A system and method for detecting a bottled liquid

Abstract

The application relates to the technical field of bottled liquid detection, and particularly provides a bottled liquid detection system and method. The system comprises a carrier table, a rotating assembly, a heating assembly arranged at the periphery of a bottled liquid to be detected, a cooling assembly arranged at the periphery of the bottled liquid to be detected, a thermal imaging camera, and a controller. The controller is used for inducing controlled convection of the bottled liquid to be detected placed on the carrier table, and is also used for acquiring thermal imaging images of the bottled liquid to be detected at multiple moments through the thermal imaging camera during the induction of the controlled convection. The controller is further used for acquiring convection velocity field information corresponding to each thermal imaging image based on the thermal imaging images. The dynamic characteristics of the convection velocity field information are related to physical and chemical properties of the bottled liquid to be detected. The system can effectively solve the problem that predicted parameter indexes cannot accurately reflect actual parameter indexes of the bottled liquid due to the fact that the influence of convection dynamic data on the temperature distribution in the bottled liquid cannot be perceived.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bottled liquid detection, in particular to a bottled liquid detection system and method. BACKGROUND

[0002] During the storage of bottled liquid, the volume and density of the bottled liquid will inevitably change due to volatilization and other reasons. For liquid food, the change in volume and density will cause changes in softness, viscosity and other taste.

[0003] At present, for the detection of bottled liquid, the detection is usually carried out by opening the bottle and taking samples, and the opening of the bottle and the sampling will inevitably cause damage to the appearance and packaging of the bottled liquid. In related technologies, in order to avoid damage to the appearance and packaging of the bottled liquid, the infrared thermal imaging technology can be used to measure the infrared radiation energy of the object and convert it into a visual thermal image, then the temperature distribution on the surface of the bottled liquid is identified based on the thermal image, and finally the parameter index of the bottled liquid is predicted based on the temperature distribution. Since the related technology only focuses on the static surface temperature distribution when predicting the parameter index of the bottled liquid, the convection in the bottled liquid will cause the temperature distribution in the bottled liquid to be uneven, that is, the surface temperature distribution obtained based on the thermal image cannot accurately reflect the actual temperature distribution inside the bottled liquid, and the related technology lacks effective means to analyze how the temperature distribution of the bottled liquid is determined by the inherent properties of the liquid and how these temperature changes reflect the flow state of the liquid. Therefore, the related technology has the problem that the predicted parameter index cannot accurately reflect the actual parameter index of the bottled liquid due to the inability to perceive the influence of the convection dynamic data on the temperature distribution inside the bottled liquid, and the accuracy and reliability of the bottled liquid parameter index prediction are low.

[0004] At present, there is no effective technical solution to the above problems. It should be noted that the above information disclosed in this part is only used to understand the background of the present application concept, and therefore can contain information that does not constitute prior art. SUMMARY

[0005] The purpose of the present application is to provide a bottled liquid detection system and method, which can effectively solve the problem that the predicted parameter index cannot accurately reflect the actual parameter index of the bottled liquid due to the inability to perceive the influence of the convection dynamic data on the temperature distribution inside the bottled liquid, and the accuracy and reliability of the bottled liquid parameter index prediction are low.

[0006] In a first aspect, the present application provides a bottled liquid detection system, comprising:

[0007] a carrier table for placing a bottled liquid to be detected;

[0008] a rotating assembly connected with the carrier table;

[0009] a heating assembly arranged at the periphery of the bottle liquid to be detected;

[0010] a cooling assembly arranged at the periphery of the bottle liquid to be detected, and arranged at a different height from the heating assembly;

[0011] a thermal imaging camera arranged at one side of the object table;

[0012] a controller configured to induce controlled convection of the bottle liquid to be detected placed on the object table to generate convection in the bottle liquid to be detected, the controlled convection including heating the bottle liquid to be detected by the heating assembly, cooling the bottle liquid to be detected by the cooling assembly, and rotating the bottle liquid to be detected by the rotating assembly, and configured to acquire thermal imaging images of the bottle liquid to be detected at multiple time points by the thermal imaging camera during the controlled convection, and configured to acquire convection velocity field information corresponding to each thermal imaging image based on the thermal imaging images, and configured to predict a parameter index of the bottle liquid to be detected according to all the convection velocity field information.

[0013] The bottle liquid detection system provided by the application can effectively solve the problem that the predicted parameter index cannot accurately reflect the actual parameter index of the bottle liquid, and the accuracy and reliability of the prediction of the parameter index of the bottle liquid are low, because the influence of the convection dynamic data on the temperature distribution in the bottle liquid cannot be perceived.

[0014] Optionally, the step of acquiring the convection velocity field information corresponding to each thermal imaging image comprises:

[0015] A1. dividing all the thermal imaging images into multiple to-be-detected regions according to a preset division rule;

[0016] A2. for each to-be-detected region, acquiring a velocity vector of the to-be-detected region according to the gradient of all the pixel points in the to-be-detected region and the difference value between the central pixel point and the non-central pixel point of the to-be-detected region;

[0017] A3. for each thermal imaging image, integrating all the velocity vectors corresponding to the thermal imaging image to obtain the convection velocity field information corresponding to the thermal imaging image.

[0018] The technical scheme regards the velocity vectors of all pixel points in the same to-be-measured region as consistent by dividing the thermal imaging images into regions and calculating the velocity vectors of each to-be-measured region, that is, the technical scheme is equivalent to performing neighborhood pooling and down-sampling on the thermal imaging images, so as to replace the calculation of the velocity vectors of each pixel point with the calculation of the velocity vectors of the to-be-measured regions, thereby reducing the data processing amount of obtaining the convection velocity field information and improving the efficiency of obtaining the convection velocity field information.

[0019] Optionally, the step A1 comprises:

[0020] A11, performing edge detection on all the thermal imaging images to obtain a bottle outline of the to-be-detected bottled liquid;

[0021] A12, determining an internal liquid region of the to-be-detected bottled liquid in all the thermal imaging images according to the bottle outline and bottle thickness information;

[0022] A13, performing regional division on the internal liquid region based on a preset division rule to divide all the thermal imaging images into a plurality of to-be-measured regions.

[0023] The technical scheme regards the velocity vectors of all pixel points in the same to-be-measured region as consistent by dividing the thermal imaging images into regions and calculating the velocity vectors of each to-be-measured region, that is, the technical scheme is equivalent to performing neighborhood pooling and down-sampling on the thermal imaging images, so as to replace the calculation of the velocity vectors of each pixel point with the calculation of the velocity vectors of the to-be-measured regions, thereby reducing the data processing amount of obtaining the convection velocity field information and improving the efficiency of obtaining the convection velocity field information.

