CN114047030A

CN114047030A - Scaling powder sampling method and system

Info

Publication number: CN114047030A
Application number: CN202111290595.5A
Authority: CN
Inventors: 肖大为; 肖健; 卢克胜
Original assignee: Jiangsu Sanwal Electronic Technology Co ltd
Current assignee: Jiangsu Sanwal Electronic Technology Co ltd
Priority date: 2021-11-02
Filing date: 2021-11-02
Publication date: 2022-02-15
Anticipated expiration: 2041-11-02
Also published as: CN114047030B

Abstract

The embodiment of the specification provides a soldering flux sampling device, which comprises a container, a sampler, a first moving device and a second moving device; the container is used for stirring the contained liquid to be prepared through rotation, and the liquid to be prepared is used for generating soldering flux; the first moving device is used for moving the sampler to the upper part of the container; the second moving device is used for moving the sampler into the container; the controller is used for controlling the first moving device, the second moving device and/or the sampler, so that the sampler obtains at least one sample, and the at least one sample is obtained from the liquid to be prepared at different depths in the container, wherein the at least one sample is used for determining the stirring uniformity of the liquid to be prepared in the container.

Description

Scaling powder sampling method and system

Technical Field

The specification relates to the technical field of welding, in particular to a scaling powder sampling device and method.

Background

The soldering flux is a substance with chemical and physical activation properties and is an indispensable auxiliary material in the welding process. Common fluxes are: lead-free soldering flux, a washing-free soldering flux formula, wave soldering flux, electronic circuit board soldering flux and the like. In the welding process, the soldering flux can remove oxides on the surface of the metal to be welded or other formed surface film layers and oxides formed on the appearance of the soldering tin, so that the purpose that the surface to be welded can be stained with the soldering tin and firmly welded is achieved. The flux also protects the metal surfaces from oxidation in the high temperature environment of the solder. In addition, the flux can reduce the surface tension of molten tin and promote the dispersion and flowing of the solder.

In the production of the soldering flux, how to uniformly mix the raw material mixture is a key link for ensuring the quality of the soldering flux in the process of producing the soldering flux. In the process of stirring and mixing raw materials, the sample is detected by extracting the sample, and then whether the stirring and mixing are needed to be continued or not is judged manually, so that subjective errors are caused, and meanwhile, the accurate time required by the continuous stirring cannot be determined, so that the production efficiency is low. Therefore, a sampling device and method with higher efficiency are needed to solve the above problems.

Disclosure of Invention

One of the embodiments of the present specification provides a flux sampling device, including: the device comprises a container, a sampler, a first moving device and a second moving device, wherein the container is used for stirring the contained liquid to be prepared through rotation, and the liquid to be prepared is used for generating the soldering flux; the first moving means for moving the sampler over the container; the second moving device is used for moving the sampler into the container; the controller is used for controlling the first moving device, the second moving device and/or the sampler, so that the sampler obtains at least one sample, the at least one sample is obtained from the liquid to be prepared at different depths in the container, wherein the at least one sample is used for determining the stirring uniformity of the liquid to be prepared in the container.

One embodiment of the present specification provides a sampling method, including: the first moving device and the second moving device move to enable the sampler to go to at least one depth in the container; the sampler extracts at least one sample at the at least one depth; the controller determines the uniformity with which the liquid to be prepared in the container is stirred based on the detection result of the at least one sample.

One of the embodiments of the present disclosure provides a computer-readable storage medium storing computer instructions, and when the computer instructions in the storage medium are read by a computer, the computer performs any one of the methods described above.

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 block diagram of a flux sampling apparatus according to some embodiments herein;

FIG. 2 is an exemplary block diagram of a sampler shown in accordance with some embodiments herein;

FIG. 3 is an exemplary flow diagram of a sampling method performed by a sampling device shown in some embodiments herein;

FIG. 4 is an exemplary flow chart of a method of determining remaining agitation time according to some embodiments of the present description;

FIG. 5 is a schematic diagram of a machine learning model 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 otherwise indicated, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at 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.

