Real-time monitoring method and system for granular medicine processing process

Abstract

The invention relates to the technical field of real-time monitoring, in particular to a real-time monitoring method and system for a particle medicine processing process, and the method comprises the following steps: setting a fixed time interval based on photoacoustic signal data in the particle medicine processing process, capturing photoacoustic signals of a particle medicine under the conditions of thermotropic photoacoustic excitation and pressure-induced photoacoustic excitation, and determining the photoacoustic signals of the particle medicine according to the photoacoustic signals; and recording the amplitude of the photoacoustic signal to obtain a photoacoustic signal feature data set. According to the method, continuous monitoring of the particle medicine forming process is achieved through photoacoustic signal capturing at a fixed time interval, and thermal-induced and pressure-induced photoacoustic excitation is combined, so that the signal collection coverage degree is improved, the photoacoustic holographic image contrast ratio is adjusted, the trace component recognition precision is improved, the peak offset rate is analyzed, and noise baseline fluctuation is compared; abnormal time points are accurately screened, the accuracy of interface change detection is improved, particle trajectory data are obtained in combination with high-frame-rate imaging, flow field disturbance distribution is analyzed, accurate control over the machining process is achieved, and stable particle quality is ensured.

Description

Technical Field

[0001] The present invention relates to the field of real-time monitoring technology, and in particular to a real-time monitoring method and system for a granular medicine processing process. Background Art

[0002] The field of real-time monitoring technology includes a technical system for real-time data collection, analysis and feedback of various processes or states such as physics, chemistry, and biology. Its core content includes sensor data acquisition, signal transmission and analysis, computer data processing, and feedback control. This technical field is widely used in industrial manufacturing, environmental monitoring, medical diagnosis and other fields. Through high-precision and fast-response data collection methods, continuous tracking and analysis of the target process can be achieved. In the process of granular drug processing, real-time monitoring can accurately obtain dynamic data on particle formation, growth and distribution status, provide data support for optimizing process parameters, and ensure the consistency and stability of processing quality.

[0003] Among them, the real-time monitoring method of the granular drug processing process refers to a technical method that uses specific technical means to collect and analyze real-time data on the formation, change and distribution status of particles during the production of granular drugs. The patent subject covers specific technical matters such as particle size detection based on optical measurement, particle charge state monitoring based on charge induction, and component detection based on online spectral analysis. It obtains particle state information by combining non-contact sensors and uses computer data processing to analyze particle physical parameters to achieve real-time monitoring and data collection of the granular drug processing process.

[0004] The existing technology has a relatively simple way to obtain the physical state of granular drugs during real-time monitoring, relying on optical measurement, charge state monitoring or spectral analysis, which makes it difficult to fully present the characteristics of granular drugs in complex environments, especially for trace components. The recognition accuracy is limited, and it is difficult to achieve high-resolution component analysis. The traditional method is mainly based on a single sensor or non-multidimensional data fusion for real-time acquisition. It is difficult to effectively distinguish the response characteristics of particles under different excitation conditions, resulting in local loss or low sensitivity of particle state information. The existing monitoring method has a low time resolution for particle interface changes. It is difficult to accurately capture the dynamic changes of the interface during rapid changes, resulting in the loss of some key data, affecting the precise adjustment of the processing process. The analysis of flow field disturbances relies on indirect speculation of particle states rather than direct measurement, resulting in limited accuracy in obtaining particle motion trajectories and unable to accurately reflect the movement trend of particles in the flow field. Since the evaluation of processing state deviations mainly relies on a single monitoring variable, it fails to fully consider the combined effects of multiple factors such as particle interface changes and flow field disturbances, resulting in a slow response speed for granular drug processing control, which is difficult to meet the needs of high-precision manufacturing. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a real-time monitoring method and system for the granular drug processing process.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a real-time monitoring method for a granular drug processing process, comprising the following steps: S1: Based on the photoacoustic signal data during the processing of granular drugs, a fixed time interval is set to capture the photoacoustic signals of granular drugs under the conditions of thermal photoacoustic excitation and pressure photoacoustic excitation, and the amplitude of the photoacoustic signal is recorded to obtain the photoacoustic signal feature data set; S2: Based on the photoacoustic signal feature data set, the photoacoustic signal amplitude is called, the contrast of the photoacoustic holographic image is adjusted, the spatial distribution information of the target component is extracted, and the micro-component identification data of the granular medicine is obtained; S3: Based on the micro-component identification data of the granular drug, extract the fluorescence spectrum data, record the fluorescence peak wavelength, analyze the fluorescence peak shift rate per unit time, screen the time point when the fluorescence peak drift rate exceeds the noise baseline fluctuation range, and obtain the granular drug interface change data; S4: Based on the particle-drug interface change data, a high frame rate optical imaging device is used to record particle trajectory data, identify the deviation angle of the particle movement direction, determine the spatial distribution of the flow field disturbance, and obtain a particle drug processing flow field disturbance data set; S5: Based on the particle drug processing flow field disturbance data set, the particle drug interface change data is called, the particle drug processing state deviation rate is analyzed, and the drug processing real-time monitoring result is obtained.

[0007] As a further scheme of the present invention, the photoacoustic signal feature data set includes thermal photoacoustic signals, pressure-induced photoacoustic signals, and photoacoustic signal amplitudes; the granular drug trace component identification data includes target component signal gain coefficient, photoacoustic holographic image contrast, and target component spatial distribution information; the granular drug interface change data includes fluorescence spectrum data, fluorescence peak wavelength, and fluorescence peak offset rate; the granular drug processing flow field disturbance data set includes particle trajectory data, particle movement direction offset angle, and flow field disturbance spatial distribution; the drug processing real-time monitoring results include granular drug interface change data, granular drug processing state deviation rate, and granular drug processing flow field disturbance data set.

