Uranium extraction liquid drop state determination method, uranium extraction liquid drop state determination equipment, medium and program product

Abstract

The invention discloses a uranium extraction liquid drop state determination method and device, a medium and a program product. The method comprises the following steps: acquiring an image set containing a micro-channel structure; wherein the micro-channel structure comprises a first channel and a second channel; the first end of the first channel is used for injecting an extracting agent; the first end of the second channel is used for injecting a uranium-containing solution; the second end of the first channel is communicated to the node part of the second channel, so that the extraction agent and the uranium-containing solution are subjected to extraction reaction to generate uranium extraction liquid drops; the uranium extraction liquid drops can flow out from the second end of the second channel; processing and identifying the images in the image set to obtain an identification result; and determining the droplet state of the uranium extraction droplet in the micro-channel structure based on the identification result.

Description

Technical Field

[0001] The present application relates to the technical field of uranium extraction, and in particular to a method, device, medium and program product for determining the state of a uranium extraction droplet. Background Art

[0002] In the field of nuclear fuel reprocessing, microfluidics has been widely used in uranium extraction. In microfluidics, it is very important to identify and locate dispersed fluid droplets in a uranium-containing continuous fluid. In practical applications, images of uranium-containing solutions are usually collected by high-speed cameras, and the images are identified by manual recognition to determine the morphology of uranium-containing droplets. However, the above method is inefficient and cannot meet the actual need to determine the morphology of uranium-containing droplets. Summary of the invention

[0003] Based on the above technical problems, the embodiments of the present application provide a method, device, medium and program product for determining the state of a uranium extraction droplet.

[0004] The technical solution provided by the embodiment of the present application is as follows:

[0005] The present application embodiment first provides a method for determining the state of a uranium extraction droplet, the method comprising:

[0006] Acquiring an image set including a microchannel structure; wherein the microchannel structure includes a first channel and a second channel; the first end of the first channel is used to inject an extractant; the first end of the second channel is used to inject a uranium-containing solution; the second end of the first channel is connected to a node of the second channel so that the extractant and the uranium-containing solution undergo an extraction reaction to generate uranium extraction droplets; the uranium extraction droplets can flow out from the second end of the second channel;

[0007] Processing and recognizing images in the image set to obtain recognition results;

[0008] Based on the identification result, the droplet state of the uranium extraction droplet in the microchannel structure is determined.

[0009] In some embodiments, before processing and identifying the images in the image set to obtain the identification results, the method further includes:

[0010] Acquiring a calibration image; wherein the calibration image and the image set are acquired by an image acquisition device connected to a microscope; the microscope is used to optically magnify the microchannel structure;

[0011] The calibration image is preprocessed to determine structural parameters, wherein the structural parameters are associated with the field of view of the microscope and the structural morphology of the microchannel structure.

[0012] In some embodiments, the processing and recognizing the images in the image set to obtain the recognition result includes:

[0013] Based on a first parameter corresponding to the field of view and a second parameter corresponding to the structural morphology, the images in the image set are segmented to obtain segmented images; wherein the structural parameters include the first parameter and the second parameter;

[0014] Tracking and identifying the pixel area associated with the target part in the segmented image to obtain the identification result; wherein the target part includes the node part and the part between the node part and the second end of the second channel.

[0015] In some embodiments, the processing and recognizing the images in the image set to obtain the recognition result includes:

[0016] Performing segmentation processing on the images in the image set to obtain segmented images; wherein the segmented images at least include pixel features of the microchannel structure;

[0017] The pixel area associated with the node position in the segmented image is identified by a semantic segmentation model to obtain the droplet morphology of the uranium extraction droplet; wherein the identification result includes the droplet morphology.

[0018] In some embodiments, the processing and recognizing the images in the image set to obtain the recognition result includes:

[0019] Performing segmentation processing on the images in the image set to obtain segmented images; wherein the segmented images at least include pixel features of the microchannel structure;

[0020] The pixel data of the portion between the node portion and the second end of the second channel in the segmented image is identified and tracked by a tracking model to obtain the movement state of the uranium extraction droplet; wherein the identification result also includes the movement state.

[0021] In some embodiments, the recognition result includes the droplet morphology and movement state of the uranium extraction droplet; and determining the droplet state of the uranium extraction droplet in the microchannel structure based on the recognition result includes:

[0022] Analyzing the droplet morphology associated with the node position to determine the growth state of the uranium extraction droplet at the node position; wherein the droplet state includes the growth state;

[0023] The moving state is analyzed to determine the moving speed of the uranium extraction droplet in the second channel; wherein the droplet state also includes the moving speed.

[0024] In some embodiments, the method further comprises:

[0025] Log data corresponding to the droplet state is generated.

[0026] In some embodiments, the identification result includes the droplet shape and movement state of the uranium extraction droplet; the method further includes:

[0027] If the movement state indicates that there is no uranium extraction droplet in the channel between the node position and the second end of the second channel, obtaining the droplet morphology associated with the node position;

[0028] Generate warning data corresponding to the droplet morphology.

[0029] An embodiment of the present application also provides a device for determining the state of a uranium extraction droplet, the device comprising a processor and a memory; wherein a computer program is stored in the memory; when the computer program is executed by the processor, the method for determining the state of a uranium extraction droplet as described above can be implemented.

[0030] An embodiment of the present application further provides a computer-readable storage medium, wherein the storage medium stores a computer program; when the computer program is executed by a processor of an electronic device, the state determination method of a uranium extraction droplet as described above can be implemented.

[0031] An embodiment of the present application further provides a computer program product, which includes a computer program; when the computer program is executed by a processor of an electronic device, it can implement any of the above methods for determining the state of uranium extraction droplets.

[0032] The method for determining the state of uranium extraction droplets provided in the embodiment of the present application collects an image set including a microchannel structure, wherein the microchannel structure includes a first channel and a second channel, wherein the first end of the first channel is used to inject an extractant, and the first end of the second channel is used to inject a uranium-containing solution, and the second end of the first channel is connected to a node portion of the second channel, so that the extractant and the uranium-containing solution undergo an extraction reaction to generate uranium extraction droplets, and the uranium extraction droplets flow out from the second end of the second channel, so that the images in the image set can intuitively and comprehensively characterize the change state of the uranium extraction droplets generated after the extraction reaction between the uranium-containing solution and the extractant in the microchannel structure; Furthermore, the images in the image set are processed and identified to obtain identification results, thereby realizing automated processing and identification of the images in the image set, thereby improving the efficiency of processing and identifying the images in the image set; on this basis, based on the identification results, the droplet state of the uranium extraction droplet in the microchannel structure is determined, which can not only improve the continuity, comprehensiveness and intuitiveness of the droplet state, but also improve the automation level and intelligence level of the droplet state determination process, thereby improving the efficiency of determining the droplet state of the uranium extraction droplet, and meeting the needs of tracking and identifying uranium extraction droplets in the uranium extraction process in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic flow chart of a method for determining the state of a uranium extraction droplet provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram of the structure of the microchannel provided in the embodiment of the present application;