The sampling device and method of one or more embodiments of the present description may be applied in a scenario where sampling of various material mixtures and determination of uniformity are performed. In some embodiments, a sampling device may be used to sample the mixing fluid, for example, the sampling device may sample the flux and determine the stirring uniformity of the flux. In some embodiments, the sampling device can be used for mixed fluid (e.g., concrete, food sauce, etc.) sampling. In some embodiments, the sampling device may be used for mixed meal (e.g., feed, pharmaceutical meal, etc.) sampling.

In some embodiments, multiple sampling devices may also serve as quality detection. For example, after the agitation is completed, it is determined whether the finished product uniformity meets production pass conditions. Wherein, qualified numerical values corresponding to different sample uniformity degrees can be established.

The sampling device and the sampling method provided by the embodiment of the specification can determine the uniformity of the liquid to be prepared, so that the processing state of the material can be known in real time. And the residual stirring time can be automatically determined through the uniformity, so that errors caused by subjectivity of manual judgment are avoided, the loss of time cost and labor cost caused by repeated processing of materials is avoided, and the residual stirring time is saved, so that the production efficiency of the soldering flux is improved.

It should be understood that the application scenarios of the sampling device and method of the present application are merely examples or embodiments of the present application, and it will be obvious to those skilled in the art that the present application can also be applied to other similar scenarios according to the drawings without inventive effort.

FIG. 1 is an exemplary block diagram of a flux sampling apparatus according to some embodiments of the present disclosure.

In some embodiments, referring to fig. 1, the sampling device 100 may include a container 110, a sampler 120, a first movement device 130, a second movement device 140, and the like.

The container 110 may be an appliance, device or facility for holding the liquid to be prepared. Such as a cartridge, a tank, a spherical tank, a liquid tower, etc. In some embodiments, the container 110 may be rotated, for example, a blender station, a blender truck, a blender jar, or the like. In some embodiments, a stirring device, such as a stirring rod or the like, may be disposed in the container 110. In some embodiments, the container 110 may be a non-enclosed container. In some embodiments, the container 110 may be a closed container that is opened periodically or aperiodically, during which time sampling and the like may occur.

In some embodiments, the container 110 is rotated by itself and/or an internal device to agitate the contained liquid to be prepared.

The liquid to be prepared may be a mixed liquid containing a formulation for producing the target product. In some embodiments, the liquid to be prepared may be a mixed liquid for generating the flux, for example, a mixed liquid of rosin and 99.5% alcohol.

The flux is a chemical substance used for assisting and promoting the welding process in the welding process, and has a protective effect and an oxidation reaction prevention effect. The soldering flux has the effects of assisting heat conduction, removing oxides, reducing the surface tension of the welded material, removing oil stains on the surface of the welded material, increasing the welding area, preventing reoxidation and the like in the welding process. The soldering flux can also achieve the process effects of no corrosive residue, low smoke, no pollution and the like. The flux is of various types, for example, a no-clean flux (e.g., a halogen-free rosin no-clean flux, an environmentally-friendly halogen-free low-solid no-clean flux, a halogen-free low-solid water-based no-clean flux, a matting-type rosin no-clean flux, etc.), a lead-free flux, a lead-free no-clean flux (e.g., a lead-free matting no-clean flux, etc.), a solar photovoltaic flux (a flux dedicated to photovoltaic modules, a flux dedicated to photovoltaic solder ribbons, etc.), an electronic circuit board flux, a wave soldering flux, etc.

In some embodiments, the formulation of the circuit board flux comprises: 25% of rosin; 75% of 99.5% alcohol. Dissolving rosin in alcohol to form a uniform solution, and obtaining the circuit board soldering flux.

In some embodiments, the formulation of the no-clean flux comprises: 1.5 percent of succinic acid; 2. 1.0% of adipic acid; 0.2 percent of dibromosuccinic acid; 0.68 percent of dibromobutenedioic acid; OP-100.35%; FSN-1000.05% (stock solution); ethanol (balance). Pouring a proper amount of ethanol into a glass ware, sequentially adding various components, and stirring uniformly by using an insulating rod to obtain the no-clean soldering flux.