[0008] As a further solution of the present invention, the step of acquiring the photoacoustic signal feature data set is specifically: S111: Based on the photoacoustic signal data during the processing of the granular medicine, a fixed time interval is set, the photoacoustic signal amplitude at each time point is detected, the data is recorded, and a photoacoustic signal amplitude sequence is obtained; S112: Based on the photoacoustic signal amplitude sequence, the amplitude change rate of adjacent time points is identified using the formula: ; Calculate the photoacoustic signal change rate at each time interval and establish a photoacoustic signal change rate sequence; in, represents the rate of change of photoacoustic signal, and represents the photoacoustic signal amplitude at adjacent time points, represents a time interval; S113: calling the photoacoustic signal change rate sequence, screening the time points where the change rate exceeds the threshold, extracting the corresponding photoacoustic signal amplitude, and obtaining a photoacoustic signal feature data set.

[0009] As a further solution of the present invention, the steps for obtaining the identification data of trace components of the granular medicine are specifically as follows: S211: Based on the photoacoustic signal feature data set, calling the photoacoustic signal amplitude, calculating the initial gain coefficient of the target component signal, and performing normalization processing to obtain a normalized gain coefficient; S212: Based on the normalized gain coefficient, by adjusting the contrast parameter of the differential area of ​​the photoacoustic holographic image, the formula is used: ; Calculate the contrast optimization parameters; in, Optimize the parameters for contrast, For the The normalized gain coefficient of pixels, For the The photoacoustic signal intensity of each pixel is is the average normalized gain coefficient of the pixel points, is the total number of pixels; S213: Based on the contrast optimization parameters, the pixel distribution of the photoacoustic holographic image is adjusted to extract the spatial distribution information of the target component to obtain the micro-component identification data of the granular medicine.

[0010] As a further solution of the present invention, the step of acquiring the particle drug interface change data is specifically as follows: S311: extracting fluorescence spectrum data based on the micro-component identification data of the granular medicine, analyzing the fluorescence intensity of each wavelength, determining the peak position of the spectrum, recording the peak wavelength, calculating the wavelength change per unit time, and obtaining the fluorescence peak shift rate; S312: Call the fluorescence peak shift rate, identify the noise baseline fluctuation range, compare the shift rate at each time point with the noise baseline fluctuation range, screen the time points beyond the fluctuation range, evaluate the cumulative change of the shift rate, and use the formula: ; The mean value of fluorescence peak drift deviation was calculated; in, represents the mean value of fluorescence peak drift deviation, Representative The fluorescence peak shift rate at each time point is Represents the mean value of the noise baseline fluctuation range, Represents the total number of time points that are beyond the range of noise baseline fluctuations, Representative The weight coefficient of each time point, Representative The time interval between time points, Represents the total measurement time length; S313: Based on the mean value of the fluorescence peak drift deviation, the time point change trend is counted, the acceleration change of the offset rate is analyzed, and the dynamic change rate of the interface is calculated in combination with the time accumulation to obtain the particle drug interface change data.

[0011] As a further solution of the present invention, the steps for acquiring the particle drug processing flow field disturbance data set are specifically: S411: extracting optical imaging data of particles based on the particle-drug interface change data, using a high frame rate optical imaging device to record trajectory data of particles in a time series, analyzing the motion trajectory vector of the particles, and obtaining particle trajectory data; S412: Call the particle trajectory data, extract the movement direction of the particles at adjacent time points, analyze the angle change trend in the time series, determine the impact of the fluid on the particle movement, adjust the disturbance parameters based on the particle force conditions, identify the offset fluctuation range of the particles in the disturbance area, and use the formula: ; The deviation angle of the particle movement direction is calculated; in, represents the deviation angle of the particle motion direction, , Represents particles at time point and The X-axis coordinate, , represents the corresponding Y-axis coordinate, Represents the vertical displacement of particles under fluid disturbance; S413: calling the particle movement direction offset angle, identifying the spatial distribution of the flow field disturbance area, analyzing the movement trend of the particles in the disturbance area, and obtaining a particle drug processing flow field disturbance data set.

[0012] As a further solution of the present invention, the steps for obtaining the real-time monitoring results of drug processing are specifically: S511: Based on the particle drug processing flow field disturbance data set, call the particle drug interface change data, analyze the particle drug morphology change rate and particle aggregation degree, and obtain the particle morphology change coefficient; S512: Based on the particle morphology variation coefficient, the variation deviation of the particle drug processing state is evaluated, and combined with the particle drug interface variation data, the formula is used: ; Identify the variation deviation of the particle drug processing state at each moment and obtain the particle processing deviation rate; in, represents the particle processing deviation rate, represents the maximum value of the particle morphology variation coefficient, represents the minimum value of the particle morphology variation coefficient, The average change value representing the trend of particle morphology change, represents the fluctuation value of the particle interface change data, represents the particle processing state deviation adjustment factor; S513: Based on the particle processing deviation rate, the real-time changes of the particle drug processing state are analyzed, and combined with the dynamic trend of the processing state deviation, whether the particle drug processing state is stable is monitored to obtain the real-time monitoring result of drug processing.