[0035] Figure 3A A schematic diagram of a process for determining structural parameters provided in an embodiment of the present application;

[0036] Figure 3B A schematic diagram of the structure of a four-part arc profile provided in an embodiment of the present application;

[0037] Figure 3C A schematic diagram of the structure of a circular field of view boundary provided in an embodiment of the present application;

[0038] Figure 3D A schematic diagram of the structure of the linear screening provided in the embodiment of the present application;

[0039] Figure 3E A schematic diagram of the fitting structure of the T-tube edge pixel feature provided in an embodiment of the present application;

[0040] Figure 3F A schematic diagram of the structure of fitting the pixel points corresponding to the circular visual field boundary and the T-tube edge provided in an embodiment of the present application;

[0041] Figure 4AA schematic structural diagram of the displacement state of a uranium extraction droplet provided in an embodiment of the present application;

[0042] Figure 4B A schematic diagram of the structure of a uranium extraction droplet in a growing state and a moving state provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of a process for determining whether a non-elastic flow anomaly occurs provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of a process for tracking uranium extraction reaction through a microchannel experimental environment provided in an embodiment of the present application;

[0045] Figure 7 A schematic diagram of the structure of a device for determining the state of uranium extraction droplets provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0047] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] In the research process of nuclear fuel reprocessing, solvent extraction equipment has always been a key research topic. However, in the actual nuclear fuel reprocessing scenario, the extraction equipment commonly used in reprocessing plants, including mixing and settling tanks, pulse extraction columns, and centrifugal extraction, all have certain defects. Therefore, developing new and efficient extraction equipment is one of the effective ways to improve the purity of nuclear fuel reprocessing products.

[0049] In recent years, thanks to the excellent fluid manipulation and transfer enhancement properties at the microscale, microchemical technology has shown obvious advantages in solvent extraction. Accordingly, microfluidics technology has been applied to the field of nuclear fuel post-processing, and this technology is mainly used in uranium extraction and stripping research.

[0050] At the same time, uranium, as an important and widely used radioactive nuclide, plays a vital role in the energy industry. During the extraction and stripping of uranium, the formation of dispersed fluid microdroplets in the uranium-containing continuous fluid involves the mass transfer process of the flowing fluid-fluid interface, which makes its flow field more complicated. Therefore, the size identification and positioning of uranium-containing droplets are crucial for studying the mass transfer dynamics and optimization of microchannel devices during uranium extraction and stripping; and the competitive wetting between the liquids in the two-phase flow during uranium extraction and stripping will lead to unstable flow patterns, which may cause fluctuations or abnormalities in the generation process of uranium-containing droplets during uranium extraction and stripping, thereby reducing the stability of the microchannel uranium extraction device and increasing the loss of uranium liquid.

[0051] Therefore, accurate identification of uranium-containing droplets during uranium extraction and back-extraction is particularly important. In practical applications, high-speed cameras are usually used to capture images of uranium-containing droplets to visualize the flow field information inside the droplets, and then the size and other droplet shapes of the uranium-containing droplets are determined through manual identification. However, manual identification is time-consuming and inefficient, and cannot meet the actual needs of identifying uranium-containing droplets.

[0052] Based on the above technical problems, the embodiments of the present application provide a method, device, medium and program product for determining the state of a uranium extraction droplet.

[0053] The embodiment of the present application first provides a method for determining the state of a uranium extraction droplet. The method can be implemented by a processor of a device for determining the state of a uranium extraction droplet, and the processor can be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a central processing unit (CPU), a controller, a microcontroller (MCU), and a microprocessor.

[0054] Figure 1 A schematic diagram of a process for determining the state of a uranium extraction droplet provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method may include the following steps:

[0055] Step 101: Acquire an image set containing a microchannel structure.

[0056] The microchannel structure includes a first channel and a second channel; the first end of the first channel is used to inject an extractant; the first end of the second channel is used to inject a uranium-containing solution; the second end of the first channel is connected to a node of the second channel so that the extractant and the uranium-containing solution can undergo an extraction reaction to generate uranium extraction droplets; the uranium extraction droplets can flow out from the second end of the second channel.

[0057] In one embodiment, the hollow structures of the first channel and the second channel may be the same or different.

[0058] In one embodiment, the cross-sectional dimensions of the hollow channels of the first channel and the second channel may be the same or different.

[0059] In one embodiment, the first channel and the second channel may be in a vertically connected relationship.

[0060] Figure 2 The schematic diagram of the microchannel structure provided in the embodiment of the present application is as follows: Figure 2 As shown, the first channel 201 is used to inject the extractant of the dispersed phase, and the first end of the second channel 202 is used to inject the uranium-containing solution of the continuous phase. At the node where the first channel 201 is vertically connected to the second channel 202, a chemical reaction can occur between the extractant and the uranium-containing solution to generate uranium-containing droplets, which flow out of the microchannel structure through the outlet position shown at the second end of the second channel 202.

[0061] because Figure 2 The first channel 201 and the second channel 202 are in a vertical relationship, so the microchannel structure in the embodiment of the present application can also be called a T-type microchannel or a T-type tube; exemplarily, in the embodiment of the present application, the continuous phase can be a 1g / LU(IV)3mol / L HNO3 solution, with 30% TBP as the dispersed phase; exemplarily, the diameter sizes Wc and Wd of the first channel 201 and the second channel 202 can be 300μm respectively.

[0062] In one embodiment, the microchannel structure may be made of a transparent material.

[0063] In one embodiment, an image set may include multiple images, and there may be a time correlation relationship between the images in the image set. For example, the kth moment corresponding to the kth image in the image set may be earlier than the k+1th moment corresponding to the k+1th image in the image set; wherein k is an integer greater than or equal to 1.

[0064] In one implementation, the image set may be acquired by:

[0065] A high-speed camera is pre-set to be connected to a microscope, and the field of view of the microscope is corrected to a posture capable of fully displaying the microchannel structure. Image frames containing the microchannel structure are then continuously collected by the high-speed camera at specified time intervals, and a collection of image frames is determined as an image collection.

[0066] In one embodiment, images in the image set may or may not contain pixel features of uranium extracted droplets.

[0067] Step 102: Process and recognize the images in the image set to obtain recognition results.

[0068] In one embodiment, the recognition result may include at least one of whether any number of images in the image set contain uranium extraction liquid droplets, the number of the contained uranium extraction liquid droplets, and the morphology of the contained uranium extraction liquid droplets.

[0069] In one implementation, the number of results included in the recognition result may be the same as the number of images in the image set.

[0070] In one implementation, the recognition result may be obtained by:

[0071] Through a neural network model or an artificial intelligence model, feature extraction and recognition processing are performed on the kth image in the image set to obtain a kth result corresponding to the kth image, and then a set of the first result to the Kth result is determined as the recognition result; wherein k is an integer greater than or equal to 1 and less than or equal to K; and K is the number of images in the image set.