The sampler 120 is a device for collecting a sample. For example, the sampler may be a cartridge, tube, cup, or the like. The sampler 120 may be a sealed device, i.e. the sample taken may be sealed in the sampler.

In some embodiments, the sampler 120 may be advanced into the container 110 to obtain at least one sample, which may be used to determine the degree of uniformity with which the liquid to be prepared is agitated in the container, as detailed in FIG. 3. In some embodiments, sampler 120 may store the taken sample inside sampler 120.

In some embodiments, referring to fig. 2, a plurality of separation spaces may be provided within sampler 120. Multiple partition spaces are used for samples of different corresponding depths. In some embodiments, sampler 120 may take multiple samples at different depths. In some embodiments, the sampler 120 controls one of the partitioned spaces to be open and the other partitioned spaces to be closed when a sample at a certain depth is obtained. For example, a valve is provided at the seal of each partition space, and a control command is sent to the valve to open or close the seal of the partition space.

In some embodiments, sampler 120 may be positioned vertically deep into the vessel such that multiple shut-off spaces within the sampler correspond to different liquid depths. As shown in fig. 2, after the sampler is vertically inserted into the container, the partition space 202 and the partition space 204 correspond to different liquid depths. The seals of the plurality of partition spaces are opened simultaneously, so that liquid samples with a plurality of depths can be obtained simultaneously. After sampling is completed, the plurality of partitioned spaces are closed and the sampler 120 is taken out of the liquid.

Sampler 120 sets up a plurality of wall spaces and can avoid changing sampler 120 when the sample of the different degree of depth of acquireing, when improving sampling efficiency, effectively guarantees the independence of a plurality of samples, avoids the analysis result mutual interference of a plurality of samples.

In some embodiments, the sampler may contain only one space for placing the sample.

In some embodiments, the sampler 120 may access different depths of the container, obtaining samples corresponding to multiple depths in a fraction. For example, first, the sampler 120 is entered to a depth of 5cm below the surface of the liquid, the seal is opened, a liquid sample is taken to that depth, the seal is closed, the sampler is removed from the container, the sample in the sampler is removed and marked. Then, the sampler 120 was advanced to a depth of 10cm below the surface of the liquid, and the above operation was repeated.

In some embodiments, multiple samplers may be utilized to acquire samples at multiple depths. Specifically, a plurality of samplers can enter different depths to respectively obtain samples of corresponding depths. For example, sampler A entered 5cm depth below the surface of the liquid, sampler B entered 10cm depth below the surface of the liquid … …, sampler Z reached the bottom of the vessel, and so on.

In some embodiments, sampler 120 may be rotatable. In some embodiments, the sampler may be rotated by a motor drive. In some embodiments, the sampler 120 may sample during the stirring process, and the sampler 120 may rotate synchronously with the container 110 while sampling.

The synchronous rotation of the sampler 120 and the container 110 can avoid stopping the stirring operation in the container 110, thereby facilitating real-time sampling. At the same time, the sampler 120 can sample in the moving stream of the mixture, and the analysis result of the obtained sample is more accurate than that of the sample in a static state.

The moving device is used for driving the sampler 120 to move. Such as a lead screw translation device, a linear motor translation device, etc. The first moving means 130 is a means for moving the sampler 120 above the container 110. The second moving means 140 is a means for moving the sampler 120 into the container 110.

In some embodiments, sampler 120 may be connected to at least one of first mobile device 130 and second mobile device 140. In some embodiments, the connection is a detachable connection.

In some embodiments, as shown in fig. 1, the first moving device 130 may include a first slide rail and a first slider, and the first slider may be driven by a motor to move in parallel along a horizontal direction on the first slide rail. The second moving device 140 may include a second slide rail and a second slider, and the second slider may be driven by the motor to move in parallel in a vertical direction on the second slide rail. One end of the first slide rail may be connected to the second slider, and the first slider may be connected to the sampler 120.

In some embodiments, the controller may control the first slider of the first moving device 130 to drive the sampler 120 to move above the container 110. The controller may control the second slide of the second moving device 140 to drive the first slide rail to move, so as to drive the sampler 120 to move into the container 110.