[0013] The real-time monitoring system for the particle drug processing process is used to implement the real-time monitoring method for the particle drug processing process, and the system comprises: The photoacoustic signal control module controls the photoacoustic excitation power and intensity, synchronizes the photoacoustic signal change amplitude, calculates the photoacoustic signal response time deviation, and obtains the photoacoustic signal stability data based on the photoacoustic signal data during the particle drug processing; The target component gain calculation module calculates the target component signal gain coefficient based on the photoacoustic signal stability data, adjusts the photoacoustic signal amplitude contrast, analyzes the target component signal peak change, compares the difference distribution between the target component signal gain coefficient and the background signal, screens the gain area, analyzes the target component signal enhancement degree, extracts the target component spatial distribution information, and obtains the target component spatial distribution data; The particle interface change tracking module calls the fluorescence spectrum characteristics based on the target component spatial distribution data, calculates the fluorescence peak wavelength shift rate, compares the fluorescence peak wavelength shift rate with the interface stability threshold, screens the fluorescence drift time exceeding the interface stability threshold, and obtains the particle drug interface change data; The flow field disturbance identification module identifies the deviation angle of the particle movement direction based on the particle drug interface change data and the particle trajectory change, compares the consistency of the particle movement direction deviation angle with the fluid movement direction, analyzes the flow field disturbance trend of the particle trajectory, and obtains the particle drug processing flow field disturbance data; The processing deviation monitoring module analyzes the particle movement direction deviation change rate based on the particle drug processing flow field disturbance data, compares the particle movement direction deviation change rate with the flow field stability parameter, calculates the particle drug processing state deviation rate, and obtains the real-time monitoring result of drug processing.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, the photoacoustic signal is captured based on a fixed time interval to ensure the continuous monitoring of the particle drug formation process, and the photoacoustic signal collection coverage of the particle drug is improved by combining the dual conditions of thermal photoacoustic excitation and pressure photoacoustic excitation, so as to achieve a more comprehensive particle state record. The gain coefficient of the target component signal is calculated by using the amplitude of the photoacoustic signal, and the contrast of the photoacoustic holographic image is adjusted to make the spatial distribution information of the target component more intuitive, improve the identification accuracy of trace components, extract fluorescence spectrum data, combine the recording of fluorescence peak wavelength, analyze the fluorescence peak offset rate per unit time, and compare the noise baseline fluctuation range, accurately screen the time point of peak drift abnormality, enhance the sensitivity to the particle drug interface change, and improve the accuracy and stability of detection. Combined with high frame rate optical imaging equipment to obtain particle trajectory data, identify the particle motion direction offset angle, analyze the spatial distribution of flow field disturbance, make the interaction between the particle motion state and the processing environment clearer, and enhance the quantitative analysis ability of flow field disturbance in the particle drug processing process. Through the correlation analysis of the particle drug interface change data and the flow field disturbance data, combined with the calculation of the particle processing state deviation rate, a real-time monitoring system is constructed to achieve precise control of the particle drug processing process, provide efficient data support for optimizing the processing technology, and ensure the quality stability and consistency of the finished particles. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 is a flow chart for obtaining a photoacoustic signal feature data set in the present invention; Figure 3 A flowchart for obtaining identification data of trace components of granular medicines in the present invention; Figure 4 This is a flow chart for obtaining the particle drug interface change data in the present invention; Figure 5 The flowchart of the acquisition of the flow field disturbance data set of the particle drug processing in the present invention; Figure 6 The figure is a flow chart for obtaining the real-time monitoring results of drug processing in the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] Example 1: Please refer to Figure 1 The present invention provides a technical solution: a real-time monitoring method for a granular drug processing process, comprising the following steps: S1: Based on the photoacoustic signal data during the processing of granular drugs, a fixed time interval is set to capture the photoacoustic signals of granular drugs under the conditions of thermal photoacoustic excitation and pressure photoacoustic excitation, and the amplitude of the photoacoustic signal is recorded to obtain the photoacoustic signal feature data set; S2: Based on the photoacoustic signal feature data set, the photoacoustic signal amplitude is called, the gain coefficient of the target component signal is calculated, the contrast of the photoacoustic holographic image is adjusted, the spatial distribution information of the target component is extracted, and the micro-component identification data of the granular drug is obtained; S3: Based on the identification data of trace components of granular drugs, extract fluorescence spectrum data, record the fluorescence peak wavelength, analyze the fluorescence peak shift rate per unit time, compare the fluorescence peak shift rate with the noise baseline fluctuation range, screen the time point when the fluorescence peak drift rate exceeds the noise baseline fluctuation range, and obtain the granular drug interface change data; S4: Based on the particle-drug interface change data, a high-frame-rate optical imaging device is used to record the particle trajectory data, identify the deviation angle of the particle movement direction, determine the spatial distribution of the flow field disturbance, and obtain the particle drug processing flow field disturbance data set; S5: Based on the granular drug processing flow field disturbance data set, the granular drug interface change data is called, the granular drug processing state deviation rate is analyzed, and the real-time monitoring results of drug processing are obtained.

[0019] The photoacoustic signal feature data set includes thermal photoacoustic signals, pressure-induced photoacoustic signals, and photoacoustic signal amplitudes. The granular drug trace component identification data includes the target component signal gain coefficient, photoacoustic holographic image contrast, and target component spatial distribution information. The granular drug interface change data includes fluorescence spectrum data, fluorescence peak wavelength, and fluorescence peak offset rate. The granular drug processing flow field disturbance data set includes particle trajectory data, particle motion direction offset angle, and flow field disturbance spatial distribution. The real-time monitoring results of drug processing include granular drug interface change data, granular drug processing state deviation rate, and granular drug processing flow field disturbance data set.

[0020] See also Figure 2 , the specific steps for obtaining the photoacoustic signal feature data set are: S111: Based on the photoacoustic signal data during the processing of the granular medicine, a fixed time interval is set, the photoacoustic signal amplitude at each time point is detected, the data is recorded, and a photoacoustic signal amplitude sequence is obtained; First, for the photoacoustic signals under thermal photoacoustic excitation and pressure photoacoustic excitation, a fixed time interval is set, and the photoacoustic signal amplitude at each time point is monitored by precise equipment. This process can be applied in the drug manufacturing process to ensure the stability and quality control of drug particles in the production process. For example, during the operation of the compressor, the photoacoustic signals emitted from the particles are recorded by monitoring equipment at regular intervals, and their amplitude changes are analyzed to monitor the changes in the physical state of the particles. This monitoring helps pharmaceutical engineers adjust machine settings to optimize the processing process of drug particles. The final recorded photoacoustic signal amplitude sequence data reflects the photoacoustic response characteristics of drug particles at different time points. The stability of the particles in the manufacturing process and its changing trend can be analyzed from the data. This data set provides key information for pharmaceutical quality control.

