Method and system for continuously monitoring sterile environment based on RGB sensor

Abstract

The invention provides a method and system for continuously monitoring a sterile environment based on an RGB sensor. The system comprises an air sampling bottle, the RGB sensor, a temperature control device, a control unit and a vacuum system. A filter membrane and a microorganism growth sensor are arranged in the air sampling bottle, the RGB sensor detects the color change of the microorganism growth sensor, the temperature control device performs heating culture, the control unit analyzes data to judge whether the sterile environment is qualified, and the vacuum system exhausts air. The control unit comprises a plurality of modules, and the model training module uses a specific data set to train a long short term memory model. According to the invention, many problems of a traditional sterile environment monitoring method are solved, continuous monitoring and intelligent interpretation are realized, the monitoring efficiency and accuracy are improved, the cost is reduced, and a reliable guarantee is provided for sterile environment monitoring.

Description

Technical Field

[0001] The present invention relates to the field of sterile environment technology, and in particular to a method and system for continuously monitoring a sterile environment based on an RGB sensor. Background Art

[0002] In the production process of sterile drugs, especially when performing high-risk packaging operations such as filling, it is necessary to complete them in a highly clean and sterile environment. In order to reduce the risk of microbial contamination, these operations are usually carried out in closed equipment with the most stringent requirements, such as isolators. Monitoring the sterile environment in these closed equipment is a key requirement of the aseptic production process.

[0003] Existing sterile environment monitoring methods mainly include the use of portable air samplers. For example, Chinese patent CN113939372B discloses a packaging system that realizes the automation of culture dish replacement. Although this method reduces manual operation to a certain extent, there are still problems such as complex system, high investment cost, and large clean space occupation. In addition, it does not solve the problems of frequent replacement of culture dishes and taking out transfer culture, cumbersome operation, and long time for manual observation of culture results. Once the sterile environment is found to be unqualified, it is impossible to respond and check in time. In addition, there are also solutions to replace manual observation with AI cameras, but the overall performance requirements of the camera are relatively high, and it is necessary to perform interference processing on various image contents under the camera system, such as light changes, bubbles and other interference factors. More importantly, there are higher requirements for image clarity, more storage space is required, and the amount of calculation is also large. The overall configuration requirements are high, resulting in a more complex overall system structure and higher costs.

[0004] Therefore, there is an urgent need for a method and system for continuously monitoring a sterile environment based on an RGB sensor to solve the problems existing in the prior art. Summary of the invention

[0005] The embodiment of the present invention provides a method and system for continuously monitoring a sterile environment based on an RGB sensor, which addresses the problems of the current technology, such as high risk of manual operation, complex and high cost of the system, low recovery rate of microorganisms, untimely result feedback, complex structure and high cost.

[0006] The core technology of the present invention mainly utilizes air sampling bottles, RGB sensors, temperature control devices and control units to achieve continuous monitoring and automatic interpretation of sterile environments by monitoring the color changes of microbial growth sensors.

[0007] In a first aspect, the present invention provides a method for continuously monitoring a sterile environment based on an RGB sensor, the method comprising the following steps: An air sampling bottle is installed in a sterile environment device, wherein the air sampling bottle contains a liquid culture medium; The air in the closed clean space is continuously sucked into the air sampling bottle to mix the air with the liquid culture medium; Control the temperature of the liquid culture medium in the air sampling bottle to keep it at a suitable culture temperature; Use RGB sensor to continuously collect the color change signal of the microbial growth sensor at the bottom of the air sampling bottle; Transmitting the collected color change signal to a computer system; Use the control unit in the computer system to analyze the color change signal to determine whether the sterile environment is qualified; Among them, the control unit includes a data acquisition module, a data cleaning module, a feature extraction module, a model prediction and discrimination module and a model training module; The data acquisition module is used to obtain the collected color change signal as RGB data; the data cleaning module is used to filter the collected RGB data to reduce the impact of random noise; the feature extraction module converts the RGB value into the HSV color space, and calculates the color change rate to obtain the feature vector; the model prediction and discrimination module is used to output the discrimination result through the trained model; the model training module is used to use the feature vector as a data set to train the deep learning model so that it can accurately monitor and discriminate the sterile environment.

[0008] Furthermore, the data cleaning module processes the RGB data by moving average filtering and interpolation.

[0009] Furthermore, the model prediction discrimination module adopts the long short-term memory method as the discrimination model and outputs the discrimination result through the Sigmoid activation function.

[0010] Furthermore, the control unit also includes an outlier detection module and an outlier processing module. The outlier detection module is used to perform outlier detection on the RGB data after data cleaning. The outlier processing module uses linear interpolation to replace the detected outliers to ensure data continuity.

[0011] Furthermore, the outlier detection module performs outlier detection on the RGB data after data cleaning by using a sliding window detection method.

[0012] Furthermore, the collection interval of the RGB sensor is once per minute.