In some embodiments, sampling device 100 also includes a camera 150.

The camera 150 is a device for acquiring image information, for example, a visible light camera, an infrared camera, or the like. In some embodiments, camera 150 may be a micro-camera.

In some embodiments, camera 150 may be integrated on sampler 120. When sampler 120 is inserted into the liquid to be prepared in container 110, camera 150 may capture images at different depth locations of the liquid to be prepared. In some embodiments, multiple cameras may be integrated on sampler 120, for example, one camera for each partition of sampler 120.

In some embodiments, the camera 150 may be disposed in other locations, such as the inner wall of the container, the bottom of the container, the sides of the transparent container, above the unsealed container, the like, or any combination thereof. In some embodiments, camera 150 may take images of the prepared liquid surface or interior periodically. In some embodiments, camera 150 may take images of the prepared liquid surface or interior during the sampling process (e.g., the process of the sampler penetrating into the container).

In some embodiments, at least one image captured by the camera 150 may be used to determine the degree of uniformity with which the liquid to be prepared is agitated in the vessel 110, as described in detail in step 340.

The controller may control and regulate various components of the sampling device 100 (e.g., the sampler 120, the first movement device 130, the second movement device 140, etc.). The controller may process data and/or information obtained from other devices or system components. The controller may execute program instructions based on such data, information, and/or processing results to perform one or more of the functions described in some embodiments of this specification.

By way of example only, the controller may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a programmable logic circuit (PLD), a micro-controller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, the like, or any combination thereof.

In some embodiments, the controller may be communicatively coupled with at least sampler 120, first mobile device 130, and/or second mobile device 140.

In some embodiments, the controller is configured to control the first movement device 130, the second movement device 140, and/or the sampler 120 such that the sampler 120 acquires at least one sample taken from the liquid to be prepared at different depths within the container. In some embodiments, the controller may determine the uniformity with which the liquid to be prepared in the vessel 110 is agitated based on the at least one sample, as detailed in fig. 3.

It should be noted that the above description of the sampling device 100 and its components is merely for convenience of description and should not limit the present application to the scope of the illustrated embodiments. It will be understood by those skilled in the art that any combination of components may be made without departing from the principles of the apparatus, having appreciated the principles of the apparatus. In some embodiments, the first mobile apparatus 130 and the second mobile apparatus 140 disclosed in fig. 1 may be different components, or may be a single component to perform the functions of two or more components. Such variations are within the scope of the present application.

Fig. 3 is an exemplary flow diagram of a sampling method performed by a sampling device shown in some embodiments herein.

The first and second moving means move the sampler to at least one depth in the container, step 310.

At least one depth may refer to a location in the container where a sample may be obtained when the liquid to be prepared is contained. For example, the at least one depth may include 5cm below the surface of the liquid, the bottom of the container, and the like.

In some embodiments, the sampler may be driven by the first and/or second moving means to move towards at least one depth in the container for sampling. For example, the controller may first control the first movement means to move the sampler above the container and then control the second movement means to move the sampler into the liquid. For another example, the controller may control the second moving device to move the sampler to a depth of the liquid to be prepared (e.g., 5cm below the liquid surface), and after the sampler is completely sampled at the depth, the controller may control the second moving device to move the sampler to a next depth of the liquid to be prepared (e.g., 10cm below the liquid surface).

At least one sample is taken at least one depth, step 320.

The sample may refer to a small amount of liquid reflecting the liquid properties of the corresponding site obtained from the liquid to be prepared. For example, the sample may be 5ml, 10ml of the liquid to be prepared.

In some embodiments, the sampling device may be manually or automatically manipulated to extract the sample. For example, manually lifting and lowering a sampling bottle for sampling, automatically sampling by a sampler, and the like. In some embodiments, the sampler may extract at least one sample at least one depth. In some embodiments, the sampler may be extended vertically into the vessel to a desired depth, extracting a sample at the corresponding depth. In some embodiments, the acquired sample may be temporarily stored inside the sampler.

