A method and system for controlling the sterile filling process of midazolam oral solution with nitrogen protection

Abstract

The application provides a midazolam oral liquid nitrogen-filled protection sterile filling process control method and system, relates to the technical field of medicine filling process control, and the application collects a plurality of spectral images sequences of headspace gas in a bottle before sealing through a transmission imaging system integrated in a filling line after nitrogen filling of the midazolam oral liquid, extracts oxygen characteristic absorption waveband light intensity attenuation data through spectral separation, and generates a two-dimensional oxygen concentration graph of a bottle mouth plane; according to this, the pixel local oxygen partial pressure is calculated, the three-dimensional oxygen concentration field is constructed in combination with the pre-stored bottle body geometric parameters, and the oxygen-rich area is identified; then, the model reference self-adaptive controller is used to compare the oxygen-rich area with an ideal nitrogen model, generate complementary parameters containing a blowing angle, intensity and time, drive an actuating mechanism to perform point pulse blowing, and after verification that the standard is met, enter cap sealing, so that the oxygen-rich area in the headspace of the midazolam oral liquid bottle can be accurately detected, directionally treated and verified to meet the standard, and the oxygen concentration before sealing can meet the standard.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of medical filling process control, in particular to a sterile filling process control method and system for midazolam oral liquid nitrogen protection. BACKGROUND

[0002] In the medical field, the quality and stability of midazolam oral liquid as a commonly used drug are crucial. The current common protection measure is nitrogen protection. In the process of sterile filling under nitrogen protection, in order to prevent the oral liquid from being oxidized and deteriorated, prolong the shelf life and ensure the drug efficacy, it is necessary to accurately control the oxygen concentration in the headspace area of the bottle. Therefore, an efficient, accurate and adjustable process control method is required to ensure that each bottle of oral liquid is filled and sealed in a low-oxygen environment that meets the standards.

[0003] At present, for the sterile filling of midazolam oral liquid under nitrogen protection, some enterprises use a fixed parameter nitrogen filling and purging method. That is, during the filling process, unified nitrogen filling is performed on the bottles according to the pre-set nitrogen filling flow rate, time and pressure parameters, and then simple sampling detection is performed to roughly assess whether the oxygen concentration in the bottles meets the standards.

[0004] This fixed parameter nitrogen filling and purging method lacks flexibility and accuracy. Since the actual conditions of each bottle of oral liquid during the filling process may differ, such as the liquid level height in the bottle body and the headspace volume, the unified nitrogen filling parameters cannot be adjusted according to the specific conditions of each bottle, which may lead to the oxygen concentration in some bottles not meeting the expected standards. Moreover, sampling detection can only reflect the conditions of some products and cannot monitor and handle each bottle, making it difficult to ensure the quality stability of all products. SUMMARY

[0005] The application aims to provide a sterile filling process control method and system for midazolam oral liquid under nitrogen protection to solve the problem in the prior art that the fixed parameter nitrogen filling and purging and sampling detection method cannot adjust the nitrogen filling parameters according to the specific conditions of each bottle, cannot monitor and handle each bottle, and cannot ensure the quality stability of the products.

[0006] To solve the above technical problems, in a first aspect, the application provides a sterile filling process control method for midazolam oral liquid under nitrogen protection, comprising:

[0007] After the midazolam oral liquid is treated under nitrogen, a multispectral image sequence of the headspace gas in the bottle before sealing is acquired by a transmission imaging system integrated on the filling line;

[0008] The spectral image sequence is subjected to spectral separation processing to extract light intensity attenuation data of the oxygen molecule characteristic absorption band, and a two-dimensional concentration map reflecting the oxygen distribution on the bottle opening plane is generated based on the light intensity attenuation data.

[0009] Based on the two-dimensional concentration map, the local oxygen partial pressure value corresponding to each pixel point is calculated, the three-dimensional oxygen concentration field of the headspace area in the bottle is constructed in combination with the pre-stored bottle body geometric parameters corresponding to the midazolam oral liquid, and the oxygen-enriched area exceeding the concentration limit is identified according to a preset oxygen concentration threshold value;

[0010] The three-dimensional oxygen concentration field is compared with an ideal nitrogen covering model by a model reference adaptive controller, and the supplementary blowing parameters for each bottle body are generated based on the distribution characteristics of the oxygen-enriched area, the supplementary blowing parameters including a blowing angle, an airflow intensity, and a blowing duration;

[0011] A blowing execution mechanism is driven based on the supplementary blowing parameters to control the nozzle orientation according to the blowing angle, and the oxygen-enriched area is subjected to point pulse blowing by using the blowing duration and the airflow intensity, and after the point pulse blowing, the treated headspace gas in the bottle is rapidly verified and detected to confirm that the oxygen concentration reaches a predetermined standard and enters a cap sealing process.

[0012] Optionally, the three-dimensional oxygen concentration field is compared with an ideal nitrogen covering model by a model reference adaptive controller, and the supplementary blowing parameters for each bottle body are generated based on the distribution characteristics of the oxygen-enriched area, the supplementary blowing parameters including a blowing angle, an airflow intensity, and a blowing duration, comprising:

[0013] An ideal nitrogen covering model is loaded by the model reference adaptive controller, the ideal nitrogen covering model defining a target oxygen concentration value of each spatial position in the headspace area in the bottle;

[0014] The three-dimensional oxygen concentration field is compared with the ideal nitrogen covering model in space to establish an accurate correspondence relationship of three-dimensional space coordinates between the two models;

[0015] Based on the accurate correspondence relationship, the measured oxygen concentration value of each position in the three-dimensional oxygen concentration field is compared with the target oxygen concentration value of the corresponding position in the ideal nitrogen covering model to identify a concentration difference value;

[0016] Based on the spatial coordinate range, the volume size, and the maximum oxygen concentration deviation value of the oxygen-enriched area, and in combination with the concentration difference value, the supplementary blowing parameters for each bottle body are generated.

[0017] Optionally, the three-dimensional oxygen concentration field is compared with the ideal nitrogen covering model in space to establish an accurate correspondence relationship of three-dimensional space coordinates between the two models, comprising:

[0018] For each bottle, the spatial coordinate range of the oxygen-enriched region relative to the azimuth angle of the bottle center axis is taken as the sweeping angle, the gas flow intensity is determined according to the concentration difference value and the maximum oxygen concentration over-difference value, and the volume size of the oxygen-enriched region and the weighted sum of the concentration difference value are taken as the sweeping duration;

[0019] The sweeping angle, gas flow intensity and sweeping duration are combined as the supplementary sweeping parameters of the corresponding bottle.

[0020] Optionally, the supplementary sweeping parameters are used to drive the sweeping execution mechanism to control the nozzle orientation according to the sweeping angle, and to implement point-pulse sweeping on the oxygen-enriched region by using the sweeping duration and gas flow intensity, and after the point-pulse sweeping, to perform rapid verification detection on the processed in-bottle headspace gas, and to enter the cap sealing process after confirming that the oxygen concentration reaches the predetermined standard, including:

[0021] Based on the supplementary sweeping parameters, a control signal is sent to the sweeping execution mechanism to drive the sweeping execution mechanism to start operation;

[0022] According to the sweeping angle in the supplementary sweeping parameters, the nozzle is rotated to the corresponding orientation of the sweeping angle by the angle adjusting assembly of the sweeping execution mechanism, so that the nozzle is aligned with the spatial position of the oxygen-enriched region;

[0023] According to the gas flow intensity in the supplementary sweeping parameters, the nitrogen output pressure of the sweeping execution mechanism is adjusted, and according to the sweeping duration in the supplementary sweeping parameters, the nitrogen output time is controlled, and nitrogen is sprayed to the oxygen-enriched region to complete the point-pulse sweeping;

[0024] After the point-pulse sweeping is completed, a spectral image of the processed in-bottle headspace region is collected, light intensity attenuation data of an oxygen molecule feature absorption band is extracted, and a current oxygen concentration value is calculated;

[0025] The current oxygen concentration value is compared with a preset oxygen concentration threshold value, and if the current oxygen concentration value reaches the preset oxygen concentration threshold value, a sealing control signal is triggered to make the bottle enter the cap sealing process.