[0024] Optionally, the step A13 comprises:

[0025] A131, performing regional division on the internal liquid region based on a preset division rule to divide all the thermal imaging images into a plurality of initial division regions;

[0026] A132, for each initial division region, obtaining temperature distribution internal gradient information, boundary dynamic change information and motion trajectory continuity information thereof in different thermal imaging images;

[0027] A133, for each initial division region, analyzing whether the initial division region is a non-convection region according to the corresponding temperature distribution internal gradient information, boundary dynamic change information and motion trajectory continuity information, if yes, removing the initial division region, and if not, taking the initial division region as a to-be-measured region, the non-convection region including a bubble region and a precipitate region.

[0028] The technical scheme can accurately capture the thermal and kinematic characteristics unique to the bubble region and the precipitate region by obtaining the internal gradient information of the temperature distribution of the initial division region, the boundary dynamic change information and the motion trajectory continuity information, and can therefore accurately classify the initial division region based on these multi-dimensional information to effectively distinguish the convection region from the non-convection region, i.e., the technical scheme can ensure that the input data for subsequent calculation of the convection velocity field information only contains the liquid part actually participating in the convection, thereby avoiding noise and errors introduced by the non-convection region, and effectively improving the accuracy and reliability of the convection velocity field information acquisition and parameter index prediction.

[0029] Optionally, the step A2 comprises:

[0030] A21, for each to-be-tested region, obtaining spatial temperature gradient information of each pixel point in the to-be-tested region, and obtaining time temperature difference information of non-central pixel points and central pixel points in the to-be-tested region;

[0031] A22, for each to-be-tested region, analyzing whether the temperature field distribution of the to-be-tested region is uniform according to the spatial temperature gradient information and the time temperature difference information, if yes, obtaining a velocity vector of the to-be-tested region according to the gradient of all pixel points in the to-be-tested region and the difference value of the central pixel point and the non-central pixel point of the to-be-tested region, if not, performing step A23, and the judgment condition of the uniform temperature field distribution is that the spatial temperature gradient information is less than a preset temperature gradient and the time temperature difference information is less than a preset temperature difference;

[0032] A23, dividing the to-be-tested region with non-uniform temperature field distribution into a plurality of local sub-regions;

[0033] A24, obtaining a local velocity vector corresponding to each local sub-region according to the gradient of all pixel points in the local sub-region and the difference value of the central pixel point and the non-central pixel point of the local sub-region, and integrating all local velocity vectors corresponding to the same to-be-tested region to obtain a velocity vector corresponding to the to-be-tested region.

[0034] Optionally, the step of obtaining the convection velocity field information corresponding to each thermal imaging image further comprises a step performed before step A1:

[0035] A4, obtaining liquid type information of the to-be-tested bottled liquid;

[0036] A5, determining a preset division rule according to the liquid type information.

[0037] Optionally, the step of predicting the parameter index of the to-be-tested bottled liquid according to all the convection velocity field information comprises:

[0038] B1, obtaining brand information and formula information of the to-be-tested bottled liquid;

[0039] B2, determining a parameter prediction strategy according to the brand information and the formula information;

[0040] B3, predicting the parameter index of the bottle liquid to be detected according to all the convection velocity field information by using the parameter prediction strategy.

[0041] Optionally, the step of inducing controlled convection to the bottle liquid to be detected placed on the object table to generate convection in the bottle liquid to be detected comprises:

[0042] C1, obtaining an actual heating temperature of the heating assembly, an actual cooling temperature of the cooling assembly, and an actual rotation speed of the object table;

[0043] C2, adjusting the heating power of the heating assembly according to the actual heating temperature and a preset target heating temperature based on a first PID control algorithm, adjusting the cooling power of the cooling assembly according to the actual cooling temperature and a preset target cooling temperature based on a second PID control algorithm, and adjusting the working parameter of the rotating assembly according to the actual rotation speed and a preset target rotation speed based on a third PID control algorithm, to induce controlled convection to the bottle liquid to be detected placed on the object table and generate convection in the bottle liquid to be detected.

[0044] Optionally, the parameter index comprises density, viscosity, and taste index.

[0045] In a second aspect, the application further provides a bottle liquid detection method, which is applied in the bottle liquid detection system provided in the first aspect, and comprises the following steps:

[0046] S1, inducing controlled convection to the bottle liquid to be detected placed on the object table to generate convection in the bottle liquid to be detected, wherein the controlled convection induction comprises heating the bottle liquid to be detected by using the heating assembly, cooling the bottle liquid to be detected by using the cooling assembly, and rotating the bottle liquid to be detected by using the rotating assembly;

[0047] S2, obtaining thermal imaging images of the bottle liquid to be detected at multiple time points by using the thermal imaging camera during the controlled convection induction;

[0048] S3, obtaining convection velocity field information corresponding to each thermal imaging image based on the thermal imaging images;

[0049] S4, predicting the parameter index of the bottle liquid to be detected according to all the convection velocity field information.

[0050] The bottle liquid detection method provided by the application can obtain the convection velocity field information directly related to the physical and chemical properties of the liquid by actively inducing convection and capturing dynamic thermal imaging images in the convection process by using a thermal imaging camera, that is, the application is equivalent to introducing convection dynamic data when predicting the parameter index of the bottle liquid, and therefore the application can effectively solve the problem that the predicted parameter index cannot accurately reflect the actual parameter index of the bottle liquid due to the inability to perceive the influence of the convection dynamic data on the temperature distribution inside the bottle liquid, and the accuracy and reliability of the prediction of the parameter index of the bottle liquid are low.

[0051] As can be seen from the above, the bottle liquid detection system and method provided by the application can obtain the convection velocity field information directly related to the physical and chemical properties of the liquid by actively inducing convection and capturing dynamic thermal imaging images in the convection process by using a thermal imaging camera, that is, the application is equivalent to introducing convection dynamic data when predicting the parameter index of the bottle liquid, and therefore the application can effectively solve the problem that the predicted parameter index cannot accurately reflect the actual parameter index of the bottle liquid due to the inability to perceive the influence of the convection dynamic data on the temperature distribution inside the bottle liquid, and the accuracy and reliability of the prediction of the parameter index of the bottle liquid are low. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 A structural schematic diagram of a bottle liquid detection system provided by an embodiment of the application.

[0053] Figure 2 A flowchart of a bottle liquid detection method provided by an embodiment of the application.

[0054] The reference signs: 1, a carrier table; 2, a bottle liquid to be detected; 3, a rotating assembly; 4, a heating assembly; 5, a cooling assembly; 6, a thermal imaging camera; 7, a controller. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. The components of the embodiments of the application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the application provided in the drawings is not intended to limit the scope of the claimed application, but only represents selected embodiments of the application. Based on the embodiments of the application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the application.

[0056] It should be noted that similar reference numerals and letters refer to like items in the accompanying drawings, and once an item is defined in one drawing, it need not be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only to distinguish descriptions, and cannot be understood as indicating or implying relative importance.