As described in the description of the sampler 120 in fig. 1, the sampler may contain only one space for placing the sample or the sampler may be provided with a plurality of partitioned spaces for storing samples of corresponding different depths. In some embodiments, the controller may control the sampler to acquire multiple samples at different depths, either at once or in multiple passes (see fig. 1 and its description for details).

In some embodiments, the controller may control the time or frequency at which the sampler enters the liquid. For example, the controller may control the sampler to enter the liquid periodically (e.g., every 5 minutes). For another example, the controller may control the sampler to enter the liquid at a plurality of predetermined time points, which may include, for example, when stirring is started, 30 minutes after stirring, 50 minutes after stirring, 60 minutes after stirring, 65 minutes after stirring, 70 minutes after stirring, and the like.

In some embodiments, the depth of the sampler into the liquid may be the same or different each time a sample is taken. For example, the sampler may be positioned 5cm below the liquid surface, 10cm below the liquid surface, 15cm below the liquid surface, etc. each time a sample is taken. For example, the sampler may be positioned 5cm below the liquid surface, 10cm below the liquid surface, or 15cm below the liquid surface for the first sampling, and the sampler may be positioned 10cm below the liquid surface, 15cm below the liquid surface, or 20cm below the liquid surface for the second sampling.

And step 330, acquiring an image of the liquid to be prepared in at least one depth shot by the camera.

The image of the liquid to be prepared (hereinafter, referred to as a liquid image) may refer to an image of the inside or the surface of the liquid to be prepared, which is captured by a camera, and for example, the liquid image may be an RGB image, an infrared image, a microscopic image, or the like.

As illustrated in fig. 1, the sampling device 100 may include at least one camera. The at least one camera may be disposed in the sampler, the isolated space of the sampler, the inner wall of the container, the bottom of the container, the side of the transparent container, above the unsealed container, or the like, or any combination thereof. At least one camera can take images of the surface or interior of the liquid to be prepared during the sampling process or periodically.

In some embodiments, the controller may control the at least one camera to continuously photograph during the entering of the liquid. In some embodiments, the controller may control at least one camera to shoot synchronously, for example, cameras at various positions shoot simultaneously, and images of various depths and/or various angles of view of the liquid at that moment are acquired. In some embodiments, the controller may control the at least one camera to take alternately or in divided shots. For example, when the sampler is 5cm below the liquid surface, the camera above the container and the camera on the sampler are made to take images. For another example, when the sampler reaches the bottom of the container, a camera at the bottom of the container and a camera on the sampler take images.

In some embodiments, the controller may acquire the liquid image from a camera via a network. Alternatively, the controller may be integrated with the camera. In some embodiments, the controller may acquire the liquid image from the camera via the bus.

The image of the liquid to be prepared can reflect the characteristics of the liquid to be prepared, and is favorable for more accurately acquiring the uniformity of the liquid to be prepared.

And step 340, determining the stirring uniformity of the liquid to be prepared in the container based on the image and the detection result of the at least one sample.

The detection result refers to a qualitative or quantitative result obtained by detecting a sample, and for example, the detection result may include uniformity of the sample, a content of a certain component, specific gravity, a solid content, an acid value, and the like.

The uniformity with which the liquid to be prepared is stirred (hereinafter referred to as uniformity) refers to the degree of uniformity of the distribution of particles in the liquid to be prepared.

Uniformity can be determined in a number of ways. For example, the degree of uniformity of the respective component particles of the liquid to be produced can be observed by a Scanning Electron Microscope (SEM).

In some embodiments, the uniformity may be determined based on a plurality of ratios of the content fraction of the detected component to the standard fraction (fraction of the component when stirred uniformly) in samples at different depths. Specifically, the ratio H is a/B (a is the ratio of the components actually measured, and B is the standard ratio when mixed uniformly). In some embodiments, the controller may consider a lowest one of the ratios as the uniformity. For example, if the ratio H1 of the sample s1 at the depth d1 is 0.8, the ratio H2 of the sample s2 at the depth d2 is 1, and the ratio H3 of the sample s3 at the depth d3 is 1.2, the ratio H1 is taken as the uniformity.