[0026] Optionally, based on the two-dimensional concentration map, a local oxygen partial pressure value corresponding to each pixel point is calculated, a three-dimensional oxygen concentration field of the in-bottle headspace region is constructed in combination with the pre-stored bottle body geometric parameters corresponding to the midazolam oral solution, and an oxygen-enriched region with concentration exceeding the limit is identified according to a preset oxygen concentration threshold value, including:

[0027] Based on the light intensity attenuation data of each pixel point in the two-dimensional concentration map, a local oxygen partial pressure value corresponding to each pixel point is calculated, and pre-stored bottle body geometric parameters corresponding to the midazolam oral solution are obtained;

[0028] Based on the local oxygen partial pressure value and the bottle body geometric parameter, a three-dimensional coordinate system is established with the bottle mouth plane as the reference, and the headspace region in the bottle is divided into multiple layered planes at a preset interval along the height direction of the bottle body;

[0029] On each layered plane, according to the variation law of the radial dimension of the bottle body, the oxygen partial pressure value of the bottle mouth plane is mapped to the corresponding position of each layered plane through a bilinear interpolation algorithm to obtain the oxygen partial pressure value of the three-dimensional space grid node;

[0030] According to the oxygen partial pressure value of all three-dimensional space grid nodes, a continuous three-dimensional oxygen concentration field is generated by using a three-dimensional data reconstruction algorithm;

[0031] The oxygen concentration value of each node in the three-dimensional oxygen concentration field is compared with a preset oxygen concentration threshold point by point, the three-dimensional space region where the oxygen concentration value exceeds the threshold value is identified as an oxygen-enriched region, and the spatial coordinate range, volume size and maximum oxygen concentration excess value of each oxygen-enriched region are recorded.

[0032] Optionally, after the midazolam oral liquid is filled with nitrogen, a multispectral image sequence of the headspace gas in the bottle before sealing is collected by a transmission imaging system integrated on the filling line, including:

[0033] After the midazolam oral liquid is filled with nitrogen, a transmission imaging system integrated on the filling line is activated, and the transmission imaging system includes a hyperspectral line array camera and an LED array light source of a specific waveband;

[0034] The LED array light source is controlled to light up narrowband light emitting units corresponding to the characteristic absorption waveband of oxygen molecules in a preset order;

[0035] The hyperspectral line array camera is triggered synchronously, and the transmission light signal of the headspace gas in the bottle corresponding to each waveband is collected when one narrowband light emitting unit is lit up, and the transmission light signal is converted into digital image data;

[0036] The digital image data collected from each waveband is combined in the order of spectral waveband to generate a multispectral image sequence containing information of the characteristic absorption waveband of oxygen molecules.

[0037] Optionally, the spectral image sequence is subjected to spectral separation processing to extract light intensity attenuation data of the characteristic absorption waveband of oxygen molecules, and a two-dimensional concentration map reflecting the oxygen distribution of the bottle mouth plane is generated based on the light intensity attenuation data, including:

[0038] The multispectral image sequence is subjected to spectral separation processing to identify and extract digital image data corresponding to the characteristic absorption waveband of oxygen molecules;

[0039] Obtain the light intensity value of each pixel point from the digital image data, calculate the decay amount of the light intensity value of each pixel point and the initial light intensity value of the corresponding wave band, and obtain the light intensity decay data of each pixel point;

[0040] Correspond the position of each pixel point to the two-dimensional coordinates of the bottle mouth plane, arrange the light intensity decay data corresponding to all two-dimensional coordinates according to the coordinate distribution order of the bottle mouth plane, and generate a two-dimensional concentration map reflecting the oxygen distribution of the bottle mouth plane.

[0041] In a second aspect, the present application provides a sterile filling process control system for midazolam oral liquid filled with nitrogen protection, comprising:

[0042] The acquisition module is configured to acquire a sequence of multi-spectral images of headspace gas in a bottle before sealing by a transmission imaging system integrated on a filling line after the midazolam oral liquid is filled with nitrogen.

[0043] The processing module is configured to perform spectral separation processing on the spectral image sequence, extract light intensity decay data of an oxygen molecule characteristic absorption wave band, and generate a two-dimensional concentration map reflecting the oxygen distribution of the bottle mouth plane based on the light intensity decay data.

[0044] The construction module is configured to calculate a local oxygen partial pressure value corresponding to each pixel point based on the two-dimensional concentration map, construct a three-dimensional oxygen concentration field of the headspace region in the bottle in combination with pre-stored bottle body geometric parameters corresponding to the midazolam oral liquid, and identify an oxygen-enriched region exceeding the concentration limit according to a pre-set oxygen concentration threshold.

[0045] The generation module is configured to perform spatial registration and comparison of the three-dimensional oxygen concentration field and an ideal nitrogen gas coverage model by a model reference adaptive controller, generate a supplemental purging parameter for each bottle body based on the distribution characteristics of the oxygen-enriched region, and the supplemental purging parameter includes a purging angle, an airflow intensity, and a purging duration.

[0046] The verification module is configured to drive a purging execution mechanism to control the nozzle orientation according to the purging angle based on the supplemental purging parameter, implement spot pulse purging on the oxygen-enriched region by using the purging duration and the airflow intensity, and perform rapid verification and detection on the treated headspace gas after the spot pulse purging, and enter a cap sealing process after confirming that the oxygen concentration meets the predetermined standard.

[0047] In a third aspect, the present application provides an electronic device, comprising:

[0048] A memory for storing a computer program;

[0049] A processor for executing the computer program to implement the steps of the sterile filling process control method for midazolam oral liquid filled with nitrogen protection according to the first aspect described above.

[0050] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program, when executed by a processor, can implement the steps of the midazolam oral liquid nitrogen protection sterile filling process control method according to the first aspect.

[0051] The midazolam oral liquid nitrogen protection sterile filling process control method provided by the present application can realize accurate monitoring of the oxygen concentration in the headspace of the bottle, accurate positioning of the oxygen-rich area, and individualized targeted processing of the oxygen-rich area. The limitations of fixed parameter nitrogen filling are effectively avoided, and it is ensured that each bottle of oral liquid is in a low-oxygen environment that meets the standards before sealing, thereby significantly improving the accuracy, flexibility of the filling process, and the stability of product quality.

[0052] Further, by loading the pre-stored ideal nitrogen coverage model into the model reference adaptive controller, the three-dimensional oxygen concentration field is spatially registered with the model to establish an accurate three-dimensional coordinate correspondence. By comparing the measured and target oxygen concentration values at the corresponding positions, the concentration difference value is obtained. In combination with the spatial coordinate range, volume, maximum oxygen concentration out-of-tolerance value, and concentration difference value of the oxygen-rich area, the supplementary blowing parameters including blowing angle, airflow intensity, and duration are generated for each bottle. This step realizes accurate comparison of the three-dimensional oxygen concentration field and the ideal model, enables the supplementary blowing parameters to be individually generated according to the specific characteristics of the oxygen-rich area of each bottle, improves the relevance and accuracy of the supplementary blowing parameters, and provides a scientific basis for subsequent pinpoint pulse blowing. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0054] Figure 1 A flowchart of a midazolam oral liquid nitrogen protection sterile filling process control method provided by an embodiment of the present application;

[0055] Figure 2A flowchart of a specific embodiment of a sterile filling process control method for the nitrogen protection of midazolam oral liquid provided by the embodiments of the present application is shown in the figure;

[0056] Figure 3 A scene diagram of a specific embodiment of a sterile filling process control method for the nitrogen protection of midazolam oral liquid provided by the embodiments of the present application is shown in the figure;

[0057] Figure 4 A structure diagram of a sterile filling process control system for the nitrogen protection of midazolam oral liquid provided by the embodiments of the present application is shown in the figure. DETAILED DESCRIPTION

[0058] In the medical field, the nitrogen protection sterile filling of midazolam oral liquid plays a key role in product quality and stability. However, the existing fixed parameter nitrogen filling and purging method has obvious shortcomings. Since the actual situation of each bottle of oral liquid is different when filling, such as different liquid level height and headspace volume, the unified nitrogen filling parameters cannot achieve "treatment according to the disease", resulting in that the oxygen concentration in some bottles does not meet the standard. And sampling detection can only reflect the condition of part of the products, and cannot monitor and process each bottle, so it is difficult to ensure that all products can complete filling and sealing in a low-oxygen environment that meets the standard, and the product quality stability is also difficult to guarantee.

[0059] To solve the above problems, the present application provides a sterile filling process control method for the nitrogen protection of midazolam oral liquid. After the nitrogen treatment of the oral liquid, the method uses a transmission imaging system to collect a multi-spectral image sequence of the headspace gas in the bottle, generates a two-dimensional concentration map and a three-dimensional oxygen concentration field through a series of processing, and accurately identifies the oxygen-rich area. Then, based on the distribution characteristics of the oxygen-rich area, the supplementary purging parameters for each bottle are generated, the purging execution mechanism is driven to perform point pulse purging on the oxygen-rich area, and rapid verification detection is performed thereafter. This way can accurately adjust according to the specific situation of each bottle, monitor and process each bottle, ensure that each bottle of oral liquid can complete filling and sealing in a low-oxygen environment that meets the standard, and effectively improve the stability of product quality.