[0021] S112: Based on the photoacoustic signal amplitude sequence, the amplitude change rate of adjacent time points is identified using the formula: ; Calculate the photoacoustic signal change rate at each time interval and establish a photoacoustic signal change rate sequence; in, represents the rate of change of photoacoustic signal, and represents the photoacoustic signal amplitude at adjacent time points, represents a time interval; In practical application scenarios, this calculation can be used to monitor the quality of granular drugs in the pharmaceutical process. For example, in granulation, the uniformity of drug particles directly affects the dissolution rate and drug release of the final tablets. It is necessary to monitor the changes in the photoacoustic signals of the particles at different time points in real time to ensure the stability of the processing process. First, on a pharmaceutical production line, the measurement time interval is set to , and at consecutive time points and The photoacoustic signal amplitude of the drug particles is collected, for example, The photoacoustic signal amplitude was measured at ,exist The photoacoustic signal amplitude was measured at ; Substitute the data into the formula to calculate the rate of change of the photoacoustic signal: ; The value is expressed in to The rate of change of the photoacoustic signal amplitude is , it can be seen that the change rate is large, indicating that the particles may have undergone significant physical changes due to changes in ambient temperature or pressure. If the calculated change rate is much larger than the normal fluctuation range of the production process (for example, the normal fluctuation range is ), it means that the physical state of the granular drug has changed suddenly, such as agglomeration or decomposition, and the production parameters need to be adjusted for correction; To ensure data integrity, the photoacoustic signal amplitude change rate at different time points in the entire production process should be continuously calculated, and the change rate sequence should be constructed to set the measurement points. And calculate the rate of change of all adjacent points, for example, Measured at ,but: ; This change rate is within the normal fluctuation range, indicating that the state of drug particles is relatively stable at this stage; The above calculation process ultimately obtains a series of change rate data, namely, the photoacoustic signal change rate sequence, which can be used to analyze the state changes of drug particles at different processing stages and provide a basis for adjusting process parameters.

[0022] S113: calling the photoacoustic signal change rate sequence, screening the time point where the change rate exceeds the threshold, extracting the corresponding photoacoustic signal amplitude, and obtaining the photoacoustic signal feature data set; In practice, it can be applied to automated alarms. For example, in chemical plants, the operating status of key equipment can be monitored by setting thresholds. When the rate of change of the photoacoustic signal suddenly exceeds the preset threshold, the system will automatically trigger an alarm to notify the operator to conduct inspections or maintenance. A reasonable rate of change threshold is set. Based on historical data and the normal operating range of the equipment, the rate of change of the photoacoustic signal is continuously tracked through real-time data monitoring, and the rate of change of each measuring point is continuously compared with the threshold using a data processing algorithm. Once a rate of change exceeding the threshold is detected, the system automatically records the amplitude of the photoacoustic signal at that time point and adds it to the feature data set for subsequent analysis and processing to generate a photoacoustic signal feature data set.

[0023] See also Figure 3 The specific steps for obtaining the identification data of trace components of granular drugs are as follows: S211: based on the photoacoustic signal feature data set, calling the photoacoustic signal amplitude, calculating the initial gain coefficient of the target component signal, and performing normalization processing to obtain a normalized gain coefficient; By comparing the photoacoustic signal amplitudes in different time windows, a preliminary calculation of the gain coefficient can be obtained. For example, in the pharmaceutical process, the trace analysis of drug components is very important. Assuming that the photoacoustic signal amplitude recorded in a specific time window is , the amplitude in the other window is ,pass To estimate, this step can help R&D personnel identify and adjust the proportion of active ingredients in drug formulas to ensure the safety and effectiveness of drugs. To refine the process, it is first necessary to collect photoacoustic signals in a laboratory environment, then analyze the signal differences in different time periods through dedicated software, and further use the computational model to process the data to obtain the normalized gain coefficient. The specific data involved in this process, such as photoacoustic wavelength, sound wave receiving sensitivity, etc., need to be obtained through precise equipment. For example, the photoacoustic wavelength is set in the visible light range, and the sensitivity is adjusted according to the experimental requirements, which will directly affect the subsequent drug quality control steps.

[0024] S212: Based on the normalized gain coefficient, the contrast parameter of the differentiated area of ​​the photoacoustic holographic image is adjusted using the formula: ; Calculate the contrast optimization parameters; in, Optimize the parameters for contrast, For the The normalized gain coefficient of pixels, For the The photoacoustic signal intensity of each pixel is is the average normalized gain coefficient of the pixel points, is the total number of pixels; In determining the normalized gain coefficient for each pixel After that, the contrast of the holographic image needs to be adjusted, which is crucial in biological tissue imaging, material analysis, and drug trace component detection. For example, in the drug analysis process, researchers need to use photoacoustic imaging technology to analyze the distribution of active ingredients in drug particles to ensure the consistency and stability of the preparation. Set up an experimental scenario, in a batch of drug samples, perform pixel-level signal analysis on the holographic image, and the photoacoustic signal intensity of each pixel point All are measured by experimental equipment. For example, the photoacoustic signal intensity of different regions of drug particles is obtained by photoacoustic detection equipment. The measured values ​​of the signal intensity of pixels in some regions are set as follows: ; The corresponding normalized gain coefficient is: ; Calculate the average normalized gain factor: ; Calculate contrast adjustment parameters The first part: ; ; Calculate the second part, the variance term of the gain coefficient: ; ; ; Finally calculate the contrast adjustment parameters: ; The calculation results show that under the experimental conditions, the contrast optimization parameter obtained by weighted calculation of the normalized gain coefficient and the photoacoustic signal intensity is 1.0767, which means that this value can be used to further adjust the contrast of the photoacoustic holographic image to optimize the visualization effect of different components. In practical applications, the adjusted contrast parameter can be used to enhance the spatial distribution of the target components, enabling researchers to more accurately identify the structural information of trace components in drug particles and improve the accuracy of pharmaceutical quality monitoring.