Taking the circuit board soldering flux as an example, the formula of the circuit board soldering flux comprises: 25% of rosin; 75% of 99.5% alcohol. Thus, the standard proportion of rosin is 25%. The contents of the rosin in the samples 1, 2 and 3 obtained at the positions d1, d2 and d3 in the liquid to be prepared of the circuit board soldering flux are respectively 30%, 20% and 25%, so that the ratio at the position d1 is 1.2, the ratio at the position d2 is 0.8 and the ratio at the position d3 is 1. The controller may use the ratio of 0.8 at d2 as the uniformity of the liquid to be prepared for the circuit board flux. It should be noted that the above description of the process 300 is for illustration and description only and is not intended to limit the scope of the present disclosure. Various modifications and changes to flow 300 will be apparent to those skilled in the art in light of this description. However, such modifications and variations are intended to be within the scope of the present description.

FIG. 4 is an exemplary flow chart of a method of determining a remaining agitation time, shown in accordance with some embodiments of the present description.

In some embodiments, the controller may determine a remaining agitation time of the liquid to be prepared held in the vessel based on a uniformity with which the liquid to be prepared in the vessel is agitated.

The remaining stirring time may refer to the shortest time period required to continue stirring the liquid to be prepared so far to obtain the target flux, for example, the remaining stirring time may be 1 minute, 10 minutes, 30 minutes, 1 hour, 24 hours, or the like.

The time course for stopping stirring can be preset based on the remaining stirring time, avoiding the loss of time cost, resource cost and/or labor cost caused by repeated stirring.

In some embodiments, the remaining agitation time may be determined by querying a remaining agitation time table (hereinafter simply referred to as a time table) based on various detection results of the sample. In some embodiments, the detection result may include: uniformity, specific gravity, solids content, acid number, adhesion, appearance, and the like, or any combination thereof. In some embodiments, the schedule includes a correspondence of at least one of the detection results to the remaining agitation time, e.g., a correspondence of a uniformity of the rosin to the remaining agitation time. In some embodiments, the schedule may be derived from historical empirical data.

In some embodiments, the controller may perform steps 410-420 to determine a remaining agitation time for the liquid to be prepared.

Step 410, predicting a plurality of predicted uniformities in the container after a plurality of time points of the liquid to be prepared via the machine learning model.

Predictive uniformity refers to an estimate of the uniformity of the liquid to be prepared throughout the container at some future time. For example, the predicted uniformity of the liquid to be prepared after 20 minutes is 0.7 and the predicted uniformity of the liquid to be prepared after 30 minutes is 0.8.

The machine learning model may include, but is not limited to, a combination of one or more of a neural network model, a support vector machine model, a k-nearest neighbor model, a decision tree model, and the like. In some embodiments, the machine learning model includes at least a feature extraction layer and a prediction layer.

In some embodiments, the input to the machine learning model may include the detection of samples at different depths for at least one point in time (e.g., the current point in time). Wherein, the detection results of samples with different depths at a time point can form a sample value vector as the input of the model. The elements of the sample value vector corresponding to a certain time point are the detection values of samples at different depths at the time point. The detected values in the vector may include the content of a particular constituent or the content of each constituent (e.g., rosin content, ethanol content, etc.) in the liquid to be prepared, and the like. For example, if the rosin content at the depths d1, d2, and d3 at the time point t1 is detected at 15%, 18%, and 20%, respectively, the sample value vector v1 corresponding to t1 is (0.15,0.18, 0.2).

In some embodiments, the input to the machine learning model may also include the vessel speed.

In some embodiments, input to the machine learning model may be the detection of samples at different depths at multiple time points. The plurality of time points may be time points including a current time point and a previous time point. Accordingly, a plurality of sample value vectors may be constructed as inputs to the model.

In some embodiments, the input to the machine learning model may also include images at different depths at multiple points in time.

In some embodiments, the output of the machine learning model may include a plurality of predicted degrees of homogeneity of the liquid to be prepared after a plurality of points in time in the future. For example, the predicted uniformity after 10 minutes is 0.7, the predicted uniformity after 20 minutes is 0.8, the predicted uniformity after 30 minutes is 0.85, the predicted uniformity after 1 hour is 0.99, and so on.

