Particle material residence time distribution detection method, device, equipment and medium

Abstract

The invention relates to the technical field of solid granulation, and discloses a particle material retention time distribution detection method, device, equipment and medium, and the method comprises the following steps: adding a tracer agent into a particle material under the condition that the granulation process reaches a preset state to obtain a granulation sample containing the tracer agent; continuously collecting the granulation samples by using the sample collection container until the visual distinguishing features of the granulation samples vertically stacked in the sample collection container meet the preset visual feature requirements, thereby obtaining collected samples; carrying out image acquisition on the collected sample to obtain a sample analysis image; performing residence time distribution analysis according to the visual feature distribution data of the sample analysis image to obtain an initial detection result; and performing flow error correction on the initial detection result according to the actual flow of the particle material in the granulation process to obtain a retention time distribution detection result. The device has the beneficial effects that the accuracy of retention time distribution detection is effectively improved through continuous collection of granulation samples and flow error correction.

Description

Technical Field

[0001] The present application relates to the technical field of solid granulation, and in particular to a method, device, equipment and medium for detecting the residence time distribution of granular materials. Background Art

[0002] In the pharmaceutical industry, traditional batch granulation processes typically involve separate material preparation and independent production for each batch. This approach often leads to significant differences between batches, limiting product consistency and stability. To address this issue, the pharmaceutical industry is gradually shifting from batch granulation to continuous granulation. By operating continuously on a single production line, this effectively reduces downtime between batches and the resulting material waste, improving production efficiency while ensuring product uniformity and consistency through real-time, precise process control, significantly enhancing product quality.

[0003] In continuous granulation processes, residence time distribution directly influences the processing conditions to which the pelletized material is subjected. Based on rational process parameter design, precise control of residence time distribution can significantly improve product quality stability and production efficiency. However, the accuracy of residence time distribution detection methods in related technologies still needs to be improved. Summary of the Invention

[0004] The present application provides a method, device, equipment and medium for detecting the residence time distribution of granular materials, which uses a sample collection container to continuously collect granulation samples, so that the distribution of the visual resolution characteristics of the collected samples in the vertical direction reflects the residence time distribution of the granular material during the granulation process, and effectively improves the accuracy of residence time distribution detection through flow error correction.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, embodiments of the present application provide a method for detecting residence time distribution of a granular material, the method comprising: adding a tracer to the granular material when the granulation process of the granular material reaches a predetermined granulation state to obtain a granulation sample containing the tracer; wherein the tracer and the granular material have different visual resolution characteristics; The granulated sample is continuously collected using a sample collection container until the visual distinguishing characteristics of the granulated sample vertically stacked in the sample collection container meet the preset visual characteristic requirements, thereby obtaining a collected sample; wherein the height of the sample collection container is greater than the cross-sectional size, and the cross-sectional size of the sample collection container is determined according to the flow rate of the granulated sample; Performing image acquisition on the collected sample to obtain a sample analysis image; performing residence time distribution analysis on the particulate material based on visual feature distribution data of the sample analysis image to obtain an initial detection result of the particulate material; The initial detection result is corrected for flow error according to the actual flow of the granular material during the granulation process to obtain a residence time distribution detection result of the granular material.

[0006] The residence time distribution detection method of the granular material proposed in the embodiment of the present application utilizes a sample collection container to continuously collect the granulation sample containing the tracer, so that the granulation sample can be vertically accumulated in the sample collection container to obtain the collected sample, thereby being able to reflect the residence time distribution of the granular material in the granulation process by the distribution of the visual resolution characteristics of the collected sample in the vertical direction, and on the basis of obtaining the initial detection result, the initial detection result is corrected for the flow error according to the actual flow of the granulation process, thereby obtaining the residence time distribution detection result of the granular material. Compared with the related art, on the one hand, the present application obtains the collected sample based on the granulation sample vertically accumulated in the sample collection container, realizes the continuous sampling of the granulation sample, effectively improves the data accuracy and resolution of the sampling, and thus improves the accuracy of the residence time distribution detection result. On the other hand, the present application uses the granulation sample after the granulation process as the collection object, rather than sampling the material in the reactor during the granulation process, reducing the influence of the sampling step on the granulation process, ensuring the stability of the granulation process, thereby indirectly improving the accuracy of the residence time distribution detection result. In addition, this application also takes into account the impact of the flow error of the granulation process on the residence time distribution detection, and corrects the flow error of the initial detection result based on the actual flow of the granulation process to obtain the residence time distribution detection result, further improving the accuracy of the residence time distribution detection result.

[0007] Optionally, performing flow error correction on the initial detection result according to the actual flow rate of the granular material during the granulation process to obtain a residence time distribution detection result of the granular material includes: Performing an error analysis based on the average flow rate and the actual flow rate of the granulation process to obtain a flow deviation of the granular material; wherein the time point corresponding to the flow deviation is recorded as a target time point; Performing data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data; The residence time distribution detection result is constructed based on the correction data and the residence time data of other time points except the target time point in the initial detection result.

[0008] Optionally, performing data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data includes: When the flow deviation is positive, the residence time data of the target time point is corrected in advance according to the correction proportional coefficient and the flow deviation to obtain the corrected data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

[0009] Optionally, performing data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data includes: When the flow deviation is negative, the residence time data at the target time point is subjected to a timing delay correction based on a correction proportional coefficient and the flow deviation to obtain the corrected data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

[0010] Optionally, performing residence time distribution analysis on the particulate material according to the visual feature distribution data of the sample analysis image to obtain an initial detection result of the particulate material includes: Calibrate the tracer concentration based on the visual feature distribution data to obtain concentration change time series data of the tracer; perform proportional conversion based on the concentration change time series data and the total concentration of the tracer to obtain concentration ratio time series data of the tracer; Performing cumulative calculation based on the concentration ratio time series data to obtain cumulative residence time data of the particulate material during the granulation process; An initial detection result of the particulate material is obtained based on the concentration ratio time series data and the residence time accumulation data.

[0011] Optionally, the visual feature distribution data of the sample analysis image is obtained by: Performing target region selection and grid division on the sample analysis image to obtain a sample image to be processed representing the target detection region in the sample analysis image; The sample image to be processed is converted into a target color space, and visual features are extracted from the converted sample image to obtain the visual feature distribution data; wherein the target color space is selected according to the type of the visual feature distribution data, and the visual feature distribution data represents the distribution of the visual resolution features of the collected samples in the vertical direction.