[0057] In a first aspect, as shown in the accompanying drawings, the present application provides a bottled liquid detection system, which comprises: Figure 1 a carrier table 1 for placing a bottled liquid 2 to be detected;

[0058] a rotating assembly 3 connected with the carrier table 1;

[0059] a heating assembly 4 arranged at the outer periphery of the bottled liquid 2 to be detected;

[0060] a cooling assembly 5 arranged at the outer periphery of the bottled liquid 2 to be detected, and the arrangement height of the cooling assembly 5 is different from that of the heating assembly 4;

[0061] a thermal imaging camera 6 arranged at one side of the carrier table 1;

[0062] a controller 7 for inducing controlled convection of the bottled liquid 2 to be detected placed on the carrier table 1, so as to generate convection in the bottled liquid 2 to be detected, the controlled convection induction includes heating the bottled liquid 2 to be detected by the heating assembly 4, cooling the bottled liquid 2 to be detected by the cooling assembly 5, and rotating the bottled liquid 2 to be detected by the rotating assembly 3, and the controller 7 is further configured to acquire thermal imaging images of the bottled liquid 2 to be detected at multiple time points by the thermal imaging camera 6 during the controlled convection induction, acquire convection velocity field information corresponding to each thermal imaging image based on the thermal imaging images, and predict a parameter index of the bottled liquid 2 to be detected according to all the convection velocity field information.

[0063]

[0064] ​This application aims to effectively solve the problem of low accuracy in non-destructive testing of bottled liquids in the prior art by integrating automated convection induction, multi-time thermal imaging image acquisition, and parameter prediction based on convection velocity field information, thereby improving the accuracy and reliability of bottled liquid parameter prediction. The bottled liquid 2 to be tested in this embodiment is a bottled liquid for which parameter prediction is required. The bottled liquid detection system provided in this embodiment can generate observable convection phenomena inside the bottled liquid without damaging its appearance and packaging. Specifically, the controlled convection induction in this embodiment refers to the precise control of the operation of the heating component 4, the cooling component 5, and the rotating component 3 to form a stable and obvious convection pattern inside the bottled liquid. As can be seen from the Navier-Stokes equations, the velocity field of a fluid is correlated with the parameters of the fluid. Therefore, this convection pattern is closely related to the parameters of the bottled liquid 2 to be tested. That is, the dynamic characteristics of the convection velocity field information are related to the physicochemical properties of the bottled liquid to be tested. This means that liquids with different densities, viscosities, thermal conductivity, and specific heat capacities will exhibit different convection patterns and dynamic changes in the velocity field under the same controlled convection induction conditions. Therefore, this embodiment can predict the parameter indicators of the bottled liquid 2 to be tested based on all convection temperature field information by first obtaining the dynamic change of the convection velocity field with respect to time based on all convection velocity field information, and then making parameter predictions based on this dynamic change. The thermal imaging camera 6 in this embodiment is a device capable of capturing infrared radiation from the surface of an object and converting it into a visual thermal imaging image. This embodiment can obtain the temperature distribution information inside the bottled liquid 2 by analyzing these thermal imaging images. The convective velocity field information in this embodiment refers to a vector field describing the velocity and direction of fluid movement inside the bottled liquid. Since the optical flow equation and the thermal convection equation are similar in form—that is, the temperature field obtained based on the thermal imaging image is equivalent to the liquid convective velocity field—this embodiment can obtain the convective velocity field information corresponding to each thermal imaging image by generating a temperature field based on the thermal imaging image using an existing optical flow algorithm and using this temperature field as the convective velocity field. Preferably, taking the calculation of the convective velocity field information corresponding to a certain thermal imaging image as an example, the specific process is as follows: calculate the velocity vector of each pixel in the thermal imaging image, and then integrate all velocity vectors into the convective velocity field information. The formula for calculating the velocity vector is: Where I(x,y) represents the pixel value of the pixel at coordinates (x,y) in the current thermal image, and t represents time. This represents the image gradient of the pixel at coordinates (x, y) in the current thermal image, and v represents the velocity vector of the pixel at coordinates (x, y) in the current thermal image. This represents the difference between the current thermal imaging image and the thermal imaging images at adjacent time points. Since the pixel value of a pixel remains unchanged within the infinitesimally variable dt, that is... = 0, and the image gradient and difference value can be obtained by an image processing algorithm, so this embodiment can obtain the velocity vector by substituting the image gradient and difference value into the formula, and the set of all velocity vectors corresponding to the current thermal imaging image is the convection velocity field information of the current thermal imaging image. The parameter index of this embodiment refers to the key physical and chemical properties of the bottle liquid 2 to be detected, such as density, viscosity, taste index, etc., which are crucial for evaluating the quality and storage state of the bottle liquid.

[0065] The carrier table 1 of this embodiment is used to stably place the bottle liquid 2 to be detected, which can be a flat circular platform, and the surface thereof can be made of anti-skid material to ensure that the bottle liquid does not move during detection. The rotating assembly 3 of this embodiment is connected with the carrier table 1, which is used to drive the bottle liquid 2 to be detected through the carrier table 1, and can be composed of a motor and a transmission mechanism. The heating assembly 4 of this embodiment is arranged at the outer periphery of the bottle liquid 2 to be detected, which is used to heat the bottle liquid, and can be an existing resistance wire heater or PTC heater. The heating assembly 4 is preferably arranged around the outer wall of the bottle body of the bottle liquid 2 to be detected to ensure uniform heating of the bottle liquid 2 to be detected. The cooling assembly 5 of this embodiment is arranged at the outer periphery of the bottle liquid 2 to be detected, which is used to cool the bottle liquid 2 to be detected. Since the setting height of the cooling assembly 5 of this embodiment is different from that of the heating assembly 4 (the cooling assembly 5 is preferably located above the heating assembly 4), this embodiment is equivalent to forming a significant temperature gradient inside the bottle liquid 2 to be detected by using the cooling assembly 5 and the heating assembly 4, so that the liquid in the bottle liquid 2 to be detected flows spontaneously, thereby realizing the generation of convection in the bottle liquid 2 to be detected. The cooling assembly 5 can adopt an existing semiconductor refrigeration sheet or circulating water cooling device. The thermal imaging camera 6 of this embodiment is used to obtain thermal imaging images of the bottle liquid at multiple times during the controlled convection induction process, which can adopt an existing infrared thermal imager. The controller 7 of this embodiment can be an embedded system or an industrial PC, which runs special control software and image processing algorithms inside. The controller 7 can accurately adjust the heating power of the heating assembly 4, the cooling power of the cooling assembly 5, and the rotation speed of the rotating assembly 3 through the PID control algorithm, so as to realize accurate control of convection.