[0072] Step 103: Based on the identification result, determine the droplet state of the uranium extraction droplet in the microchannel structure.

[0073] In one embodiment, the liquid state may include the presence or absence of uranium extraction liquid droplets in the microchannel structure.

[0074] In one embodiment, when it is determined that uranium extraction droplets are contained in the microchannel structure, the droplet state may also include at least one of the shape, size, shape change state, size change state and position of the uranium extraction droplets in the microchannel structure.

[0075] In one embodiment, the state of the droplet may be determined by any of the following methods:

[0076] The results from the identification results are integrated according to time to determine the generation process of uranium extraction droplets in the microchannel structure.

[0077] The results of the identification process are integrated over time to determine the number, shape and location of uranium extraction droplets in the microchannel structure.

[0078] As can be seen from the above, the method for determining the state of uranium extraction droplets provided in the embodiment of the present application collects an image set including a microchannel structure, and the microchannel structure includes a first channel and a second channel, the first end of the first channel is used to inject an extractant, the first end of the second channel is used to inject a uranium-containing solution, and the second end of the first channel is connected to a node portion of the second channel, so that the extractant and the uranium-containing solution undergo an extraction reaction to generate uranium extraction droplets, and flow out from the second end of the second channel. In this way, through the images in the image set, the changes of the uranium extraction droplets generated after the extraction reaction between the uranium-containing solution and the extractant in the microchannel structure can be intuitively and comprehensively characterized. state; and, processing and identifying the images in the image set to obtain identification results, realizing automated processing and identification of the images in the image set, thereby improving the efficiency of processing and identifying the images in the image set; on this basis, based on the identification results, determining the droplet state of the uranium extraction droplet in the microchannel structure can not only improve the continuity, comprehensiveness and intuitiveness of the droplet state, but also improve the automation level and intelligence level of the droplet state determination process, thereby improving the efficiency of determining the droplet state of the uranium extraction droplet, and meeting the needs of tracking and identifying uranium extraction droplets in the uranium extraction process in practical applications.

[0079] Based on the above embodiments, in the method for determining the state of uranium extraction droplets provided in the embodiments of the present application, the following steps may be further performed before processing and identifying the images in the image set and obtaining the identification results:

[0080] Step A1: Acquire a calibration image.

[0081] The calibration image and the image set are both acquired through an image acquisition device connected to a microscope; the microscope is used to optically magnify the microchannel structure.

[0082] In one implementation, the image acquisition device may be the high-speed camera in the aforementioned embodiment.

[0083] In one embodiment, the optical magnification of the microscope on the microchannel structure can be adjusted according to the size of the microchannel structure and the resolution of the high-speed camera.

[0084] In one embodiment, all pixel features of the microchannel structure may be included in the calibration image.

[0085] Step A2: pre-process the calibration image to determine the structural parameters.

[0086] Among them, the structural parameters are related to the field of view of the microscope and the structural morphology of the microchannel structure.

[0087] In one embodiment, the first parameter associated with the field of view in the structural parameters may include a pixel range corresponding to the field of view of the microscope in an image captured by the image acquisition device; illustratively, the first parameter may characterize the shape and size of a figure composed of pixel points corresponding to the field of view in the image captured by the image acquisition device.

[0088] In one embodiment, the second parameter associated with the microchannel structure in the structural parameters may include the shape and size of a figure composed of pixel points corresponding to the microchannel structure in the image captured by the image acquisition device; illustratively, the second parameter may include the shape, size and location of the node parts of the first channel and the second channel.

[0089] In one embodiment, the structural morphology can characterize the size of the first channel and the second channel in the microchannel structure and the location of the node.

[0090] Figure 3A A schematic diagram of a process for determining structural parameters provided in an embodiment of the present application, such as Figure 3A As shown, the process may include the following steps:

[0091] Step 301, start.

[0092] Exemplarily, in this step, a high-speed camera can be connected to a microscope, and the magnification and posture of the microscope can be adjusted so that the structural features of the microchannel structure can be clearly obtained through the microscope, and then a calibration image is collected by the high-speed camera.

[0093] Step 302: Read the calibration image.

[0094] Exemplarily, in this step, the mth image in the calibration image may be read; wherein m may be an integer greater than or equal to 1.

[0095] Exemplarily, when the data acquired by the high-speed camera is a video stream, the video stream may be decoded to obtain a calibration image.

[0096] Step 303: Image preprocessing.

[0097] Exemplarily, in order to reduce the influence of noise on subsequent processing, Gaussian smoothing, binarization processing and morphological opening operations may be performed on the m-th image in sequence to obtain a preprocessed image.

[0098] Exemplarily, compared with the calibration image, only black and white pixels may be retained in the preprocessed image, and noise points in the preprocessed image may have been at least partially removed, so that only the image boundary of the microscope is retained in the preprocessed image.

[0099] Step 304: Determine the circular field of view boundary.

[0100] Exemplarily, the pixel feature corresponding to the circular field of view boundary may be a first parameter corresponding to the field of view of the microscope.

[0101] Exemplarily, the circular field of view boundary may be determined by:

[0102] Taking the geometric midpoint of the mth image as the center, the mth image is evenly divided into four parts, and the Canny operator is used to perform edge detection on each part to obtain the first to fourth detection results, and then the arc contour farthest from the image center from the first to fourth detection results is taken as part of the arc, and finally the four parts of the arc contour are merged to fit the circular field of view.

[0103] Figure 3B A schematic diagram of the structure of a four-part arc profile provided in an embodiment of the present application; Figure 3C This is a schematic diagram of the structure of the circular field of view boundary provided in the embodiment of the present application. Figure 3B As shown, the four arc contours can be smoothly connected to form Figure 3C Circular field of view boundaries shown.

[0104] Step 305: Detect the edge of the T-tube.

[0105] Exemplarily, the T-tube may be the microchannel structure in the aforementioned embodiment; accordingly, the pixel feature corresponding to the edge of the T-tube may be the second parameter in the aforementioned embodiment.

[0106] Exemplarily, the T-tube edge detection may include edge detection for a first channel and edge detection for a second channel; exemplary, the second channel may be a main channel, and the first channel may be a dispersed phase channel.

[0107] Exemplarily, in the pixel area corresponding to the circular field of view boundary, different Sobel operators can be used to perform main channel edge detection and dispersed phase channel edge detection on the pixel points contained in the circular field of view boundary, respectively, to obtain a fifth detection result, and then the Hough line detection method is used to detect the straight line segments that may be contained in the fifth detection result to obtain a first screening result, and then the straight line segments contained in the screening result are screened for the second time according to the following screening conditions to obtain a second screening result, and finally the second parameter corresponding to the edge of the T-tube is determined according to the size and relative position relationship of the straight line in the second screening result.