[0012] Optionally, the residence time distribution detection result includes a residence time distribution curve; the method further comprises: performing statistical parameter extraction based on the residence time distribution detection result to obtain residence time distribution parameters; Performing shape analysis on the residence time distribution curve to obtain a residence time distribution line shape; The flow state of the granulation process is analyzed according to the residence time distribution parameter and the residence time distribution line shape to obtain the flow state of the granular material in the granulation process.

[0013] In a second aspect, an embodiment of the present application provides a device for detecting the residence time distribution of a granular material, the device comprising: a granular material tracing module configured to add a tracer to the granular material when the granulation process of the granular material reaches a preset granulation state, thereby obtaining a granulation sample containing the tracer; wherein the tracer and the granular material each have different visual resolution characteristics; a granulation sample collection module, configured to continuously collect the granulation sample using a sample collection container until the visual discrimination characteristics of the granulation sample vertically stacked in the sample collection container meet preset visual characteristic requirements, thereby obtaining a collected sample; wherein the height of the sample collection container is greater than the cross-sectional dimension, and the cross-sectional dimension of the sample collection container is determined according to the flow rate of the granulation sample; An image acquisition and analysis module is used to acquire images of the collected samples to obtain sample analysis images; perform residence time distribution analysis on the particulate material based on visual feature distribution data of the sample analysis images to obtain initial detection results of the particulate material; The flow error correction module is used to perform flow error correction on the initial detection result according to the actual flow of the granular material during the granulation process to obtain a residence time distribution detection result of the granular material.

[0014] In a third aspect, an embodiment of the present application provides a computer device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the method described in any one of the above embodiments by executing the computer instructions.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute any one of the methods in the above embodiments.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising computer instructions, wherein the computer instructions are used to enable a computer to execute any one of the methods described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A diagram showing the steps of a method for detecting the residence time distribution of particulate material provided in an embodiment of the present application; Figure 2 This is a schematic diagram of an application of a twin-screw granulator in an embodiment of the present application; Figure 3 A diagram showing the steps for constructing the residence time distribution detection results in an embodiment of the present application; Figure 4 Schematic diagram of the curve of average flow rate and actual flow rate in the embodiment of the present application; Figure 5 This is a diagram showing the steps of performing residence time distribution analysis on particulate material in an embodiment of the present application; Figure 6a Schematic diagram of a sample with known tracer concentration in an embodiment of the present application; Figure 6b This is a calibration relationship diagram of the tracer concentration and visual resolution characteristics in the embodiment of the present application; Figure 7 This is a schematic diagram of obtaining concentration ratio time series data in an embodiment of the present application; Figure 8 A diagram showing the steps for obtaining visual feature distribution data in an embodiment of the present application; Figure 9 This is a step diagram of flow state analysis in an embodiment of the present application; Figure 10a Schematic diagram of the target detection area in the sample analysis image in the embodiment of the present application; Figure 10b This is a schematic diagram of concentration ratio time series data before flow error correction in an embodiment of the present application; Figure 10c This is a schematic diagram of the concentration ratio time series data in the embodiment of the present application; Figure 10d This is a schematic diagram of the relationship between the average residence time and the screw speed in the embodiment of the present application; Figure 10e This is a schematic diagram of the residence time accumulation data in the embodiment of the present application; Figure 10f This is a schematic diagram of the accumulated data of the residence time after the dimensionless definition in the embodiment of the present application; Figure 11 A module diagram of a device for detecting the residence time distribution of particulate material provided in an embodiment of the present application; Figure 12 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, 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. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0020] In the pharmaceutical industry, traditional batch granulation processes typically involve separate material preparation and independent production for each batch. This approach often leads to significant differences between batches, limiting product consistency and stability. To address this issue, the pharmaceutical industry is gradually shifting from batch granulation to continuous granulation. By operating continuously on a single production line, this effectively reduces downtime between batches and the resulting material waste, improving production efficiency while ensuring product uniformity and consistency through real-time, precise process control, significantly enhancing product quality.

[0021] Continuous granulation processes include twin-screw continuous wet granulation and other technologies. Due to its advantages such as high efficiency and controllability, twin-screw continuous wet granulation has become an important technical means in the pharmaceutical field to improve granulation efficiency and product quality. In twin-screw continuous wet granulation, residence time distribution is a key parameter used to characterize material transport and mixing behavior. It is of great significance for evaluating uniformity and stability during the granulation process and is also an important parameter for optimizing process parameters and formulating control strategies.

[0022] Related methods for measuring residence time distribution include HPLC, fluorescence tracing, and positron emission particle tracing. HPLC requires complex sample pretreatment, making real-time online detection difficult for continuous granulation processes. Fluorescence tracing and positron emission particle tracing require specialized optical detection equipment, resulting in complex and costly testing. Furthermore, the tracers used may photodegrade, affecting the accuracy of test results.

[0023] Based on the above problems, the present application provides a residence time distribution detection method, device, equipment and medium for particulate material, including: when the granulation process reaches a preset state, adding a tracer to the particulate material to obtain a granulation sample containing the tracer; continuously collecting the granulation sample using a sample collection container until the visual resolution characteristics of the granulation samples vertically stacked in the sample collection container meet the preset visual feature requirements, thereby obtaining a collected sample; performing image acquisition on the collected sample to obtain a sample analysis image; performing residence time distribution analysis on the particulate material based on the visual feature distribution data of the sample analysis image to obtain an initial detection result of the particulate material; performing flow error correction on the initial detection result based on the actual flow rate of the particulate material during the granulation process to obtain a residence time distribution detection result of the particulate material.

[0024] The residence time distribution detection method of particulate materials provided in the present application utilizes a sample collection container to continuously collect granulation samples containing a tracer, so that the granulation samples can be vertically stacked in the sample collection container to obtain a collected sample, thereby being able to reflect the residence time distribution of the particulate material in the granulation process by the distribution of the visual resolution characteristics of the collected sample in the vertical direction, and on the basis of obtaining the initial detection results, the flow error of the initial detection results is corrected according to the actual flow rate of the granulation process, thereby obtaining the residence time distribution detection result of the particulate material.