The structure and training method of the machine learning model, see fig. 5.

Based on the plurality of predicted degrees of homogeneity, a remaining mixing time is determined, step 420.

In some embodiments, the controller may determine the remaining agitation time based on the plurality of predicted degrees of homogeneity obtained in step 410.

In some embodiments, the controller may consider the point in time at which the prediction of uniformity no longer increases as the remaining agitation time. Illustratively, the predicted uniformity after 5 minutes, 10 minutes, 15 minutes, 20 minutes, 25 minutes, 30 minutes, and 35 minutes of the liquid to be prepared is 0.881, 0.932, 0.975, 0.982, 0.991, and 0.991, respectively, i.e., after 25 minutes the predicted uniformity is not increased, the remaining stirring time is 25 minutes.

In some embodiments, the controller may determine a point in time at which the predicted uniformity first reaches a preset threshold as the remaining agitation time. For example, the predetermined threshold is 0.99, and in the above example, the predicted uniformity (0.991) after 25 minutes first reaches the predetermined threshold, the remaining stirring time is 25 minutes.

In some embodiments, if the predicted uniformity continues to increase and/or a number of predicted uniformities do not reach a preset threshold, the controller can determine the time required to reach the threshold by fitting the time points to the corresponding predicted uniformity and take that time as the remaining agitation time. For example, the preset threshold is 0.99, the prediction uniformity degrees after 5 minutes, 10 minutes, 15 minutes, 20 minutes, 25 minutes, 30 minutes and 35 minutes of the liquid to be prepared are 0.724, 0.820, 0.881, 0.932, 0.975, 0.982 and 0.987 respectively, the prediction uniformity degree of the liquid to be prepared continuously increases, and a plurality of prediction uniformity degrees do not reach the preset threshold, the controller obtains that the prediction uniformity degree after 40 minutes reaches the preset threshold by fitting the time points and the corresponding prediction uniformity degrees, and the remaining stirring time is 40 minutes.

In some embodiments, if none of the predicted uniformity ratios meet the predetermined threshold and have a large difference from the predetermined threshold (e.g., the maximum value of the predicted uniformity ratios is less than 70% of the predetermined threshold). The controller may repeat the

steps

310 and 340 for sampling again after a period of time (e.g., 5 minutes, 10 minutes), and form the detection result of the obtained sample into a sample value vector, which is supplemented to the input of the machine learning model to predict a plurality of prediction uniformity degrees after a plurality of time points again.

It should be noted that the above description related to the flow 400 is only for illustration and description, and does not limit the applicable scope of the present specification. Various modifications and changes to flow 400 will be apparent to those skilled in the art in light of this description. However, such modifications and variations are intended to be within the scope of the present description.

As shown in fig. 5, the machine learning model may include a feature extraction layer 510, a prediction layer 520, and the like.

The feature extraction layer 510 may process the liquid images at multiple depths at multiple time points to extract features in the liquid images, and obtain multiple image feature vectors. In some embodiments, the image features at each depth at each time point may be grouped into a sequence of image features, and the sequence of image features may be used as input for the prediction layer. The number of image feature sequences may be plural, each corresponding to a depth. The members of the image feature sequence corresponding to a certain depth are the image features of the images at the depth at different time points.

In some embodiments, the model type of the feature extraction layer 510 may be a convolutional neural network model (CNN), a regional convolutional neural network model (R-CNN), an accelerated regional convolutional neural network model (Fast R-CNN, etc.), an extended convolutional neural network model (Mask R-CNN), a full convolutional neural network model (FCNN), a deep convolutional neural network model, etc., and any combination thereof.

The prediction layer 520 may process the plurality of image feature vectors, the plurality of sample value vectors at the plurality of time points, and the container rotation speed to predict a plurality of prediction degrees of uniformity at the plurality of time points. The description of the sample value vector, prediction uniformity, is provided in FIG. 4 and its description.