[0108] Exemplarily, the screening conditions may include the following conditions: the straight line should be parallel to the boundary of the calibration image, if there is overlap between straight line segments, the longest straight line segment is retained, there is at least one straight line parallel to the current straight line, and the two longest straight lines are screened in the horizontal and vertical directions respectively.

[0109] Exemplarily, after completing the above screening, each frame in the calibration image only needs to retain the corresponding straight line.

[0110] Figure 3D The schematic diagram of the structure of the linear screening provided in the embodiment of the present application is as follows: Figure 3D As shown, within the binary pixel range, there are parallel straight line segments of different lengths.

[0111] Figure 3E The schematic diagram of the fitting structure of the T-tube edge pixel feature provided in the embodiment of the present application is as follows: Figure 3E As shown, the T-tube structure composed of parallel and vertical straight line segments matches the extension direction of the channel in the microchannel structure provided in the aforementioned embodiment.

[0112] Step 306: Determine whether the number of valid identifications is greater than a threshold.

[0113] For example, the effective recognition number may include the number of images in the calibration image that can determine the circular field of view boundary and the T-tube edge.

[0114] Since there is uncertainty in fitting the circular field of view area and the T-tube edge using a single frame image, the present application can use more than 30 frames of calibration images to determine the circular field of view area and the T-tube edge area, and with the help of a pre-set error probability of less than 0.02, use the Random Sample Consensus (RANSAC) algorithm to process the calibration image to determine the first parameter and the second parameter.

[0115] Exemplarily, if the number of valid identifications is greater than the threshold, step 307 is executed; if the number of valid identifications is less than or equal to the threshold, step 302 may continue to be executed.

[0116] Step 307: Fitting the circular field of view boundary and the T-tube edge.

[0117] Exemplarily, the first parameter and the second parameter may be fitted according to the pixel coordinates of the pixel points corresponding to the boundary of the circular field of view and the pixel coordinates of the pixel points corresponding to the boundary of the T-tube, so as to obtain the structural parameters.

[0118] Figure 3F A schematic diagram of the structure of fitting the pixel points corresponding to the circular field of view boundary and the T-tube edge provided in the embodiment of the present application, as shown in FIG. Figure 3F As shown, within the circular pixel range corresponding to the circular recognition boundary, a T-shaped pixel region that can fully characterize the T-shaped tube structure is retained.

[0119] Step 308: Stop.

[0120] Through the above process, accurate recognition of the calibration image is achieved, thereby improving the accuracy and comprehensiveness of the structural parameters.

[0121] It can be seen from the above that in the method for determining the state of uranium extraction droplets provided in the embodiment of the present application, the calibration image and the image set are both acquired by an image acquisition device connected to a microscope, and the microscope is used to optically magnify the microchannel structure. In this way, through the above-mentioned setting relationship between the image acquisition device and the microscope, the integrity and clarity of the pixel features of the microchannel structure in the calibration image and the image set can be improved; and, by preprocessing the calibration image, the structural parameters associated with the field of view of the microscope and the structural morphology of the microchannel structure are determined, which can not only improve the accuracy of the structural parameters, but also improve the comprehensiveness and integrity of the structural parameters.

[0122] Based on the above embodiments, in the method for determining the state of uranium extraction droplets provided in the embodiments of the present application, the images in the image set are processed and recognized to obtain the recognition results, which can be achieved by the following steps:

[0123] Step B1: Based on a first parameter corresponding to the field of view and a second parameter corresponding to the structural morphology, the images in the image set are segmented to obtain segmented images.

[0124] The structural parameters include a first parameter and a second parameter.

[0125] In one implementation, the number of images included in the segmented image may be the same as the number of images in the image set.

[0126] In one embodiment, the segmented image can be obtained by:

[0127] The images in the image set are sequentially pixel-segmented using a first pixel range represented by a first parameter and a second pixel range represented by a second parameter to obtain segmented images.

[0128] In one embodiment, the segmented image may only include pixel data corresponding to the microchannel structure, or the segmented image may also include pixel data corresponding to the field of view.

[0129] Step B2: Track and identify the pixel area associated with the target part in the segmented image to obtain a recognition result.

[0130] The target site includes a node site and a site between the node site and the second end of the second channel.

[0131] In one implementation, the recognition result may be obtained by:

[0132] Determine the set of pixel points in the segmented image that are related to the target object, and then track and identify the above pixel point set in the time dimension in turn through a neural network model or an artificial intelligence model according to the time information carried by the segmented image, so as to obtain the recognition result.

[0133] As can be seen from the above, in the state determination method of the uranium extraction droplet provided in the embodiment of the present application, firstly, based on the first parameter corresponding to the field of view and the second parameter corresponding to the structural morphology, the images in the image set are segmented to obtain the segmented images, and the structural parameters include the first parameter and the second parameter. In this way, through the above operation, the targeted segmentation of the images in the image set is achieved, thereby reducing the redundancy of the pixels in the segmented image; on this basis, the pixel area associated with the target part in the segmented image is tracked and identified to obtain the identification result, which can reduce the amount of calculation of tracking and identification, improve the efficiency of tracking and identification, and also improve the accuracy of the identification result.

[0134] Based on the above embodiments, in the method for determining the state of uranium extraction droplets provided in the embodiments of the present application, the images in the image set are processed and recognized to obtain the recognition results, which can also be achieved in the following ways:

[0135] Step C1, segmenting the images in the image set to obtain segmented images.

[0136] The segmented image at least includes pixel features of the microchannel structure.

[0137] Illustratively, after the structural parameters are determined, uranium extraction videos of the extraction reaction between the uranium-containing solution and the extractant in the microchannel structure under different experimental conditions can be collected by an image acquisition device, and the uranium extraction videos can be analyzed to obtain an image set.

[0138] Illustratively, in the above process, the dispersed phase can be an organic phase containing an extractant, and the extractant is a high-efficiency extractant such as 30% TBP-kerosene, while the continuous phase is an aqueous phase containing uranium. The two-phase flow can be pumped into the first channel and the second channel through pumps associated with T-shaped microchannels of different sizes to promote the dispersed phase and the continuous phase to flow in the T-shaped microchannel.

[0139] Step C2: using a semantic segmentation model to identify pixel regions associated with node locations in the segmented image, and obtaining the droplet morphology of the uranium extraction droplets.

[0140] Among them, the recognition result includes the droplet morphology.

[0141] In one embodiment, the pixel points contained in the pixel area associated with the node position in the segmented image can characterize the generation process of uranium extraction droplets during the extraction reaction; and, during the generation process of uranium extraction droplets, the uranium extraction droplets can undergo a deformation process from nothing to something, and from small to large. Therefore, the droplet morphology can characterize the change process of the uranium extraction droplets from nothing to something, and from small to large.