[0060] In order for those skilled in the art to better understand the present application, the present application will be further described in detail below in combination with the drawings and specific embodiments. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0061] The core of the present application is to provide a sterile filling process control method for the nitrogen protection of midazolam oral liquid, and a flowchart of a specific embodiment of the method is shown in Figure 1 The method comprises:

[0062] S101, after the midazolam oral liquid is filled with nitrogen, a multispectral image sequence of the headspace gas in the bottle before sealing is collected by a transmission imaging system integrated on the filling line;

[0063] Optionally, step S101 can specifically include the following steps:

[0064] S1011, after the midazolam oral liquid is filled with nitrogen, a multispectral image sequence of the headspace gas in the bottle before sealing is collected by a transmission imaging system integrated on the filling line;

[0065] S1012, control the LED array light source to light up the narrow-band light-emitting unit corresponding to the oxygen molecule characteristic absorption band in a predetermined order;

[0066] S1013, synchronously trigger the hyperspectral line array camera, collect the transmission light signal of the headspace gas in the bottle corresponding to the wave band at each time a narrow-band light-emitting unit is lit up, and convert the transmission light signal into digital image data;

[0067] S1014, combine the digital image data collected at each wave band in order of spectral wave band to generate a multispectral image sequence containing oxygen molecule characteristic absorption band information.

[0068] In the above scheme, the transmission imaging system is integrated on the filling line and is a device for collecting image information of the headspace gas in the bottle, which is composed of a hyperspectral line array camera and an LED array light source of specific wave bands. The hyperspectral line array camera is a camera that can collect spectral information of a specific area, and can convert the collected transmission light signal into digital image data. The LED array light source is a light source composed of multiple LED light-emitting units, which includes a narrow-band light-emitting unit corresponding to the oxygen molecule characteristic absorption band. The oxygen molecule characteristic absorption band is a specific spectral band in which oxygen molecules have an absorption phenomenon, and through which the oxygen in the headspace gas in the bottle can be analyzed. The narrow-band light-emitting unit is a light-emitting unit in the LED array light source that only emits light of a specific narrow spectral band. The transmission light signal is a light signal carrying gas information after the light passes through the headspace gas in the bottle. The digital image data is the digital image information obtained by the hyperspectral line array camera after converting the transmission light signal. The multispectral image sequence is an image sequence obtained by combining the digital image data collected at each wave band in order of spectral wave band, containing oxygen molecule characteristic absorption band information.

[0069] In the embodiments of the present application, first, after the midazolam oral liquid is filled with nitrogen, the transmission imaging system installed on the filling line is started, which is equipped with a hyperspectral line array camera capable of capturing fine spectral information and an LED array light source capable of emitting light of specific wave bands.

[0070] Secondly, the system calls the pre-stored narrow-band light-emitting unit lighting sequence by step S1012, and sends a control signal to the LED array light source according to the sequence, so that the narrow-band light-emitting units corresponding to the oxygen molecule characteristic absorption waveband in the light source are lit one by one, ensuring that each narrow-band light-emitting unit works alone at a specified time and emits light of the corresponding waveband to irradiate the headspace area in the bottle.

[0071] Then, by step S1013, a signal for lighting a certain narrow-band light-emitting unit is sent to the LED array light source at the same time, and a signal for collecting is sent to the hyperspectral line array camera, so that the camera and the light source are synchronized. When the light emitted by the narrow-band light-emitting unit passes through the headspace gas in the bottle, the camera timely captures the light signal transmitted by the gas, and then converts the captured light signal into digital image data composed of a series of numbers through the internal photoelectric conversion components of the camera and temporarily stores it.

[0072] Finally, by step S1014, the digital image data of each waveband collected in step S1013 is called, and these single-waveband digital images are arranged and integrated in turn according to the pre-set sequence of the spectral wavebands corresponding to each image, forming a continuous image set, which is a multispectral image sequence containing information of the oxygen molecule characteristic absorption waveband.

[0073] In actual application, when a bottle of midazolam oral solution completes the nitrogen filling process on the oral solution filling production line of a pharmaceutical factory, the production line control system automatically activates the transmission imaging system. The control module in the LED array light source lights up the narrow-band light-emitting unit corresponding to a certain characteristic absorption waveband of oxygen molecules according to the pre-set sequence, and triggers the hyperspectral line array camera to collect the transmission light signal of the waveband and convert it into digital image data. Then the other narrow-band light-emitting units corresponding to the characteristic absorption waveband of oxygen molecules are lit in turn, and the hyperspectral line array camera synchronously collects and converts the digital image data of each waveband. Finally, the data processing module combines these digital image data in the order of spectral wavebands to generate a multispectral image sequence of the headspace gas in the bottle.

[0074] The overall scheme of S101 above activates the transmission imaging system, uses the LED array light source to light up the narrow-band light-emitting units of specific wavebands in turn, and synchronously triggers the hyperspectral line array camera to collect the transmission light signal, and finally generates a multispectral image sequence. It can accurately collect the information of the headspace gas in the bottle at the characteristic absorption waveband of oxygen molecules, providing detailed and accurate data basis for subsequent analysis of the oxygen concentration distribution in the bottle, which helps to improve the evaluation and control of the nitrogen filling protection effect and ensure product quality.

[0075] S102, performing spectral separation processing on the spectral image sequence, extracting light intensity attenuation data of the oxygen molecule characteristic absorption waveband, and generating a two-dimensional concentration map reflecting the oxygen distribution on the bottle mouth plane based on the light intensity attenuation data;

[0076] Optionally, step S102 may specifically include the following steps:

[0077] S1021. Perform spectral separation processing on the multispectral image sequence to identify and extract digital image data corresponding to the characteristic absorption bands of oxygen molecules;

[0078] S1022. Obtain the light intensity value of each pixel from the digital image data, calculate the attenuation of the light intensity value of each pixel relative to the initial light intensity value of the corresponding band, and obtain the light intensity attenuation data of each pixel.

[0079] S1023. Correspond the position of each pixel to the two-dimensional coordinates of the bottle mouth plane, arrange the light intensity attenuation data corresponding to all two-dimensional coordinates in the order of coordinate distribution of the bottle mouth plane, and generate a two-dimensional concentration map reflecting the oxygen distribution of the bottle mouth plane.

[0080] In the above scheme, spectral separation processing is the operation of distinguishing and extracting image data from different bands in the spectral image sequence. The characteristic absorption band of oxygen molecules refers to the absorption phenomenon of oxygen molecules in specific spectral bands, which can be used to analyze oxygen conditions. A pixel is the smallest unit in an image, and each pixel has a corresponding light intensity value. Light intensity value is a numerical value that measures the intensity of light. The initial light intensity value is the light intensity value of the corresponding band before the light is absorbed by the headspace gas inside the bottle. Light intensity attenuation data is the amount of attenuation of the light intensity value of each pixel compared to the initial light intensity value of the corresponding band, reflecting the degree of light absorption by oxygen at that location. Two-dimensional coordinates are used to represent the coordinates of each point on the bottle opening plane. The two-dimensional concentration map is generated based on the light intensity attenuation data, reflecting the oxygen distribution on the bottle opening plane.

[0081] In this embodiment of the application, the multispectral image sequence obtained in step S101 is first subjected to spectral separation processing in step S1021. For example, a spectral unmixing algorithm is used to identify and extract image data that corresponds only to the characteristic absorption band of oxygen molecules from images of multiple bands.

[0082] Secondly, in step S1022, the light intensity value of each pixel is read from the extracted image data of the band, and the initial light intensity value of the corresponding band is subtracted from the light intensity value of each pixel. The initial light intensity value is the light intensity when the light does not pass through the gas. The light intensity attenuation of each pixel is calculated to obtain the light intensity attenuation data. For example, if the light intensity value of a certain pixel is 80 and the initial light intensity value of the corresponding band is 100, then the attenuation is 20.

[0083] Finally, the position of each pixel in the image is corresponded to the two-dimensional coordinates of the bottle mouth plane by step S1023, such as the row and column numbers of the image pixel correspond to the X and Y coordinates of the bottle mouth plane, and then the light intensity attenuation data corresponding to all two-dimensional coordinates are arranged in the order of coordinate distribution of the bottle mouth plane to generate a two-dimensional concentration map reflecting the oxygen distribution of the bottle mouth plane.

[0084] In actual application, after obtaining the spectral image sequence of a certain oral liquid bottle, the image data corresponding to the characteristic absorption band of oxygen molecules is extracted by using professional spectral separation software. Through image analysis program, the light intensity value of each pixel in the image data is obtained, which is compared with the initial light intensity value recorded in advance corresponding to the wave band, and the light intensity attenuation data of each pixel is calculated. According to the calibration information of the imaging system, the position of the pixel is corresponded to the two-dimensional coordinates of the bottle mouth plane. Using drawing software, the light intensity attenuation data is arranged in the order of the coordinates of the bottle mouth plane, and a two-dimensional concentration map reflecting the oxygen distribution of the bottle mouth plane is generated.