[0066] The bottle liquid detection system of the present application places the bottle liquid to be detected 2 on the object table 1, and uses the rotating assembly 3, the heating assembly 4 and the cooling assembly 5 to induce controlled convection of the bottle liquid. Specifically, the heating assembly 4 and the cooling assembly 5 act in coordination at different heights on the outer periphery of the bottle liquid to form a temperature gradient inside the bottle liquid, thereby inducing the generation of thermal convection. At the same time, the rotating assembly 3 rotates the bottle liquid, further enhancing and stabilizing the convection pattern. During the convection induction process, the thermal imaging camera 6 continuously acquires thermal imaging images of the bottle liquid at multiple time points, which record the dynamic changes of the temperature field inside the bottle liquid. The controller 7 receives these thermal imaging images and processes them to obtain convection velocity field information corresponding to each thermal imaging image. These convection velocity field information reflects the motion state of the fluid inside the bottle liquid, which is closely related to the density, viscosity and other parameter indicators of the liquid. Finally, the controller 7 uses a pre-set prediction model or algorithm to predict the parameter indicators of the bottle liquid based on all the obtained convection velocity field information.

[0067] The bottle liquid detection system provided by the present application actively induces convection and uses a thermal imaging camera to capture dynamic thermal imaging images during the convection process to obtain convection velocity field information directly related to the physical and chemical properties of the liquid. That is, the present application introduces convection dynamic data when predicting the parameter indicators of the bottle liquid, thereby effectively solving the problem that the predicted parameter indicators cannot accurately reflect the actual parameter indicators of the bottle liquid due to the inability to perceive the influence of convection dynamic data on the temperature distribution inside the bottle liquid, and improving the accuracy and reliability of the prediction of the parameter indicators of the bottle liquid. Therefore, the present application not only avoids the damage to the appearance and packaging of the bottle liquid caused by opening and sampling, but also significantly improves the accuracy and reliability of the prediction of the parameter indicators of the bottle liquid. That is, the present application provides a high-precision and non-destructive solution for the quality control and quality evaluation of bottle liquid.

[0068] In some preferred embodiments, the step of obtaining convection velocity field information corresponding to each thermal imaging image comprises:

[0069] A1, dividing all thermal imaging images into multiple test regions according to a pre-set division rule;

[0070] A2, for each test region, obtaining a velocity vector of the test region according to the gradient of all pixel points in the test region and the difference value between the center pixel point and the non-center pixel point of the test region;

[0071] A3, for each thermal imaging image, integrating all velocity vectors corresponding to the thermal imaging image to obtain the convection velocity field information corresponding to the thermal imaging image.

[0072] The preset division rule of step A1 can be set according to the physical characteristics of the bottle liquid 2 to be detected or the image resolution, for example, the preset division rule can be to divide the thermal imaging image into a regular grid area or to adaptively divide according to the temperature gradient distribution, preferably, the preset division rule indicates that the thermal imaging image is divided into a to-be-detected area according to every 3x3 pixel points, and each to-be-detected area is a local subset in the thermal imaging image, and the pixel points inside the to-be-detected area will be used to calculate the local speed information (the speed vector of the to-be-detected area). Step A2 is the core of obtaining the local speed vector. Specifically, for each to-be-detected area, first, the gradient information of all pixel points in the area is obtained, which reflects the rate and direction of temperature change in space. At the same time, the difference value of the center pixel point and the non-center pixel point of the to-be-detected area is obtained, which can reflect the relative change of the temperature field in the local area. By combining these spatial gradient information and relative difference values, the local motion trend and intensity of the fluid in the to-be-detected area (the speed vector of the to-be-detected area) can be derived using the optical flow algorithm principle in fluid mechanics or image processing. Preferably, the formula used by this embodiment to calculate the speed vector of the to-be-detected area is the same as the formula used by the above-mentioned embodiment to calculate the speed vector of the pixel point. Specifically, in the calculation of the speed vector of the to-be-detected area, this embodiment can use the average value of the gradients of all pixel points in the to-be-detected area instead of the image gradient of the pixel point with coordinates (x, y) in the current thermal imaging image in the above-mentioned embodiment. This embodiment uses the difference value of the center pixel point and the non-center pixel point of the to-be-detected area instead of the difference value of the current thermal imaging image and the thermal imaging image at the adjacent time in the above-mentioned embodiment. In step A3, the speed vectors of all to-be-detected areas corresponding to each thermal imaging image are integrated. This integration can be realized by vector superposition, interpolation or weighted average, etc. to construct the convection velocity field information of the entire to-be-detected bottle liquid 2 inside represented by the thermal imaging image. The integrated convection velocity field information is a vector field, where each point contains a speed vector indicating the direction and size of the fluid motion at that position, thereby fully reflecting the convection state inside the bottle liquid. This embodiment regards all pixel points in the same to-be-detected area as consistent by dividing the thermal imaging image into regions and calculating the speed vector of each to-be-detected area, that is, this embodiment is equivalent to performing neighborhood pooling and downsampling on the thermal imaging image to replace calculating the speed vector of each pixel point with calculating the speed vector of the to-be-detected area, thereby reducing the data processing amount of obtaining the convection velocity field information and improving the efficiency of obtaining the convection velocity field information. It should be understood that those skilled in the art can adjust the preset division rule according to actual needs to avoid the situation that the calculated speed vector cannot accurately reflect the speed vector of each pixel point in the to-be-detected area due to the to-be-detected area being too large, that is, this embodiment is equivalent to improving the calculation efficiency of the speed vector while ensuring the calculation accuracy of the speed vector.

[0073] In some preferred embodiments, step A1 comprises:

[0074] A11, performing edge detection on all thermal imaging images to obtain a bottle outline of the bottle containing liquid 2 to be detected;

[0075] A12, determining an internal liquid region of the bottle containing liquid 2 to be detected in all thermal imaging images according to the bottle outline and bottle thickness information;

[0076] A13, performing regional division on the internal liquid region based on a preset division rule to divide all thermal imaging images into a plurality of to-be-measured regions.

[0077] Step A11 accurately identifies the bottle outline of the bottle containing liquid 2 to be detected by performing edge detection on all thermal imaging images. This embodiment can use various mature image processing algorithms (such as Canny operator, Sobel operator or Prewitt operator, etc.) to realize edge detection, which identifies the boundaries in the image by analyzing the gray scale or temperature gradient changes of the image pixels. Step A12 determines the internal liquid region of the bottle containing liquid 2 to be detected in all thermal imaging images according to the obtained bottle outline and the preset bottle thickness information. Specifically, the bottle thickness information can be obtained according to the design parameters of the bottle or by actual measurement. Step A12 can accurately define the liquid region inside the bottle by inwardly contracting the bottle outline by a distance related to the bottle thickness, so as to ensure that the subsequent analysis focuses only on the actual liquid part, thereby excluding the interference of the bottle wall and the external space. This embodiment ensures the accuracy of regional division and avoids including non-liquid regions such as bottle or external environment into the analysis range by first performing edge detection on the thermal imaging images to obtain the bottle outline, then combining the bottle thickness information to determine the internal liquid region, and finally performing regional division only on the internal liquid region. That is, this embodiment effectively solves the problem that direct division of the entire thermal imaging image may introduce non-liquid region interference, so that the subsequent acquisition of the convection velocity field information can focus more on the convection activity of the liquid itself, thereby effectively improving the accuracy of the convection velocity field information acquisition and making the calculation result of the convection velocity field more truly reflect the convection state inside the bottle containing liquid, and further effectively improving the accuracy and reliability of the parameter index prediction.