[0142] In one embodiment, the semantic segmentation model may include a model obtained by fine-tuning the COCO dataset segmentation model through Yolov8; exemplarily, since the uranium extraction droplets in the embodiment of the present application meet the characteristics of slug flow, the semantic segmentation model can be called a slug flow semantic segmentation model; exemplarily, the mAP in the recognition accuracy of the slug flow semantic segmentation model in the embodiment of the present application can be greater than 0.95, and F1 can be greater than 0.95.

[0143] In one embodiment, all pixel regions in the segmented image may also be identified by a semantic segmentation model to obtain all forms of the uranium extraction droplet between the node position and the second port of the second channel.

[0144] As can be seen from the above, in the method for determining the state of uranium extraction droplets provided in the embodiment of the present application, the images in the image set are segmented to obtain segmented images, and the segmented images at least include pixel features of the microchannel structure. In this way, by segmenting the images, the morphology of the uranium extraction droplets in the microchannel structure can be more finely and specifically reflected; and, by using the semantic segmentation model, the pixel area associated with the node part in the segmented image is identified to obtain the droplet state of the uranium extraction droplet, so that the efficiency of determining the droplet state can be improved; at the same time, by identifying the pixel area associated with the node part in the segmented image, the amount of calculation of the above-mentioned identification operation can be reduced; on the other hand, with the help of the superiority of the semantic segmentation model in pixel-level classification and deeper semantic understanding, the accuracy of the droplet morphology can be improved.

[0145] Based on the above embodiments, in the method for determining the state of uranium extraction droplets provided in the embodiments of the present application, the images in the image set are processed and recognized to obtain the recognition results, which can also be achieved by the following steps:

[0146] Step D1: Segment the images in the image set to obtain segmented images.

[0147] The segmented image at least includes pixel features of the microchannel structure.

[0148] Step D2: using the tracking model to identify and track pixel data of a portion between the node portion and the second end of the second channel in the segmented image, to obtain the movement state of the uranium extraction droplet.

[0149] The recognition result also includes the movement status.

[0150] In one embodiment, the pixel area associated with the node position in the segmented image can be first processed by a semantic segmentation model to determine the shape of the uranium extraction droplet, and then the pixel data associated with the portion between the node position and the second end of the second channel in the segmented image can be tracked and identified by a tracking model to obtain the movement state of the uranium extraction droplet.

[0151] In one implementation, the tracking model may include a Byte Track tracking model.

[0152] In one embodiment, the semantic segmentation model and the tracking model can be simultaneously deployed to a monitoring system in a uranium extraction droplet state determination device to achieve dynamic and flexible tracking of uranium extraction droplets in a microchannel structure.

[0153] Exemplarily, within a unit time, the number of slug-like flows represented by the uranium extraction droplets within the field of view of the microscope corresponding to the image acquisition device is small. Therefore, the embodiment of the present application determines the motion characteristics of the uranium extraction droplets by Kalman motion state estimation, and at the same time, by detecting the shape of the uranium extraction droplets, the images in the image set are associated with the previous and next frames, and the appearance feature extraction part is removed, which can improve the speed of uranium extraction droplet recognition and tracking; and, since the uranium extraction droplets will grow slowly at the node position, if the growth rate is too fast, the geometric feature affinity between the images in the image set will be reduced, which will further lead to the failure of the previous and next frame association. Therefore, in the embodiment of the present application, when the segmented image is recognized, the position of the uranium extraction droplet in the next frame image can be predicted first according to the Kalman motion estimation, and then the growth scale of the slug-like flow corresponding to the uranium extraction droplet in the horizontal and vertical directions can be predicted according to the flow velocity, so that the size of the detection frame used to detect the uranium extraction droplet can be pre-adjusted before the image association is performed based on the geometric features.

[0154] For example, assume that the flow velocity of the uranium extraction droplet in the kth image is The position and size of the detection frame B1 for detecting uranium extraction droplets in the kth image can be expressed by (Bx, By, Bw, Bh); then, for the k+1th image, the position and size of the new detection frame B2 can be determined by equations (1) to (4):

[0155]

[0156] Among them, (Bx,By) and (B 2x ,B 2y) are used to represent the coordinates of the upper left corner of the detection box in the k-th image and the coordinates of the upper left corner of the detection box in the k+1-th image respectively; (Bw, Bh) and (B2w, B2h) are used to represent the size of the rectangle represented by the detection box in the two images, and β represents the scaling factor, which can be greater than or equal to 0.5 and less than or equal to 1.5.

[0157] Exemplarily, after determining the detection frame B2, the position of the detection frame in subsequent images in the image set can be predicted and determined through B2, thereby improving the accuracy of the association between pixel data between different images in the image set, thereby improving the accuracy of tracking uranium extraction droplets when tracking and identifying between different images.

[0158] In one embodiment, the movement state may include whether the uranium extraction liquid droplet moves between the node position and the second end of the second channel, and the movement speed.

[0159] In one embodiment, the movement status may be determined by:

[0160] The pixel areas associated with the target part between adjacent images in the segmented image are identified respectively through the tracking model to obtain the kth result and the k+1th result. Then, the displacement state is determined according to the position change state of the uranium extraction droplet in the kth result and the k+1th result and the time difference between the kth image and the k+1th image.

[0161] Figure 4A The structural schematic diagram of the displacement state of the uranium extraction droplet provided in the embodiment of the present application is as follows: Figure 4A As shown, it can be seen from the first result 401 to the third result 403 that a first droplet in a growing state has been detected at the node position, and a second droplet moving slowly has been detected between the node position and the second end of the second channel; wherein the uranium extraction droplet may include the first droplet and the second droplet.

[0162] As can be seen from the above, in the method for determining the state of uranium extraction droplets provided in the embodiment of the present application, a segmented image is obtained by segmenting the image in the image set, and the segmented image at least includes the pixel features of the microchannel structure. In this way, through the above operation, the number of pixels in the segmented image can be reduced, thereby reducing the data redundancy of the segmented image; and, through the tracking model, the portion between the node portion and the second end of the second channel in the segmented image is tracked and identified to obtain the movement state of the uranium extraction droplets, thereby realizing dynamic tracking of the uranium extraction droplets in the microchannel structure.

[0163] Based on the foregoing embodiments, in the method for determining the state of a uranium extraction droplet provided in the embodiments of the present application, the identification result includes the droplet morphology and movement state of the uranium extraction droplet.

[0164] Accordingly, based on the identification results, determining the droplet state of the uranium extraction droplet in the microchannel structure can be achieved by the following steps:

[0165] Step E1, analyzing the droplet morphology associated with the node position to determine the growth state of the uranium extraction droplet at the node position.

[0166] The droplet state includes the growth state.

[0167] In one embodiment, the growth state may include at least one of whether uranium extraction droplets are generated at the node, the generation rate of the uranium extraction droplets, and the change state of the shape and / or size of the uranium extraction droplets during the generation process.

[0168] In one embodiment, the growth status can be determined by:

[0169] The droplet morphology associated with the node position corresponding to the adjacent images in the image set is temporally correlated to determine the growth state of the uranium extraction droplet at the node position in the time dimension.