[0085] The overall scheme of S102 above accurately extracts the image data of the characteristic absorption band of oxygen molecules by spectral separation processing, calculates the light intensity attenuation data and corresponds it to the two-dimensional coordinates of the bottle mouth plane, and finally generates a two-dimensional concentration map. This enables intuitive understanding of the oxygen distribution of the bottle mouth plane, providing an important basis for subsequent judgment of the oxygen concentration distribution in the headspace area of the bottle, determination of the oxygen-enriched area and targeted nitrogen charging measures, and helps to improve the effect of nitrogen charging protection and product quality.

[0086] S103, based on the two-dimensional concentration map, calculating the local oxygen partial pressure value corresponding to each pixel, combining the pre-stored bottle body geometric parameters of the midazolam oral liquid to construct a three-dimensional oxygen concentration field of the headspace area in the bottle, and identifying the oxygen-enriched area with concentration exceeding the preset oxygen concentration threshold value;

[0087] Optionally, step S103 can specifically include the following steps:

[0088] S1031, based on the light intensity attenuation data of each pixel in the two-dimensional concentration map, calculating the local oxygen partial pressure value corresponding to each pixel, and obtaining the pre-stored bottle body geometric parameters corresponding to the midazolam oral liquid;

[0089] S1032, based on the local oxygen partial pressure value and the bottle body geometric parameters, establishing a three-dimensional coordinate system taking the bottle mouth plane as the reference, and dividing the headspace area in the bottle into multiple layered planes in the height direction of the bottle body at a preset interval;

[0090] S1033、In each layer plane, according to the bottle body radial size variation law, the oxygen partial pressure value of the bottle mouth plane is mapped to the corresponding position of each layer plane by a bilinear interpolation algorithm to obtain the oxygen partial pressure value of the three-dimensional space grid node;

[0091] S1034、According to the oxygen partial pressure value of all three-dimensional space grid nodes, a three-dimensional data reconstruction algorithm is used to generate a continuous three-dimensional oxygen concentration field;

[0092] S1035、The oxygen concentration value of each node in the three-dimensional oxygen concentration field is compared with the preset oxygen concentration threshold point by point, the three-dimensional space region where the oxygen concentration value exceeds the threshold value is identified as an oxygen-enriched region, and the spatial coordinate range, volume size and maximum oxygen concentration excess value of each oxygen-enriched region are recorded.

[0093] In the above scheme, the local oxygen partial pressure value is calculated by the light intensity attenuation data, which reflects the oxygen partial pressure at a specific position in the bottle. The bottle body geometric parameters are the pre-stored information about the shape and size of the midazolam oral liquid bottle body, which is used to assist in constructing the three-dimensional oxygen concentration field. The three-dimensional coordinate system is established based on the bottle mouth plane, which is used to determine the spatial position of each point in the headspace region of the bottle. The layer plane is obtained by dividing the headspace region of the bottle along the bottle height direction at a preset interval. The bilinear interpolation algorithm is an algorithm for calculating the value of an unknown point according to the value of a known point on a plane, which is used to map the oxygen partial pressure value of the bottle mouth plane to each layer plane. The three-dimensional space grid node is the node of the grid divided in the three-dimensional coordinate system, and its oxygen partial pressure value is obtained by the interpolation algorithm. The preset oxygen concentration threshold value is a pre-set oxygen concentration standard value. The oxygen-enriched region is a three-dimensional space region in the three-dimensional oxygen concentration field where the oxygen concentration value exceeds the preset oxygen concentration threshold value, and its distribution characteristics include the spatial coordinate range, volume size and maximum oxygen concentration excess value.

[0094] In the embodiment of the application, first, the local oxygen partial pressure value of each pixel point in the two-dimensional concentration map is calculated by using the light intensity attenuation data of each pixel point in the two-dimensional concentration map and combining the pre-set light intensity attenuation and oxygen partial pressure correspondence, which is obtained by preliminary experiment calibration, such as local oxygen partial pressure value = K x light intensity attenuation data, wherein K is the calibration coefficient, for example, the calibration coefficient K = 0.4, and the light intensity attenuation data of a certain pixel point is 25, then the local oxygen partial pressure value of the point is 0.4 x 25 = 10; At the same time, the pre-stored bottle body geometric parameters corresponding to the midazolam oral liquid are called from the system to prepare for subsequent construction of the three-dimensional concentration field.

[0095] Secondly, based on the calculated partial oxygen pressure value and the bottle body geometric parameters, a three-dimensional coordinate system is established by step S1032 in combination with the bottle mouth center position in the bottle body geometric parameters: the bottle mouth plane is defined as the XY plane, the geometric center of the bottle mouth is set as the coordinate origin (0, 0, 0), and the direction from the bottle mouth to the bottle bottom is set as the positive direction of the Z axis; then the headspace region in the bottle is divided into a plurality of layered planes parallel to the bottle mouth plane along the Z axis direction at a preset interval.

[0096] Next, by step S1033, the correspondence between each position and the pixel points of the bottle mouth plane is determined according to the variation law of the radial dimension of the bottle body on each layered plane, and a bilinear interpolation algorithm is adopted, i.e. the oxygen partial pressure value of the bottle mouth plane is mapped to the corresponding position of each layered plane to obtain the oxygen partial pressure values of a plurality of grid nodes in the three-dimensional space by calculating the intermediate point value according to the oxygen partial pressure values of the four adjacent pixel points, for example, the oxygen partial pressure values of the four pixel points corresponding to a point on a layered plane are 8, 10, 9 and 11 respectively, and the oxygen partial pressure value of the point is calculated to be 9.5 by interpolation.

[0097] Then, by step S1034, the oxygen partial pressure values of all the three-dimensional space grid nodes are collected, and these nodes are arranged in order according to their coordinate positions in the three-dimensional coordinate system; secondly, a suitable three-dimensional data reconstruction algorithm (such as volume rendering algorithm) is selected, and the arranged grid node oxygen partial pressure data is input into the algorithm; the algorithm will fill the discrete node data into continuous space data through data interpolation and rendering processing according to the oxygen partial pressure value difference between adjacent nodes, and present it in a visualized way to form a continuous three-dimensional oxygen concentration field which can intuitively display the oxygen concentration of each position in the headspace region of the bottle, for example, different gray scales are used to represent the regions with different oxygen partial pressure values by volume rendering algorithm to form a three-dimensional concentration model with gray scale gradient.

[0098] Finally, by step S1035, the oxygen concentration value of each node in the three-dimensional oxygen concentration field is compared with the preset oxygen concentration threshold point by point, and the nodes with oxygen concentration value greater than the preset threshold are marked, and the continuous space region formed by these marked nodes is the oxygen-enriched region; then the start and end coordinates of the X axis, Y axis and Z axis of each oxygen-enriched region in the three-dimensional coordinate system are determined, and the spatial coordinate range is calculated; then the volume size of each oxygen-enriched region is calculated according to the coordinate range and the space grid density; finally, the maximum oxygen concentration value in each oxygen-enriched region is found, the preset threshold is subtracted from the value to obtain the maximum oxygen concentration excess value, and the information of these oxygen-enriched regions is recorded and stored.

[0099] In practical application, the light intensity attenuation data of each pixel point is extracted from the two-dimensional concentration map on the production line of a pharmaceutical factory, and the partial oxygen pressure value is calculated according to the pre-stored conversion relationship. At the same time, the geometric parameters of the oral liquid bottle of this type are called, including the headspace height of 5 cm, the bottle opening radius of 2 cm, etc. Then, the XY plane is taken as the bottle opening plane, the center of the bottle opening is taken as (0, 0, 0), and the bottle body height direction is taken as the Z axis to establish a three-dimensional coordinate system. Combined with the headspace height of 3.5 cm and the preset interval of 1.75 mm, 20 parallel layered planes are divided along the Z axis direction from 0 to 35 mm. On each layered plane, the corresponding relationship between each position and the pixel point of the bottle opening plane is determined according to the change rule of the radial size of the bottle body. For the layered plane of Z=4mm, the grid node (2, 3, 4) is selected, and its corresponding four adjacent pixel points (1, 2), (3, 2), (1, 4), (3, 4) are found on the bottle opening plane. The oxygen partial pressure values of the four pixel points are 6, 8, 7 and 9 respectively, and the oxygen partial pressure value of the grid node is calculated to be 7.5 by bilinear interpolation. In this way, the oxygen partial pressure values of all the grid nodes of the layered planes are obtained. The oxygen partial pressure values of 5000 three-dimensional space grid nodes in the headspace area are collected, sorted by coordinates, and input into the volume rendering algorithm to generate a three-dimensional oxygen concentration field model. The preset oxygen concentration threshold is called, and each node of the three-dimensional concentration field is compared point by point. The two continuous oxygen-enriched areas formed by the nodes with oxygen concentration values greater than the preset oxygen concentration threshold are marked, and the corresponding information of the first area with a spatial coordinate range of X5-15mm, Y8-18mm, Z2-7mm, a volume size of V, and a maximum oxygen concentration over-limit value of H is recorded, and the corresponding information of the second area is recorded.