[0025] S213: Based on the contrast optimization parameters, the pixel distribution of the photoacoustic holographic image is adjusted to extract the spatial distribution information of the target component and obtain the identification data of the trace components of the granular medicine; After adjusting the contrast of the holographic image, the spatial distribution information of the target component is extracted. For example, in materials science research, understanding the microstructure of the material has an important impact on improving the material performance. For example, in the research and development of new alloys, by adjusting the image contrast, scientists can more clearly observe the microstructure distribution inside the alloy, thereby making accurate predictions about the physical properties of the material. Scientists first need to use image processing software to adjust the pixel distribution of the holographic image based on the contrast optimization parameters obtained previously, and then use advanced image analysis technology to extract the spatial structure information of the material. The information will directly reflect the internal composition of the material, and finally obtain the trace component identification data of the granular drug, which not only helps to evaluate the efficacy of the drug, but also ensures the accuracy and reproducibility of the image analysis. By adjusting the contrast, it ensures that every part of the image can be correctly analyzed, thereby obtaining reliable structural information.

[0026] See also Figure 4 , the specific steps for obtaining the particle drug interface change data are: S311: extracting fluorescence spectrum data based on the micro-component identification data of the granular medicine, analyzing the fluorescence intensity of each wavelength, determining the peak position of the spectrum, recording the peak wavelength, calculating the wavelength change per unit time, and obtaining the fluorescence peak shift rate; The fluorescence spectral data of the drug is extracted for subsequent analysis. This process involves the analysis of spectral signals and the precise positioning of spectral peaks. For example, the peak wavelength corresponding to the strongest fluorescence intensity within a certain wavelength range is determined, and then the peak data is recorded. This is particularly important for monitoring the fluorescence changes of drugs. Each change in the fluorescence peak wavelength is accurately measured to calculate the change in the fluorescence peak wavelength per unit time. The statistics of this change are achieved through time series analysis. The time series data is differentially processed to extract rate information, which provides an important indicator for determining the stability of drug ingredients and obtaining the fluorescence peak shift rate.

[0027] S312: Call the fluorescence peak shift rate, identify the noise baseline fluctuation range, compare the shift rate at each time point with the noise baseline fluctuation range, screen the time points beyond the fluctuation range, evaluate the cumulative change of the shift rate, and use the formula: ; The mean value of fluorescence peak drift deviation was calculated; in, represents the mean value of fluorescence peak drift deviation, Representative The fluorescence peak shift rate at each time point is Represents the mean value of the noise baseline fluctuation range, Represents the total number of time points that are beyond the range of noise baseline fluctuations, Representative The weight coefficient of each time point, Representative The time interval between time points, Represents the total measurement time length; By comparing the offset rate at each time point with the preset noise baseline fluctuation range, the time points where the offset rate exceeds the noise baseline range are screened out. For example, during the experiment, the fluctuation range of the fluorescence peak is set to nm, while the fluorescence peak shift rate at some time points reached nm / s, far exceeding the noise baseline, this time point is marked as a key change point. This screening uses the ratio of the offset rate at each time point to the fluctuation range of the noise baseline to calculate. If the ratio is greater than 1, the time point is judged to be a significant offset point. Since the data weights at different time points may be different, a weight coefficient is introduced to correct the influence of different time periods. For example, in the initial decomposition stage of the drug, the change rate is faster, and a higher weight is given to the data at this stage, such as , and in the later period it tends to be stable, then the weight is reduced to , further adjust the error caused by the time interval difference, for example, if a certain time point for , total experimental time for , then the time correction term , and finally calculate the mean value of fluorescence peak drift deviation; Assume that the experiment selects 5 time points that exceed the noise baseline, and the corresponding fluorescence peak shift rates are , , , , (Unit: nm / s), the weight coefficients are set as , , , , The time intervals are , , , , , put it into the formula and calculate as follows: ; Calculate the absolute value of each: ; ; ; The final calculated fluorescence peak drift deviation mean is 0.1677nm / s. This value indicates that under the current experimental conditions, the average drift deviation at the time point beyond the noise baseline is large. Further analysis of the changing trend of this value can evaluate the dynamic changes in the interface of the granular drug and be used for subsequent drug stability judgment.

[0028] S313: Based on the mean value of the fluorescence peak drift deviation, the time point change trend is counted, the acceleration change of the offset rate is analyzed, and the dynamic change rate of the interface is calculated in combination with the time accumulation to obtain the particle drug interface change data; By calculating the increase and decrease relationship of the drift deviation mean in different time periods, the change pattern in the time series can be judged. For example, if the fluorescence peak drift deviation mean gradually increases in the first half of the experiment and decreases in the second half, this indicates that the drug molecules are more active in the early stage of the reaction and then gradually stabilize. This information is extremely critical for understanding the dynamic changes of the drug. By calculating the accumulated data in the time dimension, not only the rate of fluorescence peak drift can be obtained, but also important data on drug stability and reaction rate can be provided, and the particle-drug interface change data can be obtained. The data will eventually be used to evaluate the quality and stability of the drug and provide a scientific basis for monitoring the pharmaceutical process.