[0170] The pixel data associated with the node parts in the segmented image are tracked and identified through the semantic segmentation model and the tracking model to determine the growth status.

[0171] Step E2: Analyze the movement state to determine the movement speed of the uranium extraction liquid droplets in the second channel.

[0172] The droplet state also includes the moving speed.

[0173] In one embodiment, the moving speed may be determined by:

[0174] The semantic segmentation model is used to identify and segment the uranium extraction droplets in the second channel, and the size and shape data of at least one uranium extraction droplet in the second channel are determined. Then, the displacement state of the size and shape data of at least one uranium extraction droplet is tracked by the tracking model to determine the above-mentioned displacement speed.

[0175] Figure 4B The schematic diagram of the structure of the uranium extraction droplet in the growth state and the moving state provided in the embodiment of the present application is as follows: Figure 4B As shown, at the node positions in the binary first segmented image 404 and the second segmented image 405, there are uranium extraction droplets in a growing state, respectively, and between the node position and the second end of the second channel, there are uranium extraction droplets in a moving state; wherein the segmented image may include the first segmented image and the second segmented image.

[0176] As can be seen from the above, in the state determination method of uranium extraction droplets provided in the embodiment of the present application, the growth state of the uranium extraction droplets at the node portion is determined by analyzing the droplet morphology associated with the node portion. In this way, through the above operation, the progress and state of the extraction reaction in the microchannel structure can be indirectly tracked; and the movement state of the uranium extraction droplets in the second channel is determined by analyzing the movement state. In this way, the dynamic tracking of the movement state of the uranium extraction droplets in the second channel is achieved; in summary, by tracking and determining the growth state of the node portion and the movement state in the second channel, all-round tracking of the uranium extraction droplets in the microchannel structure can be achieved.

[0177] Based on the above embodiments, the method for determining the state of the uranium extraction droplet provided in the embodiments of the present application may further perform the following operations:

[0178] Generates log data corresponding to the droplet status.

[0179] In one embodiment, the log data may include at least one of the growth state of each uranium extraction liquid droplet, the movement state of the uranium extraction liquid droplet between the node position and the second end of the second channel, and the generation time of each uranium extraction liquid droplet.

[0180] In one embodiment, the log data may also include image data including the growth process and / or movement state of each uranium extraction droplet, and may also include the length, height, and pixel area of ​​the bullet-like flow corresponding to the uranium extraction droplet.

[0181] In one embodiment, the log data may be in the form of text, pictures, videos, and audios; illustratively, the log data may be a report file for describing the uranium extraction process.

[0182] In one embodiment, log data may be generated by:

[0183] The image data and recognition results associated with the determination process of the droplet state are continuously recorded in the time dimension to obtain log data.

[0184] From the above, it can be seen that in the method for determining the state of uranium extraction droplets provided in the embodiment of the present application, by generating log data corresponding to the state of the droplets, it is possible to automatically track and record the process during the uranium extraction process, thereby being able to automatically organize and collate the historical data corresponding to the state of the droplets during the uranium extraction process, thereby providing a data basis for horizontal comparison of different uranium extraction processes and their results.

[0185] Based on the foregoing embodiments, in the method for determining the state of a uranium extraction droplet provided in the embodiments of the present application, the identification result includes the droplet morphology and movement state of the uranium extraction droplet.

[0186] Accordingly, the above method may further perform the following steps:

[0187] Step F1: if the movement state indicates that there is no uranium extraction droplet in the channel between the node portion and the second end of the second channel, obtain the droplet morphology associated with the node portion.

[0188] Accordingly, if the channel between the movement state characterizing the node position and the second end of the second channel contains at least one uranium extraction droplet, the droplet morphology associated with the node position may not be obtained.

[0189] Accordingly, if the channel between the movement state characterization node portion and the second end of the second channel contains at least one uranium extraction droplet, the droplet morphology associated with the node portion can still be obtained.

[0190] Step F2: Generate warning data corresponding to the droplet morphology.

[0191] In one embodiment, if the droplet morphology characterizes that no uranium extraction droplets are generated at the node, or there are no uranium extraction droplets in a growing state at the node, no alarm data may be generated.

[0192] In one implementation, the warning data may be output in the form of audio, vibration, text, etc.

[0193] In one embodiment, the alarm data may include status information that the second channel does not contain uranium extraction droplets and no uranium extraction droplets are generated at the node position, and may also include the generation time of the above status information.

[0194] Figure 5 A flow chart of determining whether a non-elastic flow anomaly occurs is provided in an embodiment of the present application, such as Figure 5 As shown, the process may include the following steps:

[0195] Step 501, start.

[0196] Step 502: Determine whether there is a slug flow in the main channel.

[0197] Exemplarily, it can be determined whether there is a uranium extraction droplet between the second end of the second channel and the node portion, so as to determine whether there is a bullet-like flow in the main channel.

[0198] Exemplarily, if there is no slug flow in the main channel, step 503 may be performed, and if there is a slug flow in the main channel, step 504 may be performed.

[0199] Step 503: Determine whether there is a droplet flow at the node location.

[0200] Exemplarily, whether there is a droplet flow at the node location can be determined by determining whether there is a uranium extraction droplet in a growing state at the node location.

[0201] Exemplarily, if there is a droplet flow at the node, step 505 is executed, and if there is no droplet flow at the node, step 506 is executed.

[0202] Step 504: Classify as slug flow.

[0203] Exemplarily, in this case, it can be determined that the uranium extraction droplets in the main channel are in a normal state, and step 507 can be performed at this time.

[0204] Step 505: Determine whether a non-elastic flow anomaly occurs.

[0205] Exemplarily, if no slug-like flow is detected in multiple consecutive frames of images in the main channel of the T-tube, it is considered that an abnormality has occurred. At this time, it can be identified whether there are uranium extraction droplets in a growing state at the node of the T-tube. If there are uranium extraction droplets in a growing state, it means that there are still uranium extraction droplets growing in the T-tube, but the flow pattern of the uranium extraction droplets has changed. At this time, it can be determined that a non-slug-like flow abnormality has occurred.

[0206] Exemplarily, step 507 may be executed after step 505 is completed.

[0207] Step 506: Determine that no droplets exist.

[0208] Exemplarily, if no slug-like flow is detected in multiple consecutive frames of images in the main channel of the T-tube, it is considered that an abnormality has occurred. At this time, it can be identified whether there are uranium extraction droplets in a growing state at the node of the T-tube. If no uranium extraction droplets are in a growing state, it means that a flow interruption abnormality has occurred in the T-tube, that is, it is determined that no droplets exist.

[0209] Exemplarily, step 507 may be executed after step 506 is completed.

[0210] Step 507: Stop.