[0025] Compared with related technologies, on the one hand, the present application obtains collected samples based on granulation samples vertically accumulated in the sample collection container, achieving continuous sampling of granulation samples, effectively improving the data accuracy and resolution of sampling, and thus improving the accuracy of residence time distribution detection results. On the other hand, the present application collects granulation samples after the granulation process is completed, rather than sampling the material in the reactor during the granulation process, reducing the impact of the sampling step on the granulation process, ensuring the stability of the granulation process, and indirectly improving the accuracy of the residence time distribution detection results.

[0026] In addition, this application also takes into account the impact of the flow error of the granulation process on the residence time distribution detection, and corrects the flow error of the initial detection result based on the actual flow of the granulation process to obtain the residence time distribution detection result, further improving the accuracy of the residence time distribution detection result.

[0027] The method for measuring the residence time distribution of granular materials provided in this specification can be applied to measuring the residence time distribution of continuous solid granulation processes, which may include granulation technologies such as twin-screw continuous wet granulation. It is understood that, after adaptive modification, this application can also be used to measure the residence time distribution of other granulation technologies, providing a parameter basis for process parameter optimization and control strategy formulation.

[0028] According to an embodiment of the present application, an embodiment of a method for detecting the residence time distribution of a particulate material is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] In this embodiment, a method for detecting the residence time distribution of a granular material is provided, which can be used to detect the residence time distribution of the above-mentioned continuous solid granulation process. Figure 1 As shown, the method includes: S100. When the granulation process of the granular material reaches a preset granulation state, a tracer is added to the granular material to obtain a granulation sample containing the tracer; wherein the tracer and the granular material have different visual discrimination characteristics.

[0030] S200. Continuously collect granulated samples using a sample collection container until the visual resolution characteristics of the granulated samples vertically stacked in the sample collection container meet preset visual characteristic requirements, thereby obtaining collected samples; wherein, the height of the sample collection container is greater than the cross-sectional size, and the cross-sectional size of the sample collection container is determined according to the flow rate of the granulated sample.

[0031] S300. Perform image acquisition on the collected samples to obtain sample analysis images; perform residence time distribution analysis on the particulate material based on the visual feature distribution data of the sample analysis images to obtain initial detection results of the particulate material.

[0032] S400. Perform flow error correction on the initial detection result according to the actual flow rate of the granular material during the granulation process to obtain a residence time distribution detection result of the granular material.

[0033] The preset granulation state can be a stable granulation state in which fluctuations in process parameters or product quality during the granulation process are within a preset range. When the granulation process reaches the preset granulation state, the granular material has relatively consistent material properties and flow in the reactor. The material properties include but are not limited to the particle size, morphology, strength, and fluidity of the granular material, and the product obtained based on the granulation process has relatively consistent product quality. To illustrate the preset granulation state, in the twin-screw continuous wet granulation technology, a twin-screw extruder is usually used for granulation processing. The corresponding preset granulation state can be a state in which the torque value of the twin-screw extruder remains constant. At this time, the movement fluctuations of the granular material in the twin-screw extruder, the load fluctuations on the screw, and the fluctuations in the quality of the final product are all within the preset range.

[0034] The preset visual feature requirement can be that the fluctuation of the visual distinguishing feature of the granulated sample within a fixed time window is within a preset range. At this time, the visual distinguishing feature of the granulated sample obtained based on the granulation process remains consistent, indicating that the change in the visual distinguishing feature of the granulated material caused by the tracer has returned to the state without the addition of the tracer. It is understandable that when the preset visual feature requirement is met, the collected samples present the complete process of the change in the visual distinguishing feature of the granulated material caused by the tracer over time. To illustrate the preset visual feature requirement, for a granular material with a white color, melanin can be selected as a tracer, and the corresponding visual distinguishing feature can be the lightness value of the granulated sample. The preset visual feature requirement can be that the standard deviation of the lightness value of the granulated sample within the fixed time window is within a preset range, that is, at this time, the lightness value of the granulated sample is determined only by the granular material and is not affected by the tracer.

[0035] Specifically, the granular material is used for continuous solid granulation, and the product obtained by the granulation process is also a solid granule. For example, in the case where the continuous granulation process is a twin-screw continuous wet granulation technology, the reactor for the granulation process can be a twin-screw extruder, and its structure can refer to Figure 2 As shown, the twin-screw extruder has two screws running through the entire structure, and various processing methods can be achieved through the coordinated rotation of the two screws. Figure 2 The pellets move from right to left within the twin-screw extruder. The extruder is divided into several zones, depending on the pelletizing process: the feed zone, the liquid inlet zone, the conveying zone, the mixing zone, and the dispersion zone. A feed port is located above the feed zone to receive pellets from the feeder. A liquid inlet is also located above the liquid inlet zone for the peristaltic pump to pump in the binder. After processing, the pellets are transformed into the desired product and discharged from the twin-screw extruder.

[0036] Furthermore, as the granulation process progresses, fluctuations in process parameters or product quality gradually converge within a preset range, indicating that the granulation process has reached the preset granulation state and that residence time distribution testing can be performed. Based on the visual resolution characteristics of the granular material, a tracer with different visual resolution characteristics from the granular material is selected to ensure that the tracer can be clearly distinguished from the granular material. The tracer is added to the granular material in the reactor so that the tracer and granular material are evenly mixed. After processing in the reactor, a granulation sample containing the tracer is obtained.