[0029] See also Figure 5 , the specific steps for obtaining the flow field disturbance data set of granular drug processing are: S411: based on the particle-drug interface change data, extract the optical imaging data of the particles, use a high frame rate optical imaging device to record the trajectory data of the particles in time series, analyze the motion trajectory vector of the particles, and obtain the particle trajectory data; Under the monitoring of high-frame-rate optical imaging equipment, the movement trajectory of particles can be accurately recorded. The optical equipment continuously collects images at fixed time intervals (such as 0.01 seconds). Each frame of the image contains the position information of the particle in three-dimensional space. The coordinates of each frame of the image are identified, and the spatial coordinates of the particle are extracted. The trajectory of the particle is calculated based on the spatial displacement of the particle between adjacent frames. For example, if the particle is The coordinates at the moment are (2.5, 3.6, 1.2). The coordinates at the moment are (2.8, 3.9, 1.3), then the motion trajectory vector within this time interval can be expressed as (0.3, 0.3, 0.1), and so on. After traversing the entire time series and recording the position information of all time points, the coordinate change is called to calculate the motion trajectory vector of the particle and obtain the particle trajectory data.

[0030] S412: Call the particle trajectory data, extract the movement direction of the particles at adjacent time points, analyze the angle change trend in the time series, determine the impact of the fluid on the particle movement, adjust the disturbance parameters based on the particle force conditions, identify the offset fluctuation range of the particles in the disturbance area, and use the formula: ; The deviation angle of the particle movement direction is calculated; in, represents the deviation angle of the particle motion direction, , Represents particles at time point and The X-axis coordinate, , represents the corresponding Y-axis coordinate, Represents the vertical displacement of particles under fluid disturbance; Analyze each time point in the time series step by step, and calculate the deviation angle of the particles at each time point. If the angle of the particles at multiple time points changes abnormally, it can be judged that it is caused by external disturbance. For example, if the particles It moves along the direction (1, 0, 0) at all times, and When the moment changes to (0.8, 0.6, 0), the offset angle can be calculated using the formula: ; Assume that the particles are The coordinates at the moment are (3.5, 2.2, 1.8). The coordinates at the moment are (3.9, 2.6, 1.85), then substitute the formula to calculate the offset angle: ; ; ; The calculated deviation angle of the particle motion direction is 1.41. If this angle exceeds the flow field disturbance judgment threshold, it indicates that the particle is affected by the disturbance.

[0031] S413: calling the particle movement direction offset angle, identifying the spatial distribution of the flow field disturbance area, analyzing the movement trend of the particles in the disturbance area, and obtaining the particle drug processing flow field disturbance data set; Determine the movement trend of particles in the disturbance area, extract the disturbance center and the impact range based on the offset data of multiple particles in the disturbance area. For example, if multiple particles are arrive If the deviation angle is higher than 1.2 in the range of , it can be judged that there is flow field disturbance in this area. By counting the disturbance characteristics of particles in different time periods, the dynamic change trend of the disturbance area is calculated, and the flow field disturbance data set of particle drug processing is obtained.

[0032] See also Figure 6 , the specific steps for obtaining the real-time monitoring results of drug processing are: S511: Based on the particle drug processing flow field disturbance data set, call the particle drug interface change data, analyze the particle drug morphology change rate and particle aggregation degree, and obtain the particle morphology change coefficient; First, obtain the flow field disturbance data and interface change data of the granular drug during the processing. For example, in the pharmaceutical process, use high-precision sensors and high-speed camera equipment to monitor the movement state of the particles in the mixer or reactor in real time, record their speed, position and shape changes, analyze the data, and calculate the morphological change rate and aggregation degree of the particles. The morphological change rate can be determined by measuring the size change of the particles at different time points. For example, assuming that at the initial moment, the average diameter of the particles is 100 microns, after a period of time, the measurement shows that the average diameter increases to 105 microns, then the morphological change rate is (105-100) / time Interval, the degree of aggregation can be evaluated by calculating the average distance between particles or the number of aggregates. For example, image processing technology is used to identify the number and size of aggregates, and the number and average size of aggregates in a unit volume are counted. The calculation results are normalized to obtain the particle morphology change coefficient, which can be expressed as the ratio of the morphology change rate to the degree of aggregation. For example, assuming that the morphology change rate is 0.05 μm / s and the degree of aggregation is 10 aggregates per cubic millimeter, the particle morphology change coefficient is 0.05 / 10=0.005, which is used to evaluate the stability and consistency of particles during processing.

[0033] S512: Based on the particle morphology variation coefficient, the variation deviation of the particle drug processing state is evaluated, and combined with the particle drug interface variation data, the formula is used: ; Identify the variation deviation of the particle drug processing state at each moment and obtain the particle processing deviation rate; in, represents the particle processing deviation rate, represents the maximum value of the particle morphology variation coefficient, represents the minimum value of the particle morphology variation coefficient, The average change value representing the trend of particle morphology change, Represents the fluctuation value of the particle interface change data, represents the particle processing state deviation adjustment factor; First, determine the maximum and minimum values ​​of the particle morphology variation coefficient. For example, in a batch of production, the maximum coefficient monitored is 0.008 and the minimum coefficient is 0.002. Calculate the average change value and fluctuation value. The average change value can be obtained by averaging all measured morphology variation coefficients. Assuming that 100 measurements are taken and the sum of the coefficients is 0.5, the average change value is 0.5 / 100=0.005. The fluctuation value can be obtained by calculating the standard deviation of the coefficient, assuming that the standard deviation is 0.001. in, represents the particle processing deviation rate, represents the maximum value of the particle morphology variation coefficient (0.008), represents the minimum value of the particle morphology variation coefficient (0.002), The average change value (0.005) representing the trend of particle morphology change, represents the fluctuation value of the particle interface change data (0.001), Represents the particle processing state deviation adjustment factor. The adjustment factor is determined according to the process requirements and historical data. For example, it is set to 1.2 and the value is substituted for calculation: ; The calculated particle processing deviation rate is 1.2, indicating that there is a certain degree of deviation in the processing process, and its impact needs to be evaluated according to the process specifications.