[0211] Exemplarily, after determining the type of abnormality, the corresponding abnormality identification method can be determined according to the abnormality type, and the time when the abnormality occurs and the specific abnormal state can be tracked and recorded according to the abnormality identification method. At the same time, the state of the extraction reaction when the abnormality occurs and the corresponding state data of the uranium extraction droplets are recorded to generate alarm data, and the state data corresponding to the abnormal state can also be stored in the database. After the uranium extraction reaction is completed, an experimental report represented by the log data can also be generated according to experimental requirements.

[0212] Exemplarily, the alarm data may include a timestamp corresponding to the first frame of the image corresponding to the abnormality type in which no uranium extraction droplets are detected.

[0213] As can be seen from the above, in the state determination method of the uranium extraction droplet provided in the embodiment of the present application, if there is no uranium extraction droplet in the channel between the moving state characterization node part and the second end of the second channel, the droplet morphology associated with the node part is obtained, and the alarm data corresponding to the droplet morphology is generated. In this way, through the above method, not only the continuous tracking of the morphology of the uranium extraction droplet in the channel between the droplet node part and the second end of the second channel is achieved, but also the alarm data corresponding to the droplet morphology can be generated, so that the tracking alarm of the droplet morphology in the abnormal state can be achieved.

[0214] Figure 6 A schematic diagram of a process for tracking uranium extraction reaction through a microchannel experimental environment provided in an embodiment of the present application is shown in FIG. Figure 6 As shown, the process may include the following steps:

[0215] Step 601, build a microchannel experimental environment.

[0216] Exemplarily, a microchannel structure and a pump may be provided, while the magnification of a microscope may be set, and the relative positional relationship between the microscope, the high-speed camera, and the microchannel structure may be adjusted to build a microchannel experimental environment.

[0217] Step 602: Implement pulling of video data.

[0218] For example, during the process of pumping in the uranium-containing solution and the extractant, video data including the microchannel structure can be continuously collected by a high-speed camera.

[0219] Step 603: Obtain an image set.

[0220] Exemplarily, the video data may be decoded to obtain a set of image frames contained in the video data, and then obtain an image set.

[0221] Step 604: Process the image set using the semantic segmentation model and the tracking model.

[0222] Illustratively, the method provided in the aforementioned embodiment can be used to sequentially process the images in the image set through a semantic segmentation model and a tracking model, thereby determining the growth state and movement state of the uranium extraction droplet.

[0223] Exemplarily, after step 604 is completed, if it is determined based on the growth state and the movement state that the uranium extraction droplets in the microchannel structure are abnormal, step 605 is executed; if it is determined that there is no abnormality in the uranium extraction droplets in the microchannel structure, step 606 is executed.

[0224] Step 605: Notification of abnormal droplet flow.

[0225] Exemplarily, the method provided in the foregoing embodiment may be used to generate alarm data, and the alarm data may also be output to perform abnormal notification of droplet flow.

[0226] Exemplarily, step 607 may be performed after step 605 is completed.

[0227] Step 606: Determine the state of the droplet.

[0228] Exemplarily, after step 606 is completed, log data may be generated and step 607 may be executed.

[0229] Step 607: Data storage.

[0230] Exemplarily, the alarm data and log data may be stored in a database.

[0231] Step 608: Export the analysis results.

[0232] Exemplarily, the alarm data and log data stored in the database may be exported to analyze the results such as the status of the extraction reaction.

[0233] Step 609: Pause / stop the droplet flow.

[0234] Exemplarily, if it is detected that the droplet state does not match the target state, the pump can be controlled to pause / stop pumping the droplets including the uranium-containing solution and the extractant into the microchannel structure, and step 608 can be started and step 610 can be executed.

[0235] Step 610: Adjust parameters and re-pump droplets.

[0236] For example, parameters such as the pressure and / or speed of the pump may be adjusted and the droplets containing the extractant and the uranium-containing solution may be re-pumped.

[0237] Exemplarily, after step 610 is completed, step 602 may be continued to perform the next round of uranium extraction reaction.

[0238] It should be noted that the embodiment of the present application can identify and track the uranium extraction droplets in the microchannel structure through a multiple object tracking (MOT) algorithm, and calculate its parameters to facilitate subsequent research on uranium extraction kinetics.

[0239] Through the above operations, the embodiment of the present application can not only monitor the changes in the uranium extraction liquid droplet flow in real time, provide timely feedback on abnormal conditions, improve experimental efficiency, and reduce the probability of liquid waste; moreover, compared with the traditional method, it can also automatically analyze the fluid motion picture captured by the high-speed camera, quickly determine the time information of the change in the uranium extraction liquid droplet flow, and export the experimental report, thereby reducing the experimental steps of manual operation.

[0240] Through the above process, the present application constructs a method for automatically positioning the state of uranium extraction droplets during the uranium extraction process of the post-processing process, so that the size and displacement state of the uranium extraction droplets can be efficiently detected, reducing the time cost of manually identifying and processing image data; and the above process is implemented through a microchannel structure. Compared with traditional extraction equipment such as centrifugal extractors and pulse extraction columns, the microchannel structure can not only enhance the mass transfer effect, but also improve the efficiency of concentrated uranium products; on the other hand, with the help of the visualization characteristics of video data and image sets, the accuracy of tracking the mass transfer dynamics of uranium extraction droplets can be improved; at the same time, the state tracking of uranium extraction droplets in the microchannel structure through semantic segmentation models and tracking models can improve the efficiency of state tracking during uranium extraction; on this basis, through the storage and report generation functions, the automatic organization and collation of historical data in the uranium extraction process is realized, thereby providing a data basis for the horizontal comparison of data in multiple experiments.

[0241] Based on the above embodiments, the present application also provides a device for determining the state of a uranium extraction droplet, which may include:

[0242] An acquisition module is used to collect an image set including a microchannel structure; wherein the microchannel structure includes a first channel and a second channel; the first end of the first channel is used to inject an extractant; the first end of the second channel is used to inject a uranium-containing solution; the second end of the first channel is connected to a node of the second channel so that the extractant and the uranium-containing solution undergo an extraction reaction to generate uranium extraction droplets; the uranium extraction droplets can flow out from the second end of the second channel;

[0243] A processing module, used for processing and identifying images in the image set to obtain identification results;

[0244] The determination module is used to determine the droplet state of the uranium extraction droplet in the microchannel structure based on the identification result.

[0245] In some embodiments, the acquisition module is further used to acquire a calibration image; wherein the calibration image and the image set are acquired by an image acquisition device connected to a microscope; and the microscope is used to optically magnify the microchannel structure;

[0246] The determination module is used to pre-process the calibration image to determine the structural parameters; wherein the structural parameters are associated with the field of view of the microscope and the structural morphology of the microchannel structure.

[0247] In some embodiments, the processing module is further used to perform segmentation processing on the images in the image set based on the first parameter corresponding to the field of view and the second parameter corresponding to the structural morphology to obtain the segmented image; wherein the structural parameter includes the first parameter and the second parameter;

[0248] The processing module is also used to track and identify the pixel area associated with the target part in the segmented image to obtain an identification result; wherein the target part includes the node part and the part between the node part and the second end of the second channel.