[0037] Furthermore, a sample collection container is provided at the discharge port of the reactor for collecting the granulated sample. The sample collection container can be a cylindrical container with an opening at the top, whose height is greater than its cross-sectional dimensions. The cross-sectional dimensions of the sample collection container are determined based on the flow rate of the granulated sample. When the granulated sample flow rate is high, the cross-sectional dimensions can be appropriately increased to slow the vertical accumulation rate of the granulated sample; correspondingly, when the granulated sample flow rate is low, the cross-sectional dimensions can be appropriately decreased to reduce the degree of horizontal accumulation of the granulated sample. Determining the cross-sectional dimensions of the sample collection container based on this method can effectively improve the ability of the collected sample to display changes in the tracer concentration in the vertical direction, thereby improving the quality of the visual feature distribution data. The granulated sample continuously falls into the sample collection container from the discharge port under the action of gravity and accumulates evenly in the vertical direction of the sample collection container. It can be understood that because the collection process is carried out simultaneously with the granulation process, the tracer concentration in the granulated sample gradually decreases over time, causing the visual resolution characteristics of the granulated sample to gradually change. Therefore, the visual distinguishing characteristics of granulated samples near the bottom of the sample collection container are more significantly affected by the tracer, while those near the top of the sample collection container are less affected by the tracer. Furthermore, because the sample collection container collects granulated samples after the granulation process is complete within the reactor, rather than requiring sampling within the reactor during the granulation process, this reduces interference with the material balance within the reactor, ensures the stability of the granulation process, and indirectly improves the accuracy of residence time distribution test results.

[0038] When the visual distinguishing characteristics of the granulated samples vertically stacked in the sample collection container reach the preset visual distinguishing characteristics requirements, the visual distinguishing characteristics of the granulated samples are no longer affected by the tracer, that is, the tracer has been completely discharged from the reactor, and the collection of the granulated samples is stopped at this time to obtain the collected samples. Figure 2 As shown, an industrial camera can be set around the sample collection container to photograph the granulation sample vertically stacked in the sample collection container. If the standard deviation of the brightness value of the granulation sample is within a preset range within a fixed time window, it means that the brightness value of the granulation sample is only determined by the granular material and is not affected by the tracer, and the collection of the granulation sample can be stopped.

[0039] Furthermore, an image of the collected sample is captured to produce a sample analysis image. The sample analysis image includes the sample collection container and all granulated samples stacked vertically therein. As can be appreciated, because the granulated samples are densely packed within the sample collection container and the distances between them are uniform, the image background in the sample analysis image effectively suppresses interference with the visual resolution features of the collected samples, thereby improving the accuracy of the visual feature distribution data.

[0040] Visual feature distribution data can be obtained based on the sample analysis image, which can be used to perform residence time distribution analysis on the granular material and obtain an initial detection result representing the residence time distribution of the granular material in the reactor. It should be noted that the visual feature distribution data can be the distribution of the visual resolution features of the collected sample along the vertical direction. Since the granulated sample is vertically accumulated in the sample collection container and is continuously and evenly distributed in the vertical direction of the sample collection container, the visual feature distribution data obtained can represent the continuous change of the tracer concentration in the granulated sample over time. Compared with the discrete sampling method in the related art, the sample data volume is significantly increased, the sampling error is effectively reduced, and the accuracy of the residence time distribution detection result is improved.

[0041] In actual applications, the reactor may experience flow fluctuations, resulting in unstable flow velocity of the particulate material in the reactor. Even when the granulation process of the particulate material reaches the preset granulation state, the flow fluctuations of the reactor itself will affect the output rate of the reactor for the granulation sample. In this embodiment, due to the continuous collection of granulation samples, the collection process can capture slight changes in the residence time of the particulate material in the reactor, so that the error caused by the flow fluctuation of the reactor on the residence time distribution test result is amplified, thereby reducing the accuracy of the test result. Taking the above reasons into account, in this embodiment, the actual flow rate of the particulate material during the granulation process is obtained, so as to determine the flow deviation in the granulation process, which is used to perform flow error correction on the initial test result and obtain the residence time distribution test result of the particulate material, thereby reducing the impact of flow fluctuations on the test result and further improving the accuracy of the test result.

[0042] The residence time distribution detection method of a particulate material provided in this embodiment utilizes a sample collection container to continuously collect a granulation sample containing a tracer, so that the granulation sample can be vertically stacked in the sample collection container to obtain a collected sample, thereby being able to reflect the residence time distribution of the particulate material during the granulation process by the distribution of the visual resolution characteristics of the collected sample in the vertical direction. On the basis of obtaining the initial detection result, the initial detection result is corrected for flow error according to the actual flow rate of the granulation process, thereby obtaining a residence time distribution detection result of the particulate material.

[0043] Compared with related technologies, on the one hand, the present application obtains collected samples based on granulation samples vertically accumulated in the sample collection container, achieving continuous sampling of granulation samples, effectively improving the data accuracy and resolution of sampling, and thus improving the accuracy of residence time distribution detection results. On the other hand, the present application collects granulation samples after the granulation process is completed, rather than sampling the material in the reactor during the granulation process, reducing the impact of the sampling step on the granulation process, ensuring the stability of the granulation process, and indirectly improving the accuracy of the residence time distribution detection results.

[0044] In addition, this application also takes into account the impact of the flow error of the granulation process on the residence time distribution detection, and corrects the flow error of the initial detection result based on the actual flow of the granulation process to obtain the residence time distribution detection result, further improving the accuracy of the residence time distribution detection result.

[0045] Reference Figure 3 As shown, as an embodiment of the present application, the initial detection result is corrected for flow error according to the actual flow rate of the granular material during the granulation process to obtain the residence time distribution detection result of the granular material, including: S410. Perform error analysis based on the average flow rate and the actual flow rate of the granulation process to obtain the flow rate deviation of the granular material; wherein the time point corresponding to the flow rate deviation is recorded as the target time point.

[0046] S420. Perform data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data.

[0047] S430. Construct a residence time distribution detection result based on the correction data and the residence time data of other time points except the target time point in the initial detection result.

[0048] Specifically, the flow rate is calculated based on the total duration of the granulation process and the total amount of output granular material to obtain the average flow rate of the granulation process. The total duration of the granulation process can be determined based on the total duration of the collection process. The starting time can be the time when the sample collection container starts to collect the granulated sample, and the ending time can be the time when it is determined that the visual resolution characteristics of the granulated sample vertically stacked in the sample collection container meet the preset visual characteristics requirements. The total amount of granular material can be determined based on the mass of the collected sample, referring to Figure 2 As shown, a mass measuring device, such as a scale, can be placed below the sample collection container to measure the mass of the granulated sample accumulated in the sample collection container. Similarly, the actual flow rate of the granulation process can be measured during the collection process according to a preset flow detection period. The mass of the granulated sample in the sample collection container is measured and recorded based on the preset flow detection period to obtain the flow rate of the granulated sample over time.