[0100] The overall scheme of S103 above can accurately construct the three-dimensional oxygen concentration field of the headspace area in the bottle by combining the two-dimensional concentration map and the geometric parameters of the bottle body, and comprehensively reflect the distribution of the oxygen concentration in the bottle. By comparing with the preset oxygen concentration threshold, the oxygen-enriched area can be accurately identified and its distribution characteristics can be recorded. This is helpful for taking effective nitrogen protection measures for the oxygen-enriched area in the subsequent process, improving the pertinence and effectiveness of nitrogen filling, and ensuring the quality and stability of the product in a low-oxygen environment.

[0101] S104, spatially registering and comparing the three-dimensional oxygen concentration field with an ideal nitrogen coverage model by a model reference adaptive controller, generating a supplementary purge parameter for each bottle body based on the distribution characteristics of the oxygen-enriched area, the supplementary purge parameter including a purge angle, a gas flow intensity, and a purge duration;

[0102] Optionally, step S104 can specifically include the following steps:

[0103] S1041, loading a pre-stored ideal nitrogen coverage model by the model reference adaptive controller, the ideal nitrogen coverage model defining a target oxygen concentration value of each spatial position in the headspace area of the bottle;

[0104] S1042. Spatial registration is performed between the three-dimensional oxygen concentration field and the ideal nitrogen coverage model to establish a precise correspondence between the three-dimensional spatial coordinates of the two models.

[0105] S1043. Based on the precise correspondence, the measured oxygen concentration values ​​at each location in the three-dimensional oxygen concentration field are compared with the target oxygen concentration values ​​at the corresponding locations in the ideal nitrogen coverage model to identify the concentration difference values.

[0106] S1044. Based on the spatial coordinate range, volume, and maximum oxygen concentration deviation of the oxygen-rich region, and combined with the concentration difference value, generate supplementary purging parameters for each bottle.

[0107] Specifically, step S1044 includes the following process: for each bottle, the azimuth angle of the spatial coordinate range of the oxygen-enriched area relative to the central axis of the bottle is taken as the purging angle; the airflow intensity is determined according to the concentration difference value and the maximum oxygen concentration deviation value; the weighted sum of the volume of the oxygen-enriched area and the concentration difference value is taken as the purging duration; and the combination of the purging angle, airflow intensity and purging duration is taken as the supplementary purging parameters for the corresponding bottle.

[0108] In the above scheme, the model reference adaptive controller is a controller with intelligent analysis and comparison functions, used to process relevant data from the three-dimensional oxygen concentration field and the ideal nitrogen coverage model. The ideal nitrogen coverage model is pre-stored and specifies the target oxygen concentration values ​​that should be achieved at various spatial locations in the headspace region within the bottle under ideal conditions. Spatial registration refers to establishing a precise correspondence between the three-dimensional oxygen concentration field and the ideal nitrogen coverage model on three-dimensional spatial coordinates for accurate comparison. The concentration difference value is obtained by comparing the measured oxygen concentration values ​​at each location in the three-dimensional oxygen concentration field with the target oxygen concentration values ​​at the corresponding locations in the ideal nitrogen coverage model. The oxygen-rich region is the part of the headspace region within the bottle where the oxygen concentration exceeds a preset threshold, and its distribution characteristics include spatial coordinate range, volume, and maximum oxygen concentration deviation. The bottle's central axis is a virtual straight line located at the center of the bottle in space. Supplementary purging parameters are used to further reduce the oxygen concentration in the oxygen-rich region within the bottle, including parameters such as purging angle, airflow intensity, and purging duration determined for each bottle.

[0109] In the embodiments of this application, such as Figure 2 As shown, firstly, the model reference adaptive controller loads the pre-stored ideal nitrogen coverage model in the system through step S1041. This model clarifies the target oxygen concentration value at each spatial location in the headspace inside the bottle. For example, the target oxygen concentration value at any location in the headspace inside the bottle does not exceed a predetermined value.

[0110] Secondly, the feature points are extracted from the three-dimensional oxygen concentration field and the ideal nitrogen covering model respectively through step S1042, and these feature points are the fixed geometric feature positions of the bottle body, such as multiple points of the bottle mouth edge, the intersection of the bottle body axis and the bottle mouth plane, the center of the cross section at a certain height of the bottle body, etc.; secondly, the corresponding feature points extracted from the two models are aligned by using a spatial registration algorithm based on the feature points, for example, the bottle mouth center feature points of the two models are all positioned to the spatial coordinates (0, 0, 0), and the bottle body axis feature lines are all aligned with the Z axis; finally, the coordinate error of all corresponding feature points of the two models is controlled within a very small range through algorithm iteration optimization, so as to establish the accurate corresponding relationship of the three-dimensional space coordinates between the two models.

[0111] Then, through step S1043, the three-dimensional coordinates and the corresponding measured oxygen concentration values of all spatial positions in the three-dimensional oxygen concentration field are obtained; and based on the accurate corresponding relationship established in step S1042, the position corresponding to the measured position coordinates in the ideal nitrogen covering model is found, and the target oxygen concentration value of the position is read; then the measured oxygen concentration value of each position is subtracted by the target oxygen concentration value of the corresponding position, and the concentration difference value of the position is calculated.

[0112] Finally, through step S1044, for each bottle body, the azimuth angle of the spatial coordinate range of the oxygen-enriched region relative to the center axis of the bottle body is determined, which is the sweeping angle, for example, the oxygen-enriched region is mainly distributed in the 30-degree direction to the right of the center axis of the bottle body, and the sweeping angle is set to 30 degrees; secondly, the airflow intensity is calculated according to the concentration difference value and the maximum oxygen concentration overage value, the basic airflow intensity is set to , the concentration difference value coefficient is a, the maximum oxygen concentration overage value coefficient is b, and the airflow intensity is +a×concentration difference value+b×maximum oxygen concentration overage value, the greater the two are, the greater the airflow intensity is, for example, the basic airflow intensity =2, the coefficients a=0.3 and b=0.5, the concentration difference value M=4, and the maximum oxygen concentration overage value C=6, the airflow intensity =2+0.3×4+0.5×6=6.2; then the weight coefficient of the volume size is P, and the weight coefficient of the concentration difference value is Q, the weighted sum of the product of the volume size of the oxygen-enriched region and P and the product of the concentration difference value and Q is calculated, which is the sweeping duration, for example, the volume is V and the concentration difference value is M, the sweeping duration =V×P+M×Q; finally, the sweeping angle, the airflow intensity and the sweeping duration calculated are combined as the supplementary sweeping parameters of the corresponding bottle body.

[0113] In practical applications, in the oral liquid filling workshop of a pharmaceutical factory, the ideal nitrogen covering model pre-stored by the model reference adaptive controller is loaded, fixed geometric feature points such as six uniformly distributed points on the bottle mouth edge, the intersection of the bottle body axis and the bottle mouth plane, and the center of the cross section at Z=15mm are extracted from the three-dimensional oxygen concentration field and the ideal nitrogen covering model respectively, and the spatial registration algorithm based on the feature points is used to establish accurate correspondence relationship in the three-dimensional space; then all spatial positions of the three-dimensional oxygen concentration field are traversed, the three-dimensional coordinates and the measured oxygen concentration value N of the position (8, 8, 8) are obtained, the position (8, 8, 8) is found in the ideal nitrogen covering model based on the accurate correspondence relationship, and the target oxygen concentration value K is read, and the concentration difference value of the position is calculated by subtracting K from N, and similar calculations are completed for the whole region; for a certain bottle body, the azimuth angle of the oxygen-enriched region spatial coordinate range relative to the center axis of the bottle body is determined to be 20 degrees, so the blowing angle is set to 20 degrees, the airflow intensity is calculated according to the concentration difference value M=5 and the maximum oxygen concentration overage value C=7, the basic airflow intensity is set to 3, the concentration difference value coefficient a is set to 0.4, the maximum oxygen concentration overage value coefficient b is set to 0.6, the airflow intensity is 3+0.4×5+0.6×7=9.2, the volume size weight coefficient P is set to 0.4, the concentration difference value weight coefficient Q is set to 0.6, the oxygen-enriched region volume is V, and the blowing duration is V×0.4+5×0.6. Finally, the blowing angle 20 degrees, the airflow intensity 9.2 and the calculated blowing duration are combined as the supplementary blowing parameters of the bottle body.