[0078] In some preferred embodiments, step A13 comprises:

[0079] A131, performing regional division on the internal liquid region based on a preset division rule to divide all thermal imaging images into a plurality of initial division regions;

[0080] A132. For each initially divided region, obtain its internal gradient information of temperature distribution, dynamic boundary change information, and motion trajectory continuity information in different thermal imaging images;

[0081] A133. For each initially defined region, analyze whether the initially defined region is a non-convective region based on the corresponding internal gradient information of temperature distribution, dynamic change information of boundary, and continuity information of motion trajectory. If it is, remove the initially defined region; otherwise, take the initially defined region as the region to be measured. Non-convective regions include bubble regions and sediment regions.

[0082] For each initially segmented region, step A132 needs to acquire various information about it in different thermal imaging images. Specifically, the internal gradient information of the temperature distribution refers to the degree and direction of temperature change within the region. In this embodiment, the internal gradient information of the temperature distribution can be acquired by calculating the first or second derivative of the temperature of the pixels within the region. The dynamic change information of the boundary refers to the characteristics of the boundary of the region changing over time, such as the contraction, expansion, or shape change of the boundary. In this embodiment, the dynamic change information of the boundary can be acquired by comparing the boundary of the region in thermal imaging images at different times. The motion trajectory continuity information refers to whether the motion path of the region in a continuous sequence of thermal imaging images is smooth and continuous. In this embodiment, the motion trajectory continuity information can be acquired by analyzing it using techniques such as optical flow or feature point tracking. Step A133 is crucial for identifying and excluding non-convective regions, which include bubble regions and sediment regions. Since non-convective regions typically exhibit different thermal and kinematic characteristics compared to normal liquid convection regions—specifically, bubble regions usually show a large internal temperature gradient (due to the gas-liquid interface), irregular boundary dynamics (bubble bursting and merging), and discontinuous or abrupt motion trajectories; sediment regions typically show a small internal temperature gradient (usually with insignificant temperature changes), stable boundary dynamics (fixed or slowly moving), and discontinuous or stationary motion trajectories—step A133 can determine whether an initially defined region belongs to a non-convective region by comprehensively analyzing the internal temperature gradient information, boundary dynamics information, and motion trajectory continuity information corresponding to the initially defined region. For example, if an initially defined region has an extremely high temperature gradient and drastic boundary changes, and a discontinuous motion trajectory, then the initially defined region is identified as a bubble region; if an initially defined region has an extremely low temperature gradient and stable boundaries, and a nearly stationary motion trajectory, then the initially defined region is identified as a sediment region.

[0083] The embodiment can accurately capture the thermal and kinematic characteristics unique to the bubble region and the precipitate region by obtaining the internal gradient information of the temperature distribution of the initial division region, the boundary dynamic change information, and the motion trajectory continuity information, and thus can accurately classify the initial division region based on these multi-dimensional information to effectively distinguish the convection region from the non-convection region, i.e., the embodiment can ensure that the input data for subsequent calculation of the convection velocity field information only contains the liquid part actually participating in the convection, thereby avoiding the noise and errors introduced by the non-convection region, and effectively improving the accuracy and reliability of the convection velocity field information acquisition and parameter index prediction.

[0084] In some preferred embodiments, the following is described by a specific example. Assume that when detecting a bottled beverage, the thermal imaging camera 6 obtains a series of thermal imaging images. First, according to steps A11 and A12 described above, the internal liquid region of the bottled beverage is determined. Then, in step A131, the internal liquid region is divided into a plurality of initial division regions, each of which includes 3x3 pixel points. Subsequently, in step A132, for each initial division region, the system calculates its average temperature gradient in consecutive thermal imaging images, the displacement variance of the boundary pixel points, and the motion trajectory continuity information of the region center point. For example, if the average temperature gradient of a certain initial division region is much higher than that of the surrounding region, the boundary displacement variance is large, and the motion trajectory changes dramatically in a short time, then in step A133, the region may be determined as a bubble region and removed. Conversely, if the average temperature gradient of a certain initial division region is extremely low, the boundary displacement variance is close to zero, and the motion vector is almost zero or very slow and continuous, then the region may be determined as a precipitate region and removed. Finally, the initial division regions determined as non-convection regions are removed, and the remaining initial division regions are confirmed as the to-be-detected regions. In this way, it is ensured that the calculation of the convection velocity field information is based on pure liquid convection regions, thereby improving the accuracy of the detection result.

[0085] In some preferred embodiments, step A2 comprises:

[0086] A21, for each to-be-detected region, obtaining spatial temperature gradient information of each pixel point in the to-be-detected region, and obtaining time temperature difference information of non-central pixel points and central pixel points in the to-be-detected region;

[0087] A22、for each to-be-tested region, it is analyzed whether the temperature field distribution of the to-be-tested region is uniform according to the spatial temperature gradient information and the time temperature difference information, if yes, the speed vector of the to-be-tested region is obtained according to the gradient of all pixel points in the to-be-tested region and the difference value of the center pixel point and the non-center pixel point of the to-be-tested region, if not, step A23 is executed, the judgment condition of the uniform temperature field distribution is that the spatial temperature gradient information is less than a preset temperature gradient and the time temperature difference information is less than a preset temperature difference;

[0088] A23, the to-be-tested region with non-uniform temperature field distribution is divided into multiple local sub-regions;

[0089] A24, the local speed vector corresponding to each local sub-region is obtained according to the gradient of all pixel points in the local sub-region and the difference value of the center pixel point and the non-center pixel point of the local sub-region, and all local speed vectors corresponding to the same to-be-tested region are integrated to obtain the speed vector corresponding to the to-be-tested region.