[0034] S513: Based on the particle processing deviation rate, analyze the real-time changes in the particle drug processing state, and monitor whether the particle drug processing state is stable in combination with the dynamic trend of the processing state deviation, and obtain the real-time monitoring results of drug processing; First, continuously obtain data on the particle morphology change coefficient and processing deviation rate during the processing. For example, install online monitoring equipment on the production line, record the particle morphology change coefficient and calculate the corresponding deviation rate once a minute, and compare the real-time data with the preset stability standard. For example, set the acceptance range of the deviation rate to 0.8 to 1.0. If the monitored deviation rate exceeds this range, an alarm is triggered to prompt the operator to check the production parameters and equipment status. Combined with the dynamic trend of the processing status deviation, the stability and consistency of the processing process are judged. For example, if the deviation rate continues to rise, it indicates equipment wear or fluctuations in raw material quality, and timely adjustments are required to ensure product quality.

[0035] The real-time monitoring system for the granular drug processing process is used to implement the real-time monitoring method for the granular drug processing process, and the system includes: The photoacoustic signal control module controls the photoacoustic excitation power and intensity, synchronizes the photoacoustic signal change amplitude, calculates the photoacoustic signal response time deviation, and obtains the photoacoustic signal stability data based on the photoacoustic signal data during the particle drug processing; The target component gain calculation module calculates the target component signal gain coefficient based on the photoacoustic signal stability data, adjusts the photoacoustic signal amplitude contrast, analyzes the target component signal peak change, compares the difference distribution between the target component signal gain coefficient and the background signal, screens the gain area, analyzes the target component signal enhancement degree, extracts the target component spatial distribution information, and obtains the target component spatial distribution data; The particle interface change tracking module calls the fluorescence spectrum characteristics based on the spatial distribution data of the target component, calculates the fluorescence peak wavelength shift rate, compares the fluorescence peak wavelength shift rate with the interface stability threshold, screens the fluorescence drift moment that exceeds the interface stability threshold, and obtains the particle drug interface change data; The flow field disturbance identification module is based on the particle-drug interface change data and the particle trajectory change to identify the particle movement direction offset angle, compare the particle movement direction offset angle with the fluid movement direction consistency, analyze the flow field disturbance trend of the particle trajectory, and obtain the particle drug processing flow field disturbance data; The processing deviation monitoring module is based on the particle drug processing flow field disturbance data, analyzes the particle movement direction deviation change rate, compares the particle movement direction deviation change rate with the flow field stability parameters, calculates the particle drug processing state deviation rate, and obtains real-time monitoring results of drug processing.

[0036] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A real-time monitoring method for a granular drug processing process, characterized in that: The following steps are involved: S1: Based on the photoacoustic signal data during the processing of granular drugs, a fixed time interval is set to capture the photoacoustic signals of granular drugs under the conditions of thermal photoacoustic excitation and pressure photoacoustic excitation, and the amplitude of the photoacoustic signal is recorded to obtain the photoacoustic signal feature data set; S2: Based on the photoacoustic signal feature data set, the photoacoustic signal amplitude is called, the contrast of the photoacoustic holographic image is adjusted, the spatial distribution information of the target component is extracted, and the micro-component identification data of the granular medicine is obtained; S3: Based on the micro-component identification data of the granular drug, extract the fluorescence spectrum data, record the fluorescence peak wavelength, analyze the fluorescence peak shift rate per unit time, screen the time point when the fluorescence peak drift rate exceeds the noise baseline fluctuation range, and obtain the granular drug interface change data; S4: Based on the particle-drug interface change data, a high frame rate optical imaging device is used to record particle trajectory data, identify the deviation angle of the particle movement direction, determine the spatial distribution of the flow field disturbance, and obtain a particle drug processing flow field disturbance data set; S5: Based on the particle drug processing flow field disturbance data set, the particle drug interface change data is called, the particle drug processing state deviation rate is analyzed, and the drug processing real-time monitoring result is obtained.

2. The real-time monitoring method for the granular drug processing process according to claim 1, characterized in that: The photoacoustic signal feature data set includes thermal photoacoustic signals, pressure-induced photoacoustic signals, and photoacoustic signal amplitudes; the granular drug trace component identification data includes target component signal gain coefficient, photoacoustic holographic image contrast, and target component spatial distribution information; the granular drug interface change data includes fluorescence spectrum data, fluorescence peak wavelength, and fluorescence peak offset rate; the granular drug processing flow field disturbance data set includes particle trajectory data, particle movement direction offset angle, and flow field disturbance spatial distribution; the drug processing real-time monitoring results include granular drug interface change data, granular drug processing state deviation rate, and granular drug processing flow field disturbance data set.

3. The real-time monitoring method for the granular drug processing process according to claim 1, characterized in that: The steps for acquiring the photoacoustic signal feature data set are specifically as follows: S111: Based on the photoacoustic signal data during the processing of the granular medicine, a fixed time interval is set, the photoacoustic signal amplitude at each time point is detected, the data is recorded, and a photoacoustic signal amplitude sequence is obtained; S112: Based on the photoacoustic signal amplitude sequence, the amplitude change rate of adjacent time points is identified using the formula: ； Calculate the photoacoustic signal change rate at each time interval and establish a photoacoustic signal change rate sequence; in, represents the rate of change of photoacoustic signal, and represents the amplitude of the photoacoustic signal at adjacent time points, represents a time interval; S113: calling the photoacoustic signal change rate sequence, screening the time points where the change rate exceeds the threshold, extracting the corresponding photoacoustic signal amplitude, and obtaining a photoacoustic signal feature data set.