[0114] The above-mentioned overall scheme of S104 can accurately identify the difference of the oxygen concentration in the bottle by accurately comparing the three-dimensional oxygen concentration field and the ideal nitrogen covering model. The supplementary blowing parameters are generated in combination with the distribution characteristics of the oxygen-enriched region, and individualized processing for each bottle body is realized. This helps to accurately blow the oxygen-enriched region, effectively reduces the oxygen concentration in the bottle, improves the effect of nitrogen protection, and ensures that each bottle of oral liquid can be filled in a low-oxygen environment meeting the standards, thereby improving the stability and reliability of product quality.

[0115] S105, based on the supplementary blowing parameters, driving the blowing execution mechanism to control the nozzle direction according to the blowing angle, using the blowing duration and the airflow intensity to implement point pulse blowing on the oxygen-enriched region, and after the point pulse blowing, rapidly verifying and detecting the headspace gas in the processed bottle, and entering the cap sealing process after confirming that the oxygen concentration reaches the predetermined standard.

[0116] Optionally, step S105 can specifically include the following steps:

[0117] S1051, based on the supplementary blowing parameters, sending a control signal to the blowing execution mechanism to drive the blowing execution mechanism to start running; ​

[0118] S1052, according to the purge angle in the supplementary purge parameter, the nozzle is rotated to the direction corresponding to the purge angle by the angle adjustment component of the purge execution mechanism, so that the nozzle is aligned with the spatial position where the oxygen-enriched region is located;

[0119] S1053, the nitrogen output pressure of the purge execution mechanism is adjusted according to the gas flow intensity in the supplementary purge parameter, and the nitrogen output time is controlled according to the purge duration in the supplementary purge parameter, so that nitrogen is sprayed to the oxygen-enriched region to complete the spot pulse purge;

[0120] S1054, after the spot pulse purge is completed, a processed spectral image of the headspace region in the bottle is collected, light intensity attenuation data of an oxygen molecule characteristic absorption waveband is extracted, and a current oxygen concentration value is calculated;

[0121] S1055, the current oxygen concentration value is compared with a preset oxygen concentration threshold value, and if the current oxygen concentration value reaches the preset oxygen concentration threshold value, a sealing control signal is triggered to make the bottle enter a cap sealing process.

[0122] In the above scheme, the purge execution mechanism is a device for performing the purge operation; the control signal is generated based on the supplementary purge parameter and is used to drive the purge execution mechanism to start running. The angle adjustment component is a component in the purge execution mechanism for adjusting the direction of the nozzle. The nozzle is a device for spraying nitrogen in the purge execution mechanism. The nitrogen output pressure is related to the gas flow intensity, and the gas flow intensity can be controlled by adjusting the pressure. The spot pulse purge refers to accurately spraying nitrogen to the oxygen-enriched region, and the spraying process has a pulse characteristic. The spectral image is an image containing different spectral information, which is used to detect the condition of the headspace gas in the bottle. The oxygen molecule characteristic absorption waveband is a waveband in which oxygen molecules have an absorption phenomenon, and the oxygen condition can be analyzed through the waveband. The light intensity attenuation data is the data of the light intensity weakening caused by the oxygen absorption when the light passes through the headspace gas in the bottle. The current oxygen concentration value is the current oxygen concentration in the bottle calculated by analyzing the light intensity attenuation data. The preset oxygen concentration threshold value is a pre-set qualified oxygen concentration standard. The sealing control signal is triggered after the oxygen concentration reaches the predetermined standard, and is used to make the bottle enter the cap sealing process.

[0123] In the embodiment of the application, first, the supplementary purge parameters generated in step S104 are used as the basis to send a start control signal to the purge execution mechanism to drive the execution mechanism to start running. For example, when the parameters are a purge angle of 15 degrees, a gas flow intensity of 5, and a duration of 3 seconds, a start signal containing these parameters is sent to the execution mechanism.

[0124] Secondly, according to the blowing angle in the supplementary blowing parameter, the transmission structure is started to drive the nozzle to start rotating in step S1052, and the current azimuth angle of the nozzle is detected by the angle sensor during the rotation; when the angle sensor detects that the azimuth angle of the nozzle reaches the extracted blowing angle, the servo motor stops rotating, at this time the nozzle is just aimed at the spatial position where the oxygen-enriched region is located, for example, when the blowing angle is 15 degrees, the nozzle is rotated to 15 degrees right of the center axis of the bottle body by the adjusting assembly.

[0125] Then, the gas flow intensity and the blowing duration in the supplementary blowing parameter are extracted by step S1053, for example, the gas flow intensity is 6 and the duration is 3 seconds; the actuator adjusts the internal pressure regulating valve according to the gas flow intensity, adjusts the nitrogen output pressure to a value corresponding to the gas flow intensity, the greater the gas flow intensity, the greater the output pressure; then the timer of the actuator starts timing, and at the same time the nitrogen injection valve is opened, nitrogen is injected into the oxygen-enriched region at the adjusted pressure; when the injection time displayed by the timer reaches the extracted blowing duration, the nitrogen injection valve is closed, and the fixed-point pulse blowing operation is completed. For example, the gas flow intensity 5 corresponds to adjusting the pressure to a certain value, and the duration 3 seconds controls the injection for 3 seconds.

[0126] Then, after the fixed-point pulse blowing is completed, the spectral image of the processed headspace region in the bottle is collected by using the spectral collection device in step S1054, the image is processed, the light intensity attenuation data of the oxygen molecule characteristic absorption waveband is extracted, and the current oxygen concentration value is calculated by using the pre-established relationship model between the light intensity attenuation and the oxygen concentration.

[0127] Finally, the current oxygen concentration value is compared with the pre-set qualified oxygen concentration standard, i.e. the pre-set oxygen concentration threshold value in step S1055, if the current oxygen concentration value is less than or equal to the pre-set threshold value, it means that the oxygen concentration reaches the qualified standard, then the control system sends a sealing control signal to the cap sealing device; after receiving the control signal, the cap sealing device starts the working process, and the bottle cap is tightened on the current bottle body, so that the bottle body enters the cap sealing process.

[0128] In actual application, in the oral liquid filling workshop of A Pharmaceutical Factory, after the supplementary blowing parameters of a certain bottle body are determined, the control system generates a control signal and sends it to the blowing execution mechanism, and the blowing execution mechanism is started. According to the parameter of the blowing angle of 30°, the angle adjusting assembly drives the nozzle to rotate to 30° azimuth, so that the nozzle is aimed at the oxygen-enriched region. According to the gas flow intensity requirement, the nitrogen output pressure is adjusted, and at the same time, according to the parameter of the blowing duration of 5 seconds, the nitrogen injection is controlled for 5 seconds, and the fixed-point pulse blowing is completed. After the blowing is completed, the spectral collection device collects the spectral image of the headspace region in the bottle, extracts the light intensity attenuation data of the oxygen molecule characteristic absorption waveband, and calculates the current oxygen concentration value. The value is compared with the pre-set oxygen concentration threshold value, and it is found that the standard is reached, the sealing control signal is triggered, and the bottle body enters the cap sealing process.

[0129] The overall solution of S105 described above, through precise control of the purging actuator, can accurately inject nitrogen into the oxygen-enriched area, effectively reducing the oxygen concentration in the oxygen-enriched area by utilizing appropriate airflow intensity and purging time. The rapid verification and detection mechanism can promptly confirm whether the oxygen concentration inside the bottle meets the standard, ensuring that only bottles with the standard oxygen concentration enter the capping and sealing process, thereby improving product quality and stability, and guaranteeing the storage and quality of oral liquids in low-oxygen environments.

[0130] The following is a complete example for steps 101-105, such as Figure 3 As shown, in a midazolam oral solution aseptic filling line, after a bottle of oral solution completes nitrogen filling, the transmission imaging system integrated on the filling line is activated. The system includes a hyperspectral linear array camera and a specific band of LED array light source. The LED array light source sequentially illuminates three narrowband light-emitting units corresponding to the characteristic absorption band of oxygen molecules in a preset order. Each time a unit is illuminated, the hyperspectral linear array camera is simultaneously triggered to collect the transmitted light signal of the corresponding band of headspace gas inside the bottle and convert it into digital image data. Finally, the digital image data of the three bands are combined in spectral order to generate a multispectral image sequence containing information on the characteristic absorption band of oxygen.

[0131] Next, the generated multispectral image sequence is processed by a linear spectral separation algorithm to identify and extract the image data of the corresponding oxygen molecule characteristic absorption band. The light intensity value of each pixel is read point by point from the image data. Combined with the initial light intensity value of 100 stored in the system for that band, the light intensity attenuation of each pixel is calculated. For example, if the light intensity value of a certain pixel is 70, the attenuation is 30. Then, the position of each pixel is mapped one-to-one with the two-dimensional coordinates of the bottle mouth plane. All light intensity attenuation data are arranged in the order of coordinate distribution to generate a two-dimensional concentration map reflecting the oxygen distribution on the bottle mouth plane.