[0249] In some embodiments, the processing module is used to perform segmentation processing on the images in the image set to obtain a segmented image; wherein the segmented image at least includes pixel features of the microchannel structure;

[0250] The processing module is also used to identify the pixel area associated with the node position in the segmented image through the semantic segmentation model to obtain the droplet morphology of the uranium extraction droplet; wherein the identification result includes the droplet morphology.

[0251] In some embodiments, the processing module is used to perform segmentation processing on the images in the image set to obtain a segmented image; wherein the segmented image at least includes pixel features of the microchannel structure;

[0252] The processing module is also used to identify and track the pixel data of the portion between the node portion and the second end of the second channel in the segmented image through the tracking model to obtain the movement state of the uranium extraction droplet; wherein the identification result also includes the movement state.

[0253] In some embodiments, the identification result includes the droplet morphology and movement state of the uranium extraction droplet; the processing module is used to analyze the droplet morphology associated with the node position to determine the growth state of the uranium extraction droplet at the node position; wherein the droplet state includes the growth state;

[0254] The determination module is used to analyze the moving state and determine the moving speed of the uranium extraction droplet in the second channel; wherein the droplet state also includes the moving speed.

[0255] In some embodiments, the processing module is used to generate log data corresponding to the droplet state.

[0256] In some embodiments, the identification result includes the droplet morphology and movement state of the uranium extraction droplet; an acquisition module is used to acquire the droplet morphology associated with the node portion if the movement state indicates that there is no uranium extraction droplet in the channel between the node portion and the second end of the second channel;

[0257] The processing module is used to generate warning data corresponding to the droplet morphology.

[0258] The present application also provides a device for determining the state of uranium extraction droplets. Figure 7 A schematic diagram of the structure of a device for determining the state of uranium extraction droplets provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the uranium extraction droplet state determination device 7 includes a processor 701 and a memory 702; wherein the memory 702 stores a computer program; when the computer program is executed by the processor 701, the uranium extraction droplet state determination method as described above can be implemented.

[0259] The embodiment of the present application further provides a computer-readable storage medium, wherein the storage medium stores a computer program; when the computer program is executed by a processor of an electronic device, the state determination method of a uranium extraction droplet as described above can be implemented.

[0260] An embodiment of the present application further provides a computer program product, which includes a computer program; when the computer program is executed by a processor of an electronic device, it can implement any of the above methods for determining the state of uranium extraction droplets.

[0261] The above description of various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced to each other, and for the sake of brevity, they will not be repeated herein.

[0262] The methods disclosed in the various method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0263] The features disclosed in the various product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0264] The features disclosed in the various method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0265] It should be noted that the above-mentioned computer-readable storage medium can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (Flash Memory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM) and other memories; it can also be various electronic devices including one or any combination of the above-mentioned memories, such as mobile phones, computers, tablet devices, personal digital assistants, etc.

[0266] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0267] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0268] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus necessary general hardware nodes, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0269] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0270] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0271] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0272] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for determining the state of a uranium extraction droplet, characterized in that: The method comprises: Acquiring an image set including a microchannel structure; wherein the microchannel structure includes a first channel and a second channel; the first end of the first channel is used to inject an extractant; the first end of the second channel is used to inject a uranium-containing solution; the second end of the first channel is connected to a node of the second channel so that the extractant and the uranium-containing solution undergo an extraction reaction to generate uranium extraction droplets; the uranium extraction droplets can flow out from the second end of the second channel; Processing and recognizing images in the image set to obtain recognition results; Based on the identification result, the droplet state of the uranium extraction droplet in the microchannel structure is determined.

2. The method according to claim 1, characterized in that Before processing and identifying the images in the image set to obtain the identification result, the method further includes: Acquiring a calibration image; wherein the calibration image and the image set are acquired by an image acquisition device connected to a microscope; the microscope is used to optically magnify the microchannel structure; The calibration image is preprocessed to determine structural parameters, wherein the structural parameters are associated with the field of view of the microscope and the structural morphology of the microchannel structure.

3. The method according to claim 2, characterized in that The processing and identifying the images in the image set to obtain the identification result includes: Based on a first parameter corresponding to the field of view and a second parameter corresponding to the structural morphology, the images in the image set are segmented to obtain segmented images; wherein the structural parameters include the first parameter and the second parameter; Tracking and identifying the pixel area associated with the target part in the segmented image to obtain the identification result; wherein the target part includes the node part and the part between the node part and the second end of the second channel.

4. The method according to claim 1, characterized in that: The processing and identifying the images in the image set to obtain the identification result includes: Performing segmentation processing on the images in the image set to obtain segmented images; wherein the segmented images at least include pixel features of the microchannel structure; The pixel area associated with the node position in the segmented image is identified by a semantic segmentation model to obtain the droplet morphology of the uranium extraction droplet; wherein the identification result includes the droplet morphology.

5. The method according to claim 1, characterized in that The processing and identifying the images in the image set to obtain the identification result includes: Performing segmentation processing on the images in the image set to obtain segmented images; wherein the segmented images at least include pixel features of the microchannel structure; The pixel data of the portion between the node portion and the second end of the second channel in the segmented image is identified and tracked by a tracking model to obtain the movement state of the uranium extraction droplet; wherein the identification result also includes the movement state.

6. The method according to claim 1, characterized in that The identification result includes the droplet shape and movement state of the uranium extraction droplet; and determining the droplet state of the uranium extraction droplet in the microchannel structure based on the identification result includes: Analyzing the droplet morphology associated with the node position to determine the growth state of the uranium extraction droplet at the node position; wherein the droplet state includes the growth state; The moving state is analyzed to determine the moving speed of the uranium extraction droplet in the second channel; wherein the droplet state also includes the moving speed.

7. The method according to claim 1, characterized in that The method further comprises: Log data corresponding to the droplet state is generated.

8. The method according to claim 1, characterized in that The identification result includes the droplet shape and movement state of the uranium extraction droplet; the method further includes: If the movement state indicates that there is no uranium extraction droplet in the channel between the node position and the second end of the second channel, obtaining the droplet morphology associated with the node position; Generate warning data corresponding to the droplet morphology.

9. A device for determining the state of uranium extraction droplets, characterized in that: The device for determining the state of the uranium extraction droplet comprises a processor and a memory; wherein the memory stores a computer program; when the computer program is executed by the processor, the method for determining the state of the uranium extraction droplet according to any one of claims 1 to 8 can be implemented.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program; when the computer program is executed by a processor of an electronic device, the method for determining the state of a uranium extraction droplet as claimed in any one of claims 1 to 8 can be implemented.

11. A computer program product, characterized in that The program product comprises a computer program; when the computer program is executed by a processor of an electronic device, the method for determining the state of a uranium extraction droplet as claimed in any one of claims 1 to 8 can be implemented.

Images