[0090] The acquiring of the spatial temperature gradient information of each pixel point in the to-be-tested region refers to representing the distribution characteristics of temperature in space by calculating the temperature variation rate between adjacent pixel points in the to-be-tested region. Specifically, an image processing algorithm such as a Sobel operator, a Prewitt operator or a Roberts operator can be used to achieve this. These operators calculate the gradient of the image through convolution operation, thereby obtaining the spatial temperature gradient information. The acquiring of the time temperature difference information of the non-central pixel points and the central pixel point in the to-be-tested region refers to reflecting the dynamic characteristics of temperature change over time by comparing the difference between the temperature values of the non-central pixel points at different times and the temperature value of the central pixel point at the corresponding time. This embodiment can acquire the time temperature difference information by directly subtracting the temperature values of the non-central pixel points and the central pixel point, for example, for a non-central pixel point P(x, y) and a central pixel point C, the time temperature difference can be represented as ΔT(x, y, t) = T(x, y, t) - T(C, t). This embodiment compares the spatial temperature gradient information with the preset temperature gradient and compares the time temperature difference information with the preset temperature difference to analyze whether the temperature field distribution of the to-be-tested region is uniform. Specifically, if the spatial temperature gradient information is less than the preset temperature gradient and the time temperature difference information is less than the preset temperature difference, it is determined that the temperature field distribution is uniform. It should be understood that the preset temperature gradient and the preset temperature difference can be set according to empirical values, experimental data or the requirements of a specific application scenario. When it is analyzed that the temperature field distribution is not uniform, this embodiment can use methods such as quadtree decomposition, K-means clustering or image segmentation algorithms (such as the watershed algorithm) to divide the to-be-tested region with non-uniform temperature field distribution into multiple local sub-regions. For example, the division boundary is determined according to the local maximum of the temperature gradient or the local non-uniformity of the temperature difference, so as to divide a large non-uniform region into multiple relatively uniform small regions. The specific process of acquiring the local velocity vector corresponding to each local sub-region is preferably the same as the specific process of acquiring the velocity vector of the to-be-tested region in the above embodiment, which will not be discussed in detail here. This embodiment can use a weighted average, interpolation or fusion method based on a physical model (such as the Navier-Stokes equation) to integrate all the local velocity vectors corresponding to the same to-be-tested region to obtain the velocity vector corresponding to the to-be-tested region. For example, different weights are given to different local velocity vectors according to the area of each local sub-region or the degree of uniformity of its temperature field, and then a weighted average is performed or the local velocity vectors are smoothly connected through an interpolation algorithm to form the velocity field of the entire to-be-tested region.The embodiment is equivalent to effectively improving the accuracy of the acquisition of the velocity vector in the case that the temperature field distribution of the to-be-tested region is uneven, by dividing the to-be-tested region into multiple local sub-regions, respectively calculating the local velocity vector, and then integrating, so as to make the acquisition of the convection velocity field information more accurate and reliable, that is, the embodiment can further improve the accuracy and reliability of the convection velocity field information.

[0091] In some preferred embodiments, the step of acquiring the convection velocity field information corresponding to each thermal imaging image further comprises a step performed before step A1:

[0092] A4, acquiring liquid type information of the to-be-tested bottled liquid 2;

[0093] A5, determining a preset division rule according to the liquid type information.

[0094] Step A4 can acquire the liquid type information by scanning the bar code or two-dimensional code on the to-be-tested bottled liquid 2 to query the relevant parameter information of the to-be-tested bottled liquid 2. Step A5 of determining a preset division rule according to the liquid type information means that after acquiring the liquid type information, the system will dynamically select or generate a region division rule most suitable for the current liquid type according to the information, for example, a database or lookup table containing multiple liquid types and corresponding division rules can be pre-stored in the controller 7, and when a certain liquid type information is acquired, the controller 7 retrieves the corresponding preset division rule from the database. The preset division rule of this embodiment can include but is not limited to the size, shape, division density of the region, and specific physical boundary conditions that need to be considered in the division process, etc.

[0095] This embodiment realizes the dynamic determination of the preset division rule according to the specific liquid type by acquiring the liquid type information of the to-be-tested bottled liquid 2 before performing the region division, and then dynamically determining the preset division rule based on the information, so that the preset division rule can better adapt to the physical characteristics and thermal convection behavior of different liquids, for example, for liquids with high viscosity, more detailed region division may be needed to capture local slow convection; while for liquids with low viscosity, more rough division can be used to focus on the overall flow trend, therefore, this embodiment can effectively avoid errors caused by mismatch between the preset division rule and the liquid type, thereby further improving the accuracy and reliability of the convection velocity field information acquisition, and further improving the robustness and applicability of the bottled liquid detection system.

[0096] In some preferred embodiments, the following is illustrated by a specific example. Assume that the bottled liquid 2 to be detected is mineral water or edible oil. When performing step A4, the controller 7 identifies the bottled liquid as mineral water by scanning the product label barcode on the bottled liquid 2 to be detected. Subsequently, when performing step A5, the controller 7 retrieves the region division rule for aqueous liquid from the preset database according to the liquid type information of “mineral water”, for example, the rule stipulates that due to the low viscosity of water, the convection velocity is relatively fast, and therefore a relatively uniform and slightly larger grid can be used for region division in the thermal imaging image to capture the overall flow field characteristics. If the bottled liquid 2 to be detected is identified as “edible oil”, the controller 7 will determine another set of division rules according to the liquid type information of “edible oil”, specifically, since the viscosity of edible oil is usually higher than that of water, its convection may be slower and more local, therefore the preset division rule corresponding to edible oil uses a finer grid for region division to capture local convection details more finely. In this way, the system can flexibly adjust the region division strategy according to the characteristics of different liquids to ensure that the most accurate convection velocity field information can be obtained regardless of the liquid being detected.

[0097] In some preferred embodiments, the step of predicting the parameter index of the bottled liquid 2 to be detected according to all the convection velocity field information comprises:

[0098] B1, obtaining brand information and formula information of the bottled liquid 2 to be detected;

[0099] B2, determining a parameter prediction strategy according to the brand information and the formula information;

[0100] B3, predicting the parameter index of the bottled liquid 2 to be detected according to all the convection velocity field information using the parameter prediction strategy.

[0101] The brand information and formula information of the bottle liquid 2 to be detected can be understood as obtaining specific identification and constituent data of the bottle liquid through various ways, for example, the brand and product model can be automatically identified by scanning the bar code or two-dimensional code on the bottle body, and then the corresponding formula information is retrieved from the preset database; or the brand and formula details of the bottle liquid can be manually input by the operator. Specifically, the brand information refers to the identification of the manufacturer or product series, and the formula information refers to the specific ingredient composition, production process parameters or physical and chemical property description of the liquid product. Determining the parameter prediction strategy according to the obtained brand information and formula information refers to selecting or generating a model or algorithm most suitable for the bottle liquid for parameter prediction based on these specific data. For example, the response characteristics of the density, viscosity and other parameters of liquids of different brands or formulas may be different when heated or cooled. Specifically, the embodiment can pre-establish a strategy library containing a plurality of prediction models or parameter adjustment rules. When the specific brand and formula are identified, the system can automatically match and call the corresponding prediction strategy. The parameter prediction strategy can be a specific machine learning model (such as neural network, support vector machine, etc.), and the parameter prediction strategy can also be a set of weight coefficients or calibration curves optimized for the liquid characteristics. Since the embodiment uses the parameter prediction strategy determined based on the brand information and formula information to predict the parameter indicators of the bottle liquid 2 to be detected according to all the convection velocity field information, it means that after obtaining the convection velocity field information generated by the bottle liquid 2 to be detected in the controlled convection induction process, a general model is no longer used for prediction, but the velocity field information is input into the prediction strategy optimized for the specific brand and formula. Therefore, the embodiment can obtain more accurate parameter indicator prediction results. Since liquids of different brands and formulas have their unique physical and chemical properties and thermodynamic responses, these characteristics will directly affect the correlation between the convection pattern formed under the controlled convection induction and the final parameter indicators. Therefore, the embodiment can select or generate a highly matched prediction model or algorithm for each liquid by introducing the brand information and formula information of the bottle liquid 2 to be detected and determining the customized parameter prediction strategy, so as to effectively solve the problem of insufficient accuracy of the general prediction model when processing diversified liquid products, thereby effectively improving the accuracy and reliability of parameter indicator prediction.

