so that the accuracy of the data is improved; (4) By setting the technical scheme of determining whether to carry out manual quality inspection on the key quality inspection finished product based on the confidence coefficient, the possibility of false inspection on the key quality inspection finished product can be reduced on the premise of ensuring the detection efficiency.

The embodiment of the specification also provides a system for producing the vacuum cup based on the vacuum brazing furnace. The system includes a first processing module, a second processing module, and a third processing module.

The first processing module can be used for placing the inner container of the vacuum cup in the outer container, and welding the joint of the inner container and the cup opening of the outer container to obtain a device to be processed.

The second processing module can be used for placing the device to be processed on the object stage of the feeding area and sequentially delivering the device to be processed to the vacuum chamber, the preheating chamber, the heating chamber and the cooling chamber for processing; wherein the processing comprises: pumping the vacuum degree of the vacuum chamber to a first vacuum value; heating the preheating chamber to a first temperature value, and pumping the vacuum degree of the preheating chamber to a second vacuum value; wherein the second vacuum value is greater than the first vacuum value; adjusting the vacuum degree of the heating chamber to a third vacuum value, heating the heating chamber to a second temperature value, and keeping the temperature at the second temperature value for a first time period; wherein the third vacuum value is less than the second vacuum value, and the second temperature value is greater than the first temperature value.

The third processing module can be used for sending the processed device to be processed out of the discharging area to obtain a processed finished product; wherein, the space between the inner container and the outer container of the finished product is vacuum.

The embodiment of the specification also provides a device for producing the vacuum cup based on the vacuum brazing furnace, which comprises a processor and a memory; the memory is to store computer instructions; the processor is configured to execute at least a portion of the computer instructions to implement a method of creating a vacuum cup based on a vacuum brazing furnace as previously described.

The present specification also provides a computer readable storage medium storing computer instructions which, when executed by a processor, implement the method for producing a vacuum cup based on a vacuum brazing furnace as described above.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered as illustrative only and not limiting, of the present invention. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, though not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the specification. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. 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 system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features are required than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Where numerals describing the number of components, attributes or the like are used in some embodiments, it is to be understood that such numerals used in the description of the embodiments are modified in some instances by the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by a particular embodiment. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit-preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. The production and quality inspection integrated method for the vacuum cup is characterized in that the vacuum cup is produced in a vacuum brazing furnace, the vacuum brazing furnace comprises a feeding area, a vacuum chamber, a preheating chamber, a heating chamber, a cooling chamber and a discharging area, and the method comprises the following steps:

placing an inner container of the vacuum cup in an outer container, and welding a cup opening connecting part of the inner container and the outer container to obtain a device to be processed;

placing the device to be processed on an object stage of the feeding area, and sequentially conveying the device to be processed to the vacuum chamber, the preheating chamber, the heating chamber and the cooling chamber for processing;

the processed device to be processed is sent out from the discharging area, and a processed finished product is obtained; wherein, the space between the inner container and the outer container of the finished product is vacuum;

determining key quality inspection finished products and standard finished products in the processed finished products;

extracting the standard finished products and the key quality inspection finished products through the mechanical arm, and placing the standard finished products and the key quality inspection finished products in a shooting position of the discharging area for shooting;

extracting image characteristics of the standard finished product and the key quality inspection finished product through a convolutional neural network model;

inputting the image characteristics of the standard finished product and the key quality inspection finished product into a deep neural network model, and determining the quality inspection score of the key quality inspection finished product.

2. The method of claim 1, comprising, further comprising:

and preprocessing the image of the key quality inspection finished product and the image of the standard finished product before extracting the image characteristics of the standard finished product and the key quality inspection finished product through the convolutional neural network model.

3. The method of claim 1, wherein the method further comprises:

and determining the key quality inspection finished products and the standard finished products in the processed finished products based on the relevant information of the devices to be processed and the distribution data of heating bands in the preheating chamber and the heating chamber.

4. The method of claim 3, wherein the determining the key quality inspection products and the standard products among the processed products based on the information on the devices to be processed, the distribution data of heating zones in the preheating chamber and the heating chamber comprises:

acquiring the actual temperature of the device to be processed when the device to be processed enters the cooling chamber;

constructing a characteristic matrix based on the actual temperature of the device to be processed; the elements in the feature matrix correspond to the devices to be processed one by one, and the element positions in the feature matrix correspond to the grid positions of the devices to be processed on the objective table one by one;

inputting the distribution data of the feature matrix, the preheating chamber and the heating zone in the heating chamber into a judgment model, and determining the quality risk degree of the device to be processed;

and determining the key quality inspection finished product and the standard finished product based on the quality risk degree.

5. The utility model provides a thermos cup production quality testing integration system which characterized in that, the thermos cup is produced in vacuum brazing furnace, vacuum brazing furnace includes feeding zone, real empty room, preheating chamber, heating chamber, cooling chamber and ejection of compact district, the system includes:

the first processing module is used for placing the inner container of the vacuum cup in the outer container and welding the joint of the cup mouths of the inner container and the outer container to obtain a device to be processed;

the second processing module is used for placing the device to be processed on the object stage of the feeding area and sequentially conveying the device to be processed to the vacuum chamber, the preheating chamber, the heating chamber and the cooling chamber for processing;

the third processing module is used for sending the processed device to be processed out of the discharging area to obtain a processed finished product; wherein, the space between the inner container and the outer container of the processed finished product is vacuum;

the quality inspection module is used for determining key quality inspection finished products and standard finished products in the processed finished products; extracting the standard finished product and the key quality inspection finished product through the mechanical arm, and placing the standard finished product and the key quality inspection finished product in a shooting position of the discharging area for shooting; extracting image characteristics of the standard finished product and the key quality inspection finished product through a convolutional neural network model; inputting the image characteristics of the standard finished product and the key quality inspection finished product into a deep neural network model, and determining the quality inspection score of the key quality inspection finished product.

6. The system of claim 5, wherein the quality inspection module is further to:

7. The system of claim 5, wherein the quality inspection module is further to:

and determining the key quality inspection finished products and the standard finished products in the processed finished products based on the relevant information of the devices to be processed and the distribution data of heating belts in the preheating chamber and the heating chamber.

8. The system of claim 7, wherein the quality inspection module is further to:

constructing a characteristic matrix based on the actual temperature of the device to be processed; the elements in the characteristic matrix correspond to the devices to be processed one by one, and the element positions in the characteristic matrix correspond to the grid positions of the devices to be processed on the objective table one by one;

9. An integrated device for production and quality inspection of a vacuum cup is characterized by comprising at least one processor and at least one memory; the at least one memory is for storing computer instructions; the at least one processor is configured to execute at least some of the computer instructions to implement the method of any of claims 1-4.

10. A computer-readable storage medium, characterized in that the storage medium stores computer instructions which, when executed by a processor, implement the method according to any one of claims 1 to 4.