[0049] Reference Figure 4 As shown in the figure, the real-time particle flow rate is the actual flow rate of the granulation process, and the average particle flow rate is the average flow rate of the granulation process. An error analysis is performed based on the average flow rate and the actual flow rate, and the flow deviation of the granular material is obtained based on the deviation between the two. It should be noted that the flow deviation can be a series of values corresponding to multiple time points, that is, there is a flow deviation only at some time points in the granulation process, and there is no flow error at time points other than the above-mentioned some time points. The time point corresponding to the flow deviation is recorded as the target time point, and the residence time data of the target time point in the initial detection result is corrected according to the flow deviation at the target time point to obtain the corrected data corresponding to the target time point.

[0050] It is understood that for time points other than the target time point where there is no flow rate deviation, the corresponding residence time data does not require data correction. Therefore, time series data is constructed based on the correction data and the residence time data for time points other than the target time point in the initial test results to obtain the residence time distribution test results of the granular material. Compared with related technologies, this embodiment corrects the initial test results for flow rate errors based on the flow rate deviation of the granulation process, thereby reducing the impact of flow rate fluctuations on the test results and further improving the accuracy of the test results.

[0051] As an embodiment of the present application, data correction is performed on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data, including: S422. When the flow deviation is positive, the residence time data at the target time point is corrected in advance according to the correction proportional coefficient and the flow deviation to obtain corrected data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

[0052] Specifically, when flow deviation occurs during the granulation process, the vertical accumulation velocity of the granulated sample in the sample collection container changes due to the flow deviation, causing a deviation in the vertical accumulation height of the granulated sample within the same timeframe, which in turn leads to a mismatch between the initial test results and the time point. Therefore, by performing a time-series correction on the initial test results, the impact of flow deviation on the test results can be effectively reduced.

[0053] Furthermore, a positive flow deviation indicates that the actual flow rate is greater than the average flow rate, that is, the flow velocity of the granular material is greater than the average flow velocity of the granulation process. At this time, the residence time of the granular material in the reactor is shorter, and correspondingly, the tracer concentration in the granulation sample changes faster. Therefore, it is necessary to perform a timing advance correction on the residence time data at the target time point to reflect the faster flow velocity of the granular material. Exemplarily, the method of timing advance correction can be to shift the residence time data at the target time point forward along the time axis according to the correction proportional coefficient and the flow deviation to obtain a correction time point, and the data at the correction time point is used as the correction data. The correction time point can be obtained by the following formula: T′ i =T i -k t *ΔQ i Among them, T′ i Indicates the calibration time point; T i is the target time point; k t is the correction proportional coefficient; ΔQ i is the flow deviation.

[0054] It should be noted that the correction proportional coefficient is obtained based on preliminary experiments. In the preliminary experiments, the correction proportional coefficient is used as an undetermined coefficient, and experimental data is collected from granulation samples based on known flow rates to obtain experimental data. Based on the experimental data, the correction proportional coefficient is solved using the undetermined coefficient method to obtain the correction proportional coefficient. It is understood that the correction proportional coefficient is related to the cross-sectional dimensions of the sample collection container. The larger the cross-sectional dimensions of the sample collection container, the less the flow deviation during the granulation process interferes with the vertical stacking of the granulated sample, and the smaller the correction proportional coefficient. Conversely, the smaller the cross-sectional dimensions of the sample collection container, the greater the flow deviation during the granulation process interferes with the vertical stacking of the granulated sample, and the larger the correction proportional coefficient.

[0055] As an embodiment of the present application, data correction is performed on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data, including: S424. When the flow deviation is negative, the residence time data at the target time point is subjected to a timing delay correction based on the correction proportional coefficient and the flow deviation to obtain corrected data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

[0056] Specifically, a negative flow deviation indicates that the actual flow rate is less than the average flow rate, that is, the flow rate of the granular material is less than the average flow rate during the granulation process. In this case, the granular material resides in the reactor for a longer time, and accordingly, the tracer concentration in the granulated sample changes more slowly. Therefore, it is necessary to perform a timing delay correction on the residence time data at the target time point to reflect the slower flow rate of the granular material. Exemplarily, the timing delay correction method can be to shift the residence time data at the target time point backward along the time axis based on the correction scale factor and the flow deviation to obtain a correction time point. The data at the correction time point is used as the correction data. The correction time point can also be obtained using the previous formula.

[0057] It should be noted that the correction proportional coefficient is obtained based on preliminary experiments. In the preliminary experiments, the correction proportional coefficient is used as an undetermined coefficient, and experimental data is collected from granulation samples based on known flow rates to obtain experimental data. Based on the experimental data, the correction proportional coefficient is solved using the undetermined coefficient method to obtain the correction proportional coefficient. It is understood that the correction proportional coefficient is related to the cross-sectional dimensions of the sample collection container. The larger the cross-sectional dimensions of the sample collection container, the less the flow deviation during the granulation process interferes with the vertical stacking of the granulated sample, and the smaller the correction proportional coefficient. Conversely, the smaller the cross-sectional dimensions of the sample collection container, the greater the flow deviation during the granulation process interferes with the vertical stacking of the granulated sample, and the larger the correction proportional coefficient.

[0058] Reference Figure 5 As shown, as an embodiment of the present application, the residence time distribution analysis of the particulate material is performed based on the visual feature distribution data of the sample analysis image to obtain the initial detection results of the particulate material, including: S310. Calibrate the tracer concentration based on the visual feature distribution data to obtain tracer concentration change time series data; perform proportional conversion based on the concentration change time series data and the total tracer concentration to obtain tracer concentration ratio time series data.

[0059] S320. Perform cumulative calculation based on the concentration ratio time series data to obtain cumulative data on the residence time of the granular material during the granulation process.

[0060] S330. Obtain the initial detection results of the particulate material based on the concentration ratio time series data and the residence time cumulative data.