In some embodiments, the model type of the prediction layer 520 may be a Recurrent Neural Network (RNN), an Echo State Network (Echo State Network), a Long Short Term memory Network (Long Short Term memory Network), a Bi-directional RNN (Bi-directional RNN), a Hierarchical RNN (Recurrent RNN), a Recurrent Multilayer Perceptron (Recurrent Multilayer Perceptron), a Second Order Recurrent Neural Network (Second Order Recurrent Network), and the like, and any combination thereof.

In some embodiments, a machine learning model may be trained based on a large number of training samples with identifications.

Each training sample can comprise sample images with different depths at a plurality of time points, sample value vectors and sample rotating speeds, and the label can be a plurality of stirring evenness degrees after different time points.

In some embodiments, the feature extraction layer may be trained in conjunction with the prediction layer.

In some embodiments, the output of the feature extraction layer may be the input of the prediction layer, and the feature extraction layer and the prediction layer may be obtained by joint training. For example, training sample data, namely sample images of different depths at a plurality of time points, are input to the feature extraction layer, and a plurality of image feature vectors output by the feature extraction layer are obtained; and then inputting the plurality of image characteristic vectors as training sample data, sample value vectors and sample rotating speed into a prediction layer to obtain a plurality of predicted stirring uniformity degrees output by the prediction layer after different time points, establishing a loss function based on the sample label and the output of the prediction layer, and iteratively updating parameters of the characteristic extraction layer and the prediction layer based on the loss function until preset conditions are met.

The parameters of the feature extraction layer are obtained through the training mode, the problem that labels are difficult to obtain when the feature extraction layer is trained independently is solved, and the feature extraction layer can better obtain sample information contained in a reflection picture.

The beneficial effects that may be brought by the embodiments of the present description include, but are not limited to: 1) and under the condition of no shutdown, a sample is obtained, and the detection and production efficiency is improved. 2) The residual stirring time is judged, which is beneficial to reducing the waste of resources and manpower.

It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although 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 description. 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 than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of 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 used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. 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. A scaling powder sampling device comprises a container, a sampler, a first moving device and a second moving device, and is characterized in that,

the container is used for stirring the contained liquid to be prepared through rotation, and the liquid to be prepared is used for generating the soldering flux;

the first moving means for moving the sampler over the container;

the second moving device is used for moving the sampler into the container;

the controller is used for controlling the first moving device, the second moving device and/or the sampler, so that the sampler obtains at least one sample, the at least one sample is obtained from the liquid to be prepared at different depths in the container, wherein the at least one sample is used for determining the stirring uniformity of the liquid to be prepared in the container.

2. A sampler device as claimed in claim 1, wherein the sampler rotates synchronously with the container.

3. A sampling device according to claim 2, wherein the sampling device further comprises a camera for capturing images of the liquid to be prepared in the vessel, the capturing of at least one image being used to determine the degree of homogeneity with which the liquid to be prepared in the vessel is agitated.

4. The sampling device of claim 1, wherein the controller is further configured to determine a remaining mixing time for the liquid to be prepared held in the container, the remaining mixing time being determined based on a uniformity with which the liquid to be prepared in the container is mixed.

5. A sampling method performed by the sampling device of claims 1-4, comprising:

the first moving device and the second moving device move to enable the sampler to go to at least one depth in the container;

the sampler extracts at least one sample at the at least one depth;

the controller determines the uniformity with which the liquid to be prepared in the container is stirred based on the detection result of the at least one sample.

6. The sampling method of claim 5, wherein the controller determining a uniformity with which the liquid to be prepared in the container is agitated based on the detection of the at least one sample comprises:

the controller obtains an image of the liquid to be prepared, which is shot by the camera at the at least one depth;

the controller determines a degree of uniformity with which the liquid to be prepared in the container is agitated based on the image and the detection of the at least one sample.

7. The sampling method of claim 5, wherein the method further comprises:

the controller determines a remaining agitation time based on a uniformity with which the liquid to be prepared in the container is agitated.

8. The sampling method of claim 7, comprising,

predicting a plurality of prediction evenness degrees after a plurality of time points through a machine learning model;

determining the remaining agitation time based on the plurality of predicted degrees of uniformity.

9. A computer-readable storage medium storing computer instructions that, when executed, implement the sampling method of claims 5-8.