[0132] Subsequently, based on the light intensity attenuation data of each pixel in the two-dimensional concentration map, the local oxygen partial pressure value of each pixel is calculated, while the pre-stored geometric parameters of this type of oral liquid bottle are retrieved. A three-dimensional coordinate system is established with the bottle mouth plane as the XY plane, the bottle mouth center as (0,0,0), and the bottle height direction as the Z-axis. The headspace region is divided into 25 layered planes at 2mm intervals along the Z-axis. On each layered plane, according to the radial dimension variation law of the bottle body, the oxygen partial pressure value of the bottle mouth plane is mapped to the corresponding position of each layered plane using a bilinear interpolation algorithm to obtain the oxygen partial pressure value of the three-dimensional spatial grid node. All grid node data are collected, and a continuous three-dimensional oxygen concentration field is generated through a volume rendering algorithm. Finally, the oxygen concentration value of each node is compared with the preset oxygen concentration threshold point by point to identify the oxygen-rich areas with excessive oxygen concentration, and the spatial coordinate range, volume size, and maximum oxygen concentration deviation of the oxygen-rich areas are recorded.

[0133] Then the model reference adaptive controller loads the pre-stored ideal nitrogen cover model, extracts the characteristic points such as four uniformly distributed points on the bottle opening edge and the center of the bottle opening from the three-dimensional oxygen concentration field and the ideal model respectively, aligns the characteristic points of the two models by using a registration algorithm based on the characteristic points, and establishes an accurate coordinate correspondence; based on the correspondence, the measured oxygen concentration values at each position of the three-dimensional oxygen concentration field are compared with the target values at the corresponding positions of the ideal model, and the concentration difference values are calculated; according to the concentration difference value and the maximum oxygen concentration overage value, the airflow intensity is calculated, the basic airflow intensity is set to , the concentration difference value coefficient is a, the maximum oxygen concentration overage value coefficient is b, and the airflow intensity is +a×concentration difference value+b×maximum oxygen concentration overage value, the greater the two are, the greater the airflow intensity is; then the weight coefficient of the volume size is set to P, the weight coefficient of the concentration difference value is set to Q, the product of the volume size of the oxygen-enriched area and P is calculated, and the product of the concentration difference value and Q is added, and the weighted sum obtained is the blowing duration, and the three parameters are combined as the supplementary blowing parameters.

[0134] Finally, based on the supplementary blowing parameters, a control signal is sent to the blowing execution mechanism to drive the execution mechanism to start; the blowing angle is extracted from the signal, the nozzle is rotated to the direction by the servo motor of the angle adjusting assembly, the oxygen-enriched area is aligned, the airflow intensity and the blowing duration are extracted, the nitrogen output pressure is adjusted to the corresponding value, the nitrogen is sprayed for the blowing duration to complete the point pulse blowing; after blowing, the transmission imaging system is triggered to collect the headspace spectral image again, the current oxygen concentration value is obtained by repeating the light intensity decay calculation process; the current oxygen concentration value is compared with the preset oxygen concentration threshold value, and when the current oxygen concentration value is less than or equal to the preset oxygen concentration threshold value, a sealing control signal is triggered to make the bottle enter the cap sealing process.

[0135] Figure 4 A specific implementation structure schematic diagram of a midazolam oral liquid nitrogen-filled protection aseptic filling process control system provided by the embodiment of the application is provided, and the system can include Figure 4 , and the system can include

[0136] The acquisition module 41 is configured to acquire a sequence of multispectral images of headspace gas in a bottle before sealing by a transmission imaging system integrated on a filling line after nitrogen filling treatment of the midazolam oral liquid.

[0137] The processing module 42 is configured to perform spectral separation processing on the spectral image sequence, extract light intensity decay data of an oxygen molecule characteristic absorption band, and generate a two-dimensional concentration map reflecting oxygen distribution on a bottle opening plane based on the light intensity decay data.

[0138] The constructing module 43 is configured to calculate a local oxygen partial pressure value corresponding to each pixel point based on the two-dimensional concentration map, construct a three-dimensional oxygen concentration field of a headspace region in the bottle in combination with pre-stored bottle body geometric parameters of the midazolam oral liquid, and identify an oxygen-enriched region exceeding a preset oxygen concentration threshold based on the three-dimensional oxygen concentration field.

[0139] The generating module 44 is configured to perform spatial registration and comparison of the three-dimensional oxygen concentration field and an ideal nitrogen covering model by a model reference adaptive controller, generate a supplementary purging parameter for each bottle body based on a distribution feature of the oxygen-enriched region, and the supplementary purging parameter includes a purging angle, an airflow intensity, and a purging duration.

[0140] The driving module 45 is configured to drive a purging execution mechanism to control a nozzle direction according to the purging angle based on the supplementary purging parameter, perform a spot pulse purging on the oxygen-enriched region by using the purging duration and the airflow intensity, and perform a rapid verification detection on the processed headspace gas after the spot pulse purging, and enter a cap sealing procedure after confirming that the oxygen concentration reaches a predetermined standard.

[0141] The midazolam oral liquid nitrogen-filling protection sterile filling process control system of the embodiment is used to implement the foregoing midazolam oral liquid nitrogen-filling protection sterile filling process control method, and therefore the specific embodiments in the midazolam oral liquid nitrogen-filling protection sterile filling process control system can refer to the foregoing embodiment part of the midazolam oral liquid nitrogen-filling protection sterile filling process control method, and the specific embodiments can refer to the descriptions of the respective embodiment parts, which will not be described herein again.

[0142] The embodiment further provides an electronic device, which comprises a memory configured to store a computer program and a processor configured to execute the computer program to implement the steps of the foregoing any one of the midazolam oral liquid nitrogen-filling protection sterile filling process control methods.

[0143] The embodiment further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the foregoing any one of the midazolam oral liquid nitrogen-filling protection sterile filling process control methods.

[0144] In an exemplary embodiment, the foregoing computer readable storage medium can include but is not limited to a U disk, a read-only memory, a random access memory, a mobile hard disk, a magnetic disk or an optical disk, and various media that can store a computer program.

[0145] The embodiment further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the steps of the foregoing any one of the midazolam oral liquid nitrogen-filling protection sterile filling process control methods.

[0146] Those skilled in the art will further appreciate that the units and algorithms described in connection with the examples disclosed herein can be implemented in electronic hardware, computer software, or both. As described above, the order of execution of the examples' steps is generally consistent with the flowcharts illustrating the examples. As people of skill in the art will appreciate, the software can be machine code, firmware, embedded code, and / or software. The steps of the examples can be performed by hardware, software, or any combination of the two. The steps of the examples can be performed in an order different than presented in the flowcharts. The steps of the examples can be performed concurrently in different processing units. Software can be stored on a computer-readable medium, which can include random access memory (RAM), read-only memory (ROM), magnetic disk, optical disk, or any other volatile or non-volatile computer storage medium known in the art. A computer-readable medium can be a computer program product. The computer-readable medium can be a memory, a magnetic or optical disk, a memory chip, a disk drive, or any other suitable device known in the art. The disclosure encompasses all possible combinations of the examples' steps.

[0147] The above provides a kind of midazolam oral liquid nitrogen protection sterile filling process control method and system provided by the application.The principle and implementation mode of the present application are described in the specific examples in this paper.The above example is only used to help understand the method and its core idea of the present application.It should be pointed out that for the ordinary skilled in the art, without departing from the principle of the present application, some improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of the present application.

Claims

1. A method for controlling the aseptic filling process of midazolam oral solution under nitrogen protection, characterized in that, include: After nitrogen filling of midazolam oral solution, a multispectral image sequence of headspace gas inside the bottle before sealing was acquired by a transmission imaging system integrated into the filling line. The spectral image sequence is subjected to spectral separation processing to extract the light intensity attenuation data of the characteristic absorption band of oxygen molecules, and a two-dimensional concentration map reflecting the oxygen distribution in the bottle mouth plane is generated based on the light intensity attenuation data. Based on the two-dimensional concentration map, the local oxygen partial pressure value corresponding to each pixel is calculated. Combined with the pre-stored bottle geometry parameters corresponding to the midazolam oral solution, a three-dimensional oxygen concentration field of the headspace region inside the bottle is constructed. The oxygen-rich region with excessive concentration is identified according to the preset oxygen concentration threshold. The three-dimensional oxygen concentration field is spatially registered and compared with the ideal nitrogen coverage model by a model reference adaptive controller. Based on the distribution characteristics of the oxygen-rich area, supplementary purging parameters for each bottle are generated. The supplementary purging parameters include purging angle, airflow intensity and purging duration. Based on the supplementary purging parameters, the purging actuator controls the nozzle orientation according to the purging angle, and performs targeted pulse purging on the oxygen-rich area using the purging duration and airflow intensity. After targeted pulse purging, the treated headspace gas inside the bottle is quickly verified and tested. After confirming that the oxygen concentration reaches the predetermined standard, the bottle enters the capping and sealing process.