[0061] Specifically, the visual feature distribution data can be the distribution of the visual distinguishing features of the collected samples along the vertical direction, indicating the continuous change of the tracer concentration in the granulated sample over time. The numerical relationship between the visual distinguishing features and the tracer concentration can be determined by using a granulated sample containing a known tracer concentration. For example, for white granular materials, the tracer can be melanin, and the visual distinguishing feature can be the lightness value of the granulated sample. Figure 6aAs shown, a plurality of granulation samples containing known melanin concentrations were obtained, wherein the mass fractions of melanin were 0.25%, 0.50%, 0.75%, 1.00%, 1.25%, 1.50%, 1.75% and 2.00%, respectively. The above granulation samples were imaged and analyzed, and the brightness values corresponding to the different granulation samples were determined. Data fitting was performed based on the above data to obtain the numerical relationship between the brightness value and the melanin concentration. Figure 6b As shown, based on Figure 6a The numerical relationship obtained for the multiple granulation samples shown can be expressed by the following formula: y=-10.431x+86.731 Where x is the melanin concentration and y is the lightness value. A quality assessment of the above equation yielded a correlation coefficient of 0.9845, indicating a strong positive correlation between the two. Based on this numerical relationship and the visual feature distribution data, the tracer concentration can be calibrated to obtain time-series data on tracer concentration changes.

[0062] Further, refer to Figure 7 As shown, the tracer concentration at each time point can be determined based on the concentration change time series data. The tracer concentration is proportionally converted to the total tracer concentration of the added particulate material to obtain the tracer concentration ratio at each time point, thereby obtaining the tracer concentration ratio time series data to reflect the flow and retention status of the particulate material in the reactor. The concentration ratio time series data is in the following form: Where E(t) represents the concentration ratio time series data; C(t) is the tracer concentration, C i t i The tracer concentration at the time instant; n is the total number of time segments.

[0063] Furthermore, cumulative calculations are performed based on the concentration ratio time series data to obtain cumulative residence time data for the granular material during the granulation process, representing the cumulative amount of tracer in the sample collection container over time. The cumulative residence time data can be obtained by integrating the concentration ratio time series data, and together with the concentration ratio time series data, can be used to reflect the flow and residence state of the granular material in the reactor. The cumulative residence time data is in the following format: Where F(t) represents the accumulated data of residence time.

[0064] Reference Figure 8 As shown, as an embodiment of the present application, the visual feature distribution data of the sample analysis image is obtained by the following method: S302. Perform target region selection and grid division on the sample analysis image to obtain a sample image to be processed representing the target detection region in the sample analysis image.

[0065] S304. Convert the sample image to be processed into a target color space, and perform visual feature extraction on the converted sample image to obtain visual feature distribution data; wherein, the target color space is selected according to the type of visual feature distribution data, and the visual feature distribution data characterizes the distribution of the visual resolution features of the collected samples in the vertical direction.

[0066] Specifically, image recognition is performed on the sample analysis image to identify the non-reflective portion of the sample analysis image containing the sample collection container as the target detection area. This target detection area is then gridded to produce a sample image to be processed, representing the target detection area in the sample analysis image. It should be understood that the width of the target detection area remains the same for all sample analysis images. In addition to the sample analysis image, an image of the sample collection container containing the granular material without the addition of a tracer is also used as a reference analysis image to minimize the impact of the granular material's inherent visual resolution characteristics on the visual feature distribution data.

[0067] Furthermore, according to the type of visual feature distribution data, a color space type that can highlight the visual feature distribution data is selected as the target color space, and the sample image to be processed is converted into a color space. For example, when the sample image to be processed is in the RGB color space and the visual resolution feature can be the lightness value of the granulated sample, the visual feature distribution data can be the distribution of the lightness value, and the target color space can be the Lab color space. First, the sample image to be processed is converted from the RGB color space to the XYZ color space, and the conversion formula is as follows: Among them, R, G, and B are channel values of RGB color space; X, Y, and Z are channel values of XYZ color space. Secondly, the sample image to be processed is converted from XYZ color space to Lab color space. The conversion formula is as follows: L * =116f(Y)-16 a * =500[f(X)-f(Y)] b * =200[f(Y)-f(Z)] Among them, f(t) is the nonlinear transformation formula; L * 、a * and b *are the channel values of the Lab color space respectively. It is understandable that, in other embodiments, the target color space can also be other types of color spaces. On this basis, the converted sample image to be processed is subjected to visual feature extraction to obtain visual feature distribution data.

[0068] Reference Figure 9 As shown, as an embodiment of the present application, the residence time distribution detection result includes a residence time distribution curve; the method further includes: S510. Perform statistical parameter extraction based on the residence time distribution detection result to obtain residence time distribution parameters.

[0069] S520. Perform shape analysis based on the residence time distribution curve to obtain the residence time distribution line shape.

[0070] S530. Perform flow state analysis on the granulation process according to the residence time distribution parameter and the residence time distribution line shape to obtain the flow state of the granular material during the granulation process.

[0071] Specifically, statistical parameters are extracted from the residence time distribution test results, and the statistical characteristics of the residence time distribution test results are used as residence time distribution parameters. For example, the residence time distribution parameters may include the mean, variance, and dimensionless variance of the residence time distribution test results. The mean of the residence time distribution test results represents the average residence time, i.e., the time required for 50% of the tracer to exit the reactor after entering the reactor, and is expressed as follows: Among them, t m Represents the average residence time. The variance of the residence time distribution test result represents the degree of dispersion of the residence time distribution, and its form is as follows: Among them, σ 2 Represents the variance of the residence time distribution test results. In order to eliminate the influence of time units on the residence time distribution parameters, a dimensionless residence time constant is defined to replace the time variable in the variance, and its form is as follows: in, Represents the dimensionless variance of the residence time distribution test results.

[0072] Furthermore, shape analysis is performed based on the residence time distribution curve to obtain the residence time distribution line shape. The flow state analysis of the granulation process is performed based on the residence time distribution parameters and the residence time distribution line shape to obtain the flow state of the granular material during the granulation process. For example, for an ideal plug flow reactor, the dimensionless variance For a fully mixed flow ideal reactor, the dimensionless variance like It means that the flow state in the reactor is between plug flow and mixed flow.

[0073] This application also provides an embodiment to describe the actual use scenario of the residence time distribution detection method for granular materials. In this embodiment, the color of the granular material is white, the tracer is the melanin solvent black 5, the visual feature distribution data is the distribution data of the lightness value, and the reactor structure is referenced. Figure 2 shown.