4. The real-time monitoring method for the granular drug processing process according to claim 3, characterized in that: The specific steps for obtaining the identification data of trace components of the granular medicine are as follows: S211: Based on the photoacoustic signal feature data set, calling the photoacoustic signal amplitude, calculating the initial gain coefficient of the target component signal, and performing normalization processing to obtain a normalized gain coefficient; S212: Based on the normalized gain coefficient, by adjusting the contrast parameter of the differential area of ​​the photoacoustic holographic image, the formula is used: ； Calculate and obtain contrast optimization parameters; in, Optimize the parameters for contrast, For the The normalized gain coefficient of pixels, For the The photoacoustic signal intensity of each pixel is is the average normalized gain coefficient of the pixel points, is the total number of pixels; S213: Based on the contrast optimization parameters, the pixel distribution of the photoacoustic holographic image is adjusted to extract the spatial distribution information of the target component to obtain the micro-component identification data of the granular medicine.

5. The real-time monitoring method for the granular drug processing process according to claim 4, characterized in that: The steps for obtaining the particle drug interface change data are specifically as follows: S311: extracting fluorescence spectrum data based on the micro-component identification data of the granular medicine, analyzing the fluorescence intensity of each wavelength, determining the peak position of the spectrum, recording the peak wavelength, calculating the wavelength change per unit time, and obtaining the fluorescence peak shift rate; S312: Call the fluorescence peak shift rate, identify the noise baseline fluctuation range, compare the shift rate at each time point with the noise baseline fluctuation range, screen the time points beyond the fluctuation range, evaluate the cumulative change of the shift rate, and use the formula: ； The mean value of fluorescence peak drift deviation was calculated; in, represents the mean value of fluorescence peak drift deviation, Representative The fluorescence peak shift rate at each time point is Represents the mean value of the noise baseline fluctuation range, Represents the total number of time points that are beyond the range of noise baseline fluctuations, Representative The weight coefficient of each time point, Representative The time interval between time points, Represents the total measurement time length; S313: Based on the mean value of the fluorescence peak drift deviation, the time point change trend is counted, the acceleration change of the offset rate is analyzed, and the dynamic change rate of the interface is calculated in combination with the time accumulation to obtain the particle drug interface change data.

6. The real-time monitoring method for the granular drug processing process according to claim 5, characterized in that: The steps for acquiring the particle drug processing flow field disturbance data set are specifically as follows: S411: extracting optical imaging data of particles based on the particle-drug interface change data, using a high frame rate optical imaging device to record trajectory data of particles in a time series, analyzing the motion trajectory vector of the particles, and obtaining particle trajectory data; S412: Call the particle trajectory data, extract the movement direction of the particles at adjacent time points, analyze the angle change trend in the time series, determine the impact of the fluid on the particle movement, adjust the disturbance parameters based on the particle force conditions, identify the offset fluctuation range of the particles in the disturbance area, and use the formula: ； The deviation angle of the particle movement direction is calculated; in, represents the deviation angle of the particle motion direction, , Represents particles at time point and The X-axis coordinate, , represents the corresponding Y-axis coordinate, Represents the vertical displacement of particles under fluid disturbance; S413: calling the particle movement direction offset angle, identifying the spatial distribution of the flow field disturbance area, analyzing the movement trend of the particles in the disturbance area, and obtaining a particle drug processing flow field disturbance data set.

7. The real-time monitoring method for the granular drug processing process according to claim 6, characterized in that: The steps for obtaining the real-time monitoring results of drug processing are specifically as follows: S511: Based on the particle drug processing flow field disturbance data set, call the particle drug interface change data, analyze the particle drug morphology change rate and particle aggregation degree, and obtain the particle morphology change coefficient; S512: Based on the particle morphology variation coefficient, the variation deviation of the particle drug processing state is evaluated, and combined with the particle drug interface variation data, the formula is used: ； Identify the variation deviation of the particle drug processing state at each moment and obtain the particle processing deviation rate; in, represents the particle processing deviation rate, represents the maximum value of the particle morphology variation coefficient, represents the minimum value of the particle morphology variation coefficient, The average change value representing the trend of particle morphology change, represents the fluctuation value of the particle interface change data, represents the particle processing state deviation adjustment factor; S513: Based on the particle processing deviation rate, the real-time changes of the particle drug processing state are analyzed, and combined with the dynamic trend of the processing state deviation, whether the particle drug processing state is stable is monitored to obtain the real-time monitoring result of drug processing.

8. A real-time monitoring system for the processing of granular drugs, characterized in that: According to the real-time monitoring method of the granular drug processing process according to any one of claims 1 to 7, the system comprises: The photoacoustic signal control module controls the photoacoustic excitation power and intensity, synchronizes the photoacoustic signal change amplitude, calculates the photoacoustic signal response time deviation, and obtains the photoacoustic signal stability data based on the photoacoustic signal data during the particle drug processing; The target component gain calculation module calculates the target component signal gain coefficient based on the photoacoustic signal stability data, adjusts the photoacoustic signal amplitude contrast, analyzes the target component signal peak change, compares the difference distribution between the target component signal gain coefficient and the background signal, screens the gain area, analyzes the target component signal enhancement degree, extracts the target component spatial distribution information, and obtains the target component spatial distribution data; The particle interface change tracking module calls the fluorescence spectrum characteristics based on the target component spatial distribution data, calculates the fluorescence peak wavelength shift rate, compares the fluorescence peak wavelength shift rate with the interface stability threshold, screens the fluorescence drift time exceeding the interface stability threshold, and obtains the particle drug interface change data; The flow field disturbance identification module identifies the deviation angle of the particle movement direction based on the particle drug interface change data and the particle trajectory change, compares the consistency of the particle movement direction deviation angle with the fluid movement direction, analyzes the flow field disturbance trend of the particle trajectory, and obtains the particle drug processing flow field disturbance data; The processing deviation monitoring module analyzes the particle movement direction deviation change rate based on the particle drug processing flow field disturbance data, compares the particle movement direction deviation change rate with the flow field stability parameter, calculates the particle drug processing state deviation rate, and obtains the real-time monitoring result of drug processing.

Images