[0102] In some preferred embodiments, the following is illustrated by a specific example. Suppose that two different brands of milk need to be detected, for example, brand A pure milk and brand B low-fat milk. After the controlled convection induction is carried out and the convection velocity field information is obtained, the system first obtains the brand information and formula information of the two kinds of milk. For brand A pure milk, the system will select a parameter prediction model optimized for high-fat milk from the preset strategy library according to its brand and formula (for example, it is known that its fat content is high and the viscosity is relatively large), which may have used a large amount of brand A pure milk data during training and considered its unique thermophysical properties. For brand B low-fat milk, the system will select another parameter prediction model optimized for low-fat milk, which may focus more on capturing the subtle changes of low-viscosity liquids in convection. In this way, even if the convection velocity field information of the two kinds of milk is similar in some aspects, the predicted density, viscosity or taste indicators will be more accurate in reflecting the true characteristics of the respective products by using targeted prediction strategies, thereby avoiding the prediction bias that may be caused by using a single model.

[0103] In some preferred embodiments, the step of inducing controlled convection in the bottle liquid 2 placed on the stage 1 to generate convection in the bottle liquid 2 includes:

[0104] C1, obtaining the actual heating temperature of the heating assembly 4, the actual cooling temperature of the cooling assembly 5, and the actual rotation speed of the stage 1;

[0105] C2, adjusting the heating power of the heating assembly 4 based on the first PID control algorithm according to the actual heating temperature and the preset target heating temperature, adjusting the cooling power of the cooling assembly 5 based on the second PID control algorithm according to the actual cooling temperature and the preset target cooling temperature, and adjusting the working parameters of the rotating assembly 3 based on the third PID control algorithm according to the actual rotation speed and the preset target rotation speed, to induce controlled convection in the bottle liquid 2 placed on the stage 1 and generate convection in the bottle liquid 2.

[0106] The actual heating temperature of this embodiment refers to the current temperature value of the heating assembly 4 monitored in real time by the temperature sensor arranged near the heating assembly 4, the actual cooling temperature of this embodiment refers to the current temperature value of the cooling assembly 5 monitored in real time by the temperature sensor arranged near the cooling assembly 5, and the actual rotation speed of this embodiment refers to the current rotation speed of the object table 1 detected in real time by the speed sensor or encoder arranged on the rotation assembly 3. The acquisition of these actual parameters aims to provide real-time feedback data for the subsequent control algorithm. The first PID control algorithm, the second PID control algorithm and the third PID control algorithm (Proportional-Integral-Derivative control algorithm) of this embodiment are a feedback control method widely used in industrial control field, which adjusts the control quantity according to the weighted sum of the proportional, integral and derivative parameters by calculating the error between the set value and the actual value. Specifically, the first PID control algorithm is used to dynamically adjust the heating power of the heating assembly 4 according to the deviation between the actual heating temperature and the preset target heating temperature, so that the temperature of the heating assembly 4 approaches and stabilizes at the target heating temperature, the second PID control algorithm is used to dynamically adjust the cooling power of the cooling assembly 5 according to the deviation between the actual cooling temperature and the preset target cooling temperature, so that the temperature of the cooling assembly 5 approaches and stabilizes at the target cooling temperature, and the third PID control algorithm is used to dynamically adjust the working parameters (such as motor driving voltage or current) of the rotation assembly 3 according to the deviation between the actual rotation speed and the preset target rotation speed, so that the rotation speed of the object table 1 approaches and stabilizes at the target rotation speed. The target heating temperature, the target cooling temperature and the target rotation speed of this embodiment are preferably the ideal operating parameters preset according to the type of the bottle liquid 2 to be detected, the expected convection mode and the detection requirements. This embodiment realizes accurate and dynamic adjustment of the heating assembly 4, the cooling assembly 5 and the rotation assembly 3 by introducing the PID control algorithm. Since the PID control algorithm can acquire actual running parameters in real time and make feedback adjustment according to the deviation between the actual running parameters and the target parameters, this embodiment can continuously optimize the heating power, the cooling power and the working parameters of the rotation assembly 3, so as to ensure that the heating, cooling and rotation processes are always carried out according to the preset conditions, thereby effectively offsetting the influence of external environmental changes and system internal disturbances on the convection induction process and ensuring the stability and repeatability of the internal convection of the bottle liquid 2 to be detected. By accurately controlling the temperature gradient and the shear force, a specific and stable convection mode can be induced, which is crucial for accurately obtaining the thermal imaging image and the convection velocity field information subsequently.By the technical solution, the accuracy and stability of the controlled convection induction process can be improved significantly. Since the heating, cooling and rotation conditions are accurately controlled at the preset target values, the convection mode generated inside the bottle liquid 2 to be detected is more stable and predictable, so that clearer and more accurate thermal imaging images can be obtained, and the extraction of the convection velocity field information is more reliable, thereby effectively improving the accuracy and reliability of the prediction of the parameter index of the bottle liquid.

[0107] In some preferred embodiments, the parameter index includes density, viscosity and mouthfeel index. The density refers to the mass of a substance per unit volume, which is a basic physical property of a liquid, and its change can reflect the change of the composition or state of the liquid. The viscosity refers to the resistance of a fluid to shear stress, which reflects the difficulty of liquid flow and has an important influence on the processing, storage and use performance of the liquid. The mouthfeel index is a comprehensive sensory evaluation, which usually involves the flavor, texture and body of the liquid, and is particularly crucial for product quality control in the food and beverage industries.

[0108] In a second aspect, as shown in Figure 2 The application also provides a bottle liquid detection method, which is applied in the bottle liquid detection system provided in the first aspect, and the method comprises the following steps:

[0109] S1, controlled convection induction is performed on the bottle liquid 2 to be detected placed on the object table 1 to generate convection in the bottle liquid 2 to be detected, and the controlled convection induction comprises heating the bottle liquid 2 to be detected by the heating assembly 4, cooling the bottle liquid 2 to be detected by the cooling assembly 5, and rotating the bottle liquid 2 to be detected by the rotating assembly 3;

[0110] S2, during the controlled convection induction, the thermal imaging camera 6 is used to acquire thermal imaging images of the bottle liquid 2 to be detected at multiple time points;

[0111] S3, the convection velocity field information corresponding to each thermal imaging image is acquired based on the thermal imaging images;

[0112] S4, the parameter index of the bottle liquid 2 to be detected is predicted according to all the convection velocity field information.