[0074] First, 5 mg of tracer was added to the twin-screw extruder through the feed port. The collection start time was recorded. The pelletized sample containing the tracer was collected in a sample collection container, and the mass of the sample collection container was measured at a sampling frequency of 5 Hz. When the visual resolution characteristics of the pelletized sample vertically stacked in the sample collection container met the preset visual characteristics requirements, the collection was stopped to obtain the collected sample, and the collection end time T1 = 300 s was recorded. In this example, sample collection was performed at different screw speeds: 150 rpm, 200 rpm, and 250 rpm.

[0075] Secondly, the collected samples were imaged to obtain sample analysis images. The sample analysis images at different screw speeds were referenced. Figure 10a As shown. Based on the visual feature distribution data of the sample analysis image, the residence time distribution of the particulate material is analyzed to obtain the initial detection results of the particulate material. The curve diagram of the concentration ratio time series data curve can be referred to Figure 10b shown.

[0076] Next, based on the mass measurement results of the sample collection container, the average flow rate during the granulation process in this embodiment was determined to be 12.84 g / min. For target time points where flow rate deviation existed, flow rate error correction was performed on the initial detection results based on the flow rate deviation, in the following form: T′ i =T i -0.013*(Q i -Q avg ) Among them, Q i is the actual flow rate; Q avg is the average flow rate. The residence time distribution test results of the granular material are obtained from this. The residence time distribution test results after flow error correction can be referred to Figure 10c As shown. Figure 10cIt can be seen that with the increase of screw speed, the peak value of the concentration ratio time series data curve becomes higher, the width becomes narrower, and the overall shift is to the left, indicating that the residence time of the granular material becomes shorter due to extrusion, thereby reducing the range of the residence time distribution.

[0077] Finally, statistical parameter extraction and shape analysis were performed based on the residence time distribution test results to obtain residence time distribution parameters and residence time distribution line shape, thereby analyzing the flow state of the granulation process and determining the flow state of the granular material during the granulation process. The residence time distribution parameters of this embodiment are shown in Table 1.

[0078] Table 1 Residence time distribution parameters at different screw speeds As can be seen from Table 1, as the screw speed increases, the average residence time decreases, and the distribution range of the average residence time also decreases. This phenomenon may be caused by the screw being the main driving force for the flow of particulate material in the reactor. Increasing the screw speed can effectively shorten the residence time.

[0079] Reference Figure 10d As shown in the figure, it can be seen that when the feeding rate of the granular material is constant, the average residence time is negatively correlated with the screw speed, and the average residence time decreases with the increase of the screw speed. When the screw speed increases from 150r / min to 200r / min, the average residence time decreases from 111s to 103s; and when the screw speed increases from 200r / min to 250r / min, the average residence time decreases from 103s to 102s.

[0080] Reference Figure 10e and Figure 10f As shown, the residence time distribution curve obtained in this example lies between plug flow and mixed flow. The higher the screw speed, the closer the residence time distribution curve is to mixed flow. However, the intervals between the residence time distribution curves corresponding to different screw speeds are small, indicating that the screw speed has little effect on the degree of mixing of the particulate material.

[0081] In summary, when other process conditions remain unchanged, appropriately reducing the screw speed can prolong the residence time of the granular material, thereby increasing the mixing degree of the granular material, which is more conducive to the granulation of product particles and improving the uniformity of particles.

[0082] Accordingly, please refer to Figure 11 , an embodiment of the present application provides a device for detecting the residence time distribution of a particulate material, the device comprising: The granular material tracing module 1410 is used to add a tracer to the granular material when the granulation process of the granular material reaches a preset granulation state to obtain a granulation sample containing the tracer; wherein the tracer and the granular material have different visual identification characteristics.

[0083] The granulation sample collection module 1420 is used to continuously collect granulation samples using a sample collection container until the visual resolution characteristics of the granulation samples vertically stacked in the sample collection container meet the preset visual feature requirements, thereby obtaining a collected sample; wherein, the height of the sample collection container is greater than the cross-sectional size, and the cross-sectional size of the sample collection container is determined according to the flow rate of the granulation sample.

[0084] The image acquisition and analysis module 1430 is used to acquire images of the collected samples to obtain sample analysis images; perform residence time distribution analysis on the particulate material based on the visual feature distribution data of the sample analysis images to obtain initial detection results of the particulate material.

[0085] The flow error correction module 1440 is used to perform flow error correction on the initial detection result according to the actual flow rate of the granular material during the granulation process, so as to obtain the residence time distribution detection result of the granular material.

[0086] In some optional embodiments, the flow error correction module 1440 includes: The flow deviation calculation unit is used to perform error analysis based on the average flow and actual flow of the granulation process to obtain the flow deviation of the granular material; wherein the time point corresponding to the flow deviation is recorded as the target time point.

[0087] The data correction unit is used to perform data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data.

[0088] The detection result construction unit is used to construct a residence time distribution detection result based on the correction data and the residence time data of other time points except the target time point in the initial detection result.

[0089] In some optional embodiments, the data correction unit includes: The timing advance correction subunit is used to perform timing advance correction on the residence time data of the target time point according to the correction proportional coefficient and the flow deviation when the flow deviation is positive, so as to obtain correction data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

[0090] In some optional embodiments, the data correction unit includes: The timing delay correction subunit is used to perform timing delay correction on the residence time data of the target time point according to the correction proportional coefficient and the flow deviation when the flow deviation is negative, so as to obtain correction data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

[0091] In some optional embodiments, the image acquisition and analysis module 1430 includes: The tracer concentration ratio conversion unit is used to calibrate the tracer concentration based on the visual feature distribution data to obtain the tracer concentration change time series data; and to perform ratio conversion based on the concentration change time series data and the total concentration of the tracer to obtain the tracer concentration ratio time series data.

[0092] The time series data accumulation calculation unit is used to perform accumulation calculation according to the concentration ratio time series data to obtain the residence time accumulation data of the granular material during the granulation process.

[0093] The initial detection result acquisition unit is used to obtain the initial detection result of the particulate material according to the concentration ratio time series data and the residence time accumulation data.

[0094] In some optional embodiments, the image acquisition and analysis module 1430 includes: The sample image preprocessing unit is used to select the target area and divide the grid into the sample analysis image to obtain the sample image to be processed which represents the target detection area in the sample analysis image.