2. The method according to claim 1, characterized in that, The process involves spatially registering and comparing the three-dimensional oxygen concentration field with an ideal nitrogen coverage model using a model reference adaptive controller. Based on the distribution characteristics of the oxygen-rich region, supplementary purging parameters are generated for each bottle. These supplementary purging parameters include purging angle, airflow intensity, and purging duration. The model reference adaptive controller loads a pre-stored ideal nitrogen coverage model, which defines the target oxygen concentration value at each spatial location in the headspace region inside the bottle. The three-dimensional oxygen concentration field is spatially registered with the ideal nitrogen coverage model to establish a precise correspondence between the three-dimensional spatial coordinates of the two models. Based on the precise correspondence, the measured oxygen concentration values ​​at each location in the three-dimensional oxygen concentration field are compared with the target oxygen concentration values ​​at the corresponding locations in the ideal nitrogen coverage model to identify the concentration difference values. Based on the spatial coordinate range, volume, and maximum oxygen concentration deviation of the oxygen-rich region, supplementary purging parameters are generated for each bottle, combined with the concentration difference value.

3. The method according to claim 2, characterized in that, Based on the spatial coordinate range, volume, and maximum oxygen concentration deviation of the oxygen-rich region, combined with the concentration difference value, supplementary purging parameters are generated for each bottle, including: For each bottle, the azimuth angle of the spatial coordinate range of the oxygen-enriched area relative to the central axis of the bottle is used as the purging angle. The airflow intensity is determined based on the concentration difference value and the maximum oxygen concentration deviation value. The weighted sum of the volume of the oxygen-enriched area and the concentration difference value is used as the purging duration. The combination of the purging angle, airflow intensity, and purging duration is used as supplementary purging parameters for the corresponding bottle.

4. The method according to claim 1, characterized in that, The purging actuator, driven by the supplementary purging parameters, controls the nozzle orientation according to the purging angle, performs targeted pulse purging on the oxygen-rich area using the purging duration and airflow intensity, and after targeted pulse purging, performs rapid verification testing on the treated headspace gas inside the bottle. Once the oxygen concentration is confirmed to meet the predetermined standard, the bottle proceeds to the capping and sealing process, including: Based on the supplementary purging parameters, a control signal is sent to the purging actuator to drive the purging actuator to start operation; According to the purging angle in the supplementary purging parameters, the nozzle is rotated to the position corresponding to the purging angle by the angle adjustment component of the purging actuator, so that the nozzle is aligned with the spatial position of the oxygen-rich area. Adjust the nitrogen output pressure of the purging actuator according to the airflow intensity in the supplementary purging parameters, control the duration of nitrogen output according to the purging duration in the supplementary purging parameters, and inject nitrogen into the oxygen-rich area to complete the fixed-point pulse purging. After the fixed-point pulse purging is completed, the spectral image of the headspace region inside the bottle is acquired, the light intensity attenuation data of the characteristic absorption band of oxygen molecules is extracted, and the current oxygen concentration value is calculated. The current oxygen concentration value is compared with a preset oxygen concentration threshold. If the current oxygen concentration value reaches the preset oxygen concentration threshold, a sealing control signal is triggered to cause the bottle to enter the capping and sealing process.

5. The method according to claim 1, characterized in that, Based on the two-dimensional concentration map, the local oxygen partial pressure value corresponding to each pixel is calculated. A three-dimensional oxygen concentration field is constructed in the headspace region inside the bottle, combining this with the pre-stored bottle geometry parameters corresponding to the midazolam oral solution. Oxygen-rich areas exceeding the concentration limit are identified according to a preset oxygen concentration threshold, including: Based on the light intensity attenuation data of each pixel in the two-dimensional concentration map, the local oxygen partial pressure value corresponding to each pixel is calculated, and the pre-stored bottle geometry parameters of midazolam oral solution are obtained. Based on the local oxygen partial pressure value and the bottle body geometric parameters, a three-dimensional coordinate system is established with the bottle mouth plane as the reference, and the headspace region inside the bottle is divided into multiple layered planes at preset intervals along the height direction of the bottle body. On each layered plane, based on the variation law of the radial dimension of the bottle body, the oxygen partial pressure value of the bottle mouth plane is mapped to the corresponding position of each layered plane through the bilinear interpolation algorithm to obtain the oxygen partial pressure value of the three-dimensional spatial grid node; Based on the oxygen partial pressure values ​​of all three-dimensional spatial grid nodes, a continuous three-dimensional oxygen concentration field is generated using a three-dimensional data reconstruction algorithm. The oxygen concentration value of each node in the three-dimensional oxygen concentration field is compared with the preset oxygen concentration threshold point by point. The three-dimensional spatial regions where the oxygen concentration value exceeds the threshold are identified as oxygen-rich regions. The spatial coordinate range, volume, and maximum oxygen concentration deviation of each oxygen-rich region are recorded.

6. The method according to claim 1, characterized in that, After nitrogen filling of the midazolam oral solution, a multispectral image sequence of the headspace gas inside the bottle before sealing is acquired using a transmission imaging system integrated into the filling line, including: After nitrogen purging of midazolam oral solution, a transmission imaging system integrated on the filling line is activated. The transmission imaging system includes a hyperspectral linear array camera and a specific band of LED array light source. The LED array light source is controlled to sequentially illuminate the narrowband light-emitting units corresponding to the characteristic absorption bands of oxygen molecules in a preset order; The hyperspectral linear array camera is synchronously triggered to collect the transmitted light signal of the corresponding band of the head air gas inside the bottle when each narrowband light-emitting unit is lit, and convert the transmitted light signal into digital image data. The digital image data acquired in each band are combined in spectral band order to generate a multispectral image sequence containing information on the characteristic absorption bands of oxygen molecules.

7. The method according to claim 1, characterized in that, The step of performing spectral separation processing on the spectral image sequence to extract light intensity attenuation data of the characteristic absorption bands of oxygen molecules, and generating a two-dimensional concentration map reflecting the oxygen distribution at the bottle opening plane based on the light intensity attenuation data, includes: The multispectral image sequence is subjected to spectral separation processing to identify and extract digital image data corresponding to the characteristic absorption bands of oxygen molecules; The light intensity value of each pixel is obtained from the digital image data, and the attenuation of the light intensity value of each pixel relative to the initial light intensity value of the corresponding band is calculated to obtain the light intensity attenuation data of each pixel. The position of each pixel is mapped one-to-one with the two-dimensional coordinates of the bottle opening plane. The light intensity attenuation data corresponding to all the two-dimensional coordinates are arranged in the order of the coordinate distribution of the bottle opening plane to generate a two-dimensional concentration map reflecting the oxygen distribution of the bottle opening plane.

8. A nitrogen-filled aseptic filling process control system for midazolam oral solution, characterized in that, include: The acquisition module is used to acquire multispectral image sequences of headspace gas inside the bottle before sealing by a transmission imaging system integrated on the filling line after nitrogen filling of midazolam oral solution. The processing module is used to perform spectral separation processing on the spectral image sequence, extract the light intensity attenuation data of the characteristic absorption band of oxygen molecules, and generate a two-dimensional concentration map reflecting the oxygen distribution in the bottle mouth plane based on the light intensity attenuation data. The construction module is used to calculate the local oxygen partial pressure value corresponding to each pixel based on the two-dimensional concentration map, construct a three-dimensional oxygen concentration field in the headspace region inside the bottle by combining the pre-stored bottle geometry parameters corresponding to the midazolam oral solution, and identify the oxygen-rich areas with excessive concentration according to the preset oxygen concentration threshold. The generation module is used to spatially register and compare the three-dimensional oxygen concentration field with the ideal nitrogen coverage model through a model reference adaptive controller, and generate supplementary purging parameters for each bottle based on the distribution characteristics of the oxygen-rich area. The supplementary purging parameters include purging angle, airflow intensity and purging duration. The verification module is used to drive the purging actuator to control the nozzle orientation according to the purging angle based on the supplementary purging parameters, and to perform fixed-point pulse purging on the oxygen-rich area using the purging duration and airflow intensity. After the fixed-point pulse purging, the treated headspace gas in the bottle is quickly verified and tested. After confirming that the oxygen concentration reaches the predetermined standard, the bottle enters the capping and sealing process.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the aseptic filling process control method for nitrogen protection of midazolam oral solution as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, enables a method for controlling the aseptic filling process of midazolam oral solution under nitrogen protection as described in any one of claims 1 to 7.

Images