[0113] The bottle liquid detection method provided by the application is applied in the bottle liquid detection system provided in the first aspect, and the principle of the bottle liquid detection method provided in this embodiment is the same as that of the bottle liquid detection system provided in the first aspect, which will not be discussed in detail here.

[0114] From the above, the bottle liquid detection system and method provided by the application can obtain the convection velocity field information directly related to the physical and chemical properties of the liquid by actively inducing convection and using a thermal imaging camera to capture dynamic thermal imaging images in the convection process, that is, the application is equivalent to introducing convection dynamic data when predicting the parameter index of the bottled liquid, and therefore the application can effectively solve the problem that the predicted parameter index cannot accurately reflect the actual parameter index of the bottled liquid due to the inability to perceive the influence of the convection dynamic data on the temperature distribution inside the bottled liquid, and the accuracy and reliability of the bottled liquid parameter index prediction are low.

[0115] In the embodiments provided in the present application, it should be understood that, in this paper, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations.

[0116] The above is only an embodiment of the present application and is not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A bottled liquid detection system, characterized by, The bottle liquid detection system comprises: a stage for placing a bottle liquid to be detected; a rotating assembly connected to the stage; a heating assembly arranged at the periphery of the bottle liquid to be detected; a cooling assembly arranged at the periphery of the bottle liquid to be detected, and having a different arrangement height from the heating assembly; a thermal imaging camera arranged at one side of the stage; a controller configured to induce a controlled convection in the bottle liquid to be detected placed on the stage to generate a convection in the bottle liquid to be detected, the controlled convection induction comprising heating the bottle liquid to be detected by the heating assembly, cooling the bottle liquid to be detected by the cooling assembly, and rotating the bottle liquid to be detected by the rotating assembly, acquiring thermal imaging images of the bottle liquid to be detected at multiple time points by the thermal imaging camera during the controlled convection induction, acquiring convection velocity field information corresponding to each thermal imaging image based on the thermal imaging images, and predicting a parameter index of the bottle liquid to be detected according to all the convection velocity field information; the step of acquiring the convection velocity field information corresponding to each thermal imaging image comprises: A1, dividing all the thermal imaging images into multiple test regions according to a preset division rule; A2, for each test region, acquiring a velocity vector of the test region according to a gradient of all pixel points in the test region and a difference value between a center pixel point and a non-center pixel point of the test region; A3, for each thermal imaging image, integrating all the velocity vectors corresponding to the thermal imaging image to obtain the convection velocity field information corresponding to the thermal imaging image; step A2 comprises: A21, for each test region, acquiring spatial temperature gradient information of each pixel point in the test region, and acquiring time temperature difference information of a non-center pixel point and a center pixel point in the test region; A22, for each test region, analyzing whether a temperature field distribution of the test region is uniform according to the spatial temperature gradient information and the time temperature difference information, if yes, acquiring a velocity vector of the test region according to a gradient of all pixel points in the test region and a difference value between a center pixel point and a non-center pixel point of the test region, if not, performing step A23, and the judgment condition that the temperature field distribution is uniform is that the spatial temperature gradient information is less than a preset temperature gradient and the time temperature difference information is less than a preset temperature difference; A23, dividing the test region with the non-uniform temperature field distribution into multiple local sub-regions; A24, acquiring a local velocity vector corresponding to each local sub-region according to a gradient of all pixel points in the local sub-region and a difference value between a center pixel point and a non-center pixel point of the local sub-region, and integrating all the local velocity vectors corresponding to the same test region to obtain a velocity vector corresponding to the test region.

2. The bottled liquid detection system of claim 1, wherein, step A1 comprises: A11, performing edge detection on all the thermal imaging images to obtain a bottle outline of the bottle liquid to be detected; A12, determining the internal liquid region of the bottle liquid to be detected in all the thermal imaging images according to the bottle body contour and bottle body thickness information; A13, performing region division on the internal liquid region based on a preset division rule to divide all the thermal imaging images into a plurality of to-be-measured regions.

3. The bottled liquid detection system of claim 2, wherein, Step A13 includes: A131, performing region division on the internal liquid region based on a preset division rule to divide all the thermal imaging images into a plurality of initial division regions; A132, for each initial division region, acquiring its temperature distribution internal gradient information, boundary dynamic change information and motion trajectory continuity information in different thermal imaging images; A133, for each initial division region, analyzing whether it is a non-convection region according to the corresponding temperature distribution internal gradient information, boundary dynamic change information and motion trajectory continuity information, if yes, removing the initial division region, if not, taking the initial division region as a to-be-measured region, the non-convection region includes a bubble region and a precipitate region.

4. The bottled liquid detection system of claim 2, wherein, The step of acquiring the convection velocity field information corresponding to each thermal imaging image further includes a step performed before step A1: A4, acquiring liquid type information of the bottle liquid to be detected; A5, determining a preset division rule according to the liquid type information.

5. The bottled liquid detection system of claim 1, wherein, The step of predicting the parameter index of the bottle liquid to be detected according to all the convection velocity field information includes: B1, acquiring brand information and formula information of the bottle liquid to be detected; B2, determining a parameter prediction strategy according to the brand information and the formula information; B3, predicting the parameter index of the bottle liquid to be detected according to all the convection velocity field information by using the parameter prediction strategy.

6. The bottled liquid detection system of claim 1, wherein, The step of performing controlled convection induction on the bottle liquid to be detected placed on the object table to generate convection in the bottle liquid to be detected includes: C1, acquiring actual heating temperature of the heating assembly, actual cooling temperature of the cooling assembly and actual rotation speed of the object table; C2, adjusting the heating power of the heating assembly based on a first PID control algorithm according to the actual heating temperature and a preset target heating temperature, adjusting the cooling power of the cooling assembly based on a second PID control algorithm according to the actual cooling temperature and a preset target cooling temperature, and adjusting the working parameters of the rotation assembly based on a third PID control algorithm according to the actual rotation speed and a preset target rotation speed, to perform controlled convection induction on the bottle liquid to be detected placed on the object table and generate convection in the bottle liquid to be detected.

7. The bottled liquid detection system of claim 1, wherein, The parameter index includes density, viscosity and taste index.

8. A method of detecting a bottled liquid, characterized by, The bottle liquid detection method is applied in the bottle liquid detection system as claimed in any one of claims 1-7, and the bottle liquid detection method includes the following steps: S1, controlled convection induction is performed on a bottle liquid placed on a stage to generate convection in the bottle liquid, the controlled convection induction comprising heating the bottle liquid by the heating assembly, cooling the bottle liquid by the cooling assembly, and rotating the bottle liquid by the rotating assembly; S2, during the controlled convection induction, thermal imaging images of the bottle liquid at multiple time points are acquired by the thermal imaging camera; S3, convection velocity field information corresponding to each thermal imaging image is acquired based on the thermal imaging images; S4, a parameter index of the bottle liquid is predicted according to all the convection velocity field information.

Images