[0095] The sample image processing unit is used to convert the sample image to be processed into a target color space, and extract visual features of the converted sample image to be processed to obtain visual feature distribution data; wherein, the target color space is selected according to the type of visual feature distribution data, and the visual feature distribution data represents the distribution of the visual resolution features of the collected samples in the vertical direction.

[0096] In some optional embodiments, the device further includes a detection result analysis module, including: The parameter extraction unit is used to extract statistical parameters according to the residence time distribution detection result to obtain the residence time distribution parameters.

[0097] The shape analysis unit is used to perform shape analysis based on the residence time distribution curve to obtain the residence time distribution line shape.

[0098] The flow state analysis unit is used to perform flow state analysis on the granulation process according to the residence time distribution parameter and the residence time distribution line shape, and obtain the flow state of the granular material during the granulation process.

[0099] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0100] The residence time distribution detection device of the particulate material in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0101] See also Figure 12 , Figure 12 1 is a structural diagram of a computer device provided by an embodiment of the present application. As shown in the figure, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 12 A processor 10 is taken as an example.

[0102] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0103] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0104] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0105] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0106] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0107] The embodiments of the present application also provide a computer-readable storage medium. The above-mentioned method according to the embodiment of the present application can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0108] An embodiment of the present application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform a method according to any embodiment of the present application.

[0109] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

[0110] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0111] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing this application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0112] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0113] 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 produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. 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.

[0114] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work 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 1The function specified in one or more boxes.

[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0116] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0117] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0118] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

[0119] Although the embodiments of the present application have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations shall fall within the scope defined by the appended claims.

Claims

1. A method for detecting the residence time distribution of particulate material, characterized in that: The method comprises: When the granulation process of the granular material reaches a preset granulation state, a tracer is added to the granular material to obtain a granulation sample containing the tracer; wherein the tracer and the granular material have different visual distinguishing characteristics; The granulated sample is continuously collected using a sample collection container until the visual distinguishing characteristics of the granulated sample vertically stacked in the sample collection container meet the preset visual characteristic requirements, thereby obtaining a collected sample; wherein the height of the sample collection container is greater than the cross-sectional size, and the cross-sectional size of the sample collection container is determined according to the flow rate of the granulated sample; Performing image acquisition on the collected sample to obtain a sample analysis image; performing residence time distribution analysis on the particulate material based on visual feature distribution data of the sample analysis image to obtain an initial detection result of the particulate material; The initial detection result is corrected for flow error according to the actual flow of the granular material during the granulation process to obtain a residence time distribution detection result of the granular material.

2. The method according to claim 1, characterized in that The flow error correction is performed on the initial detection result according to the actual flow rate of the granular material during the granulation process to obtain the residence time distribution detection result of the granular material, including: Performing an error analysis based on the average flow rate and the actual flow rate of the granulation process to obtain a flow deviation of the granular material; wherein the time point corresponding to the flow deviation is recorded as a target time point; Performing data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data; The residence time distribution detection result is constructed based on the correction data and the residence time data of other time points except the target time point in the initial detection result.

3. The method according to claim 2, characterized in that The step of performing data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data includes: When the flow deviation is positive, the residence time data of the target time point is corrected in advance according to the correction proportional coefficient and the flow deviation to obtain the corrected data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

4. The method according to claim 2, characterized in that The step of performing data correction on the residence time data of the target time point in the initial detection result according to the flow deviation to obtain corrected data includes: When the flow deviation is negative, the residence time data at the target time point is subjected to a timing delay correction based on a correction proportional coefficient and the flow deviation to obtain the corrected data; wherein the correction proportional coefficient is obtained based on preliminary experiments and is related to the cross-sectional size of the sample collection container.

5. The method according to claim 1, characterized in that The performing residence time distribution analysis on the particulate material according to the visual feature distribution data of the sample analysis image to obtain the initial detection result of the particulate material includes: Calibrate the tracer concentration based on the visual feature distribution data to obtain concentration change time series data of the tracer; perform proportional conversion based on the concentration change time series data and the total concentration of the tracer to obtain concentration ratio time series data of the tracer; Performing cumulative calculation based on the concentration ratio time series data to obtain cumulative residence time data of the particulate material during the granulation process; An initial detection result of the particulate material is obtained based on the concentration ratio time series data and the residence time accumulation data.

6. The method according to claim 1, characterized in that The visual feature distribution data of the sample analysis image is obtained by: Performing target region selection and grid division on the sample analysis image to obtain a sample image to be processed representing the target detection region in the sample analysis image; The sample image to be processed is converted into a target color space, and visual features are extracted from the converted sample image to obtain the visual feature distribution data; wherein the target color space is selected according to the type of the visual feature distribution data, and the visual feature distribution data represents the distribution of the visual resolution features of the collected samples in the vertical direction.

7. The method according to any one of claims 1 to 6, characterized in that The residence time distribution detection result includes a residence time distribution curve; the method further includes: Extracting statistical parameters based on the residence time distribution detection results to obtain residence time distribution parameters; Performing shape analysis on the residence time distribution curve to obtain a residence time distribution line shape; The flow state of the granulation process is analyzed according to the residence time distribution parameter and the residence time distribution line shape to obtain the flow state of the granular material in the granulation process.

8. A device for detecting the residence time distribution of particulate material, characterized in that: The device comprises: a granular material tracing module, configured to add a tracer to the granular material when the granulation process of the granular material reaches a preset granulation state, thereby obtaining a granulation sample containing the tracer; wherein the tracer and the granular material have different visual distinguishing characteristics; a granulation sample collection module, configured to continuously collect the granulation sample using a sample collection container until the visual discrimination characteristics of the granulation sample vertically stacked in the sample collection container meet preset visual characteristic requirements, thereby obtaining a collected sample; wherein the height of the sample collection container is greater than the cross-sectional dimension, and the cross-sectional dimension of the sample collection container is determined according to the flow rate of the granulation sample; An image acquisition and analysis module is used to acquire images of the collected samples to obtain sample analysis images; perform residence time distribution analysis on the particulate material based on visual feature distribution data of the sample analysis images to obtain initial detection results of the particulate material; The flow error correction module is used to perform flow error correction on the initial detection result according to the actual flow of the granular material during the granulation process to obtain a residence time distribution detection result of the granular material.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images