[0013] Furthermore, the model training steps of the control unit include: A dataset consisting of multiple feature matrices {xm_1, xm_2, xm_3, ..., xm_T} is used. The dataset is divided into a training set, a validation set, and a test set in a preset ratio. Among them, xm_1~xm_T are the final feature matrices obtained by combining feature vectors. Each set of data is normalized by subtracting the mean and dividing by the standard deviation; The long short-term memory method is used as the discriminant model, and the overall training process is controlled by three dimensions: batch size, number of training rounds, and validation set results; Use binary_crossentropy as the loss function to evaluate the error between the predicted label and the true label; During the training process, precision, accuracy, and recall are used to evaluate model performance; The precision, accuracy and recall are combined to draw the ROC curve and calculate the AUC value to assist in selecting the value basis for using Sigmoid for classification; Complete model training.

[0014] In a second aspect, the present invention provides a device for continuously monitoring a sterile environment based on an RGB sensor, comprising: The air sampling bottle comprises an air inlet pipe, a liquid culture medium, a filter membrane provided below the liquid culture medium, a microbial growth sensor provided at the bottom, and an air outlet pipe provided in the air sampling bottle, which is connected to a sterilizing filter; RGB sensor, located below the air sampling bottle, to detect the color change of the microbial growth sensor; A temperature control device, used for heating and culturing the air sampling bottle; A control unit, connected to the RGB sensor, equipped with the above-mentioned method for continuously monitoring a sterile environment based on the RGB sensor, for analyzing and interpreting data collected by the RGB sensor; The vacuum system is connected to the air inlet pipe of the air sampling bottle and is used to draw the gas in the sterile environment into the air sampling bottle.

[0015] Furthermore, the outlet pipe is provided with a contraction section, a narrow channel, a conical condensation wall and an inlet end, the narrow channel is located between the contraction section and the conical condensation wall, and the conical condensation wall is provided with an outlet hole. When bubbles emerge from the liquid culture medium, they pass through the inlet end, the contraction section, the narrow channel and the outlet hole in sequence.

[0016] Furthermore, a dehumidification filter is provided between the air outlet pipe and the sterilization filter.

[0017] The main contributions and innovations of the present invention are as follows: 1) Realize continuous monitoring and save consumables: The air sampling bottle replaces the culture dish and contains liquid culture medium, which solves the problem that the solid culture medium will affect the growth of microorganisms after losing water for a long time during sampling. Only one air sampling bottle is needed throughout the process, realizing continuous monitoring and saving consumables.

[0018] 2) High microbial recovery rate: There is a filter membrane under the liquid culture medium surface inside the air sampling bottle, which can intercept all microorganisms in the air under the filter membrane, and the microbial recovery rate can reach 100%.

[0019] 3) In-situ culture and automatic interpretation: A temperature control device is installed under the air sampling bottle, and in-situ culture can be directly realized after sampling. Culture and interpretation can be carried out simultaneously during the sampling stage. The color change of the microbial growth sensor is monitored in real time through the RGB sensor, and the artificial intelligence algorithm is used to automatically judge whether there is microbial growth in the liquid culture medium, determine whether the sterile environment is qualified, and automatically generate a test report.

[0020] 4) Timely output of results: Rapid sterility monitoring results are output in a timely manner, which is conducive to timely feedback of monitoring results by the experimenter. Once the sterile environment is unqualified, the polluted environment can be analyzed in time, and the drugs produced under unqualified conditions can be handled in time to reduce corporate losses. Using the rapid microbial detection method of the present invention, the results can be obtained in less than 8 hours at the fastest, which is much more efficient than the traditional method based on solid culture dishes in an incubator that takes 5 days or more.

[0021] 5) Intelligent and automated processing: Through specific system design and automatic analysis and interpretation by artificial intelligence algorithms, the intelligent and automated processing of culture results and culture reports is realized, which improves the accuracy of traditional culture dish detection results and reduces the errors and risks caused by manual operations. At the same time, compared with the use of image recognition, the use of RGB sensors can eliminate the interference processing of various image contents under the camera system and simplify the system structure and data processing process.

[0022] 6) Simplify data processing and reduce costs: The simplified data processing process significantly reduces the demand for system resources. Lower computing resource consumption means that it can be run on relatively low-configuration devices, reducing hardware requirements and thus reducing equipment costs. At the same time, smaller storage requirements also facilitate data management and storage, making it more suitable for some resource-limited application scenarios or cost-sensitive projects.

[0023] 7) Enhanced stability and adaptability: The detection method of microbial growth sensor combined with RGB sensor is more adaptable to environmental changes. RGB sensor directly monitors color changes and is relatively less affected by factors such as ambient light. As long as a certain range of light intensity is guaranteed, data can be obtained relatively stably. At the same time, color change-based detection is relatively easier to distinguish and identify color changes caused by different microbial growth. The system has better stability and adaptability and can accurately monitor sterile environments under a wider range of environmental conditions.

[0024] The details of one or more embodiments of the invention are set forth in the following drawings and description so that other features, objects, and advantages of the invention are more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 is a schematic structural diagram of a system for continuously monitoring a sterile environment based on an RGB sensor according to an embodiment of the present invention; Figure 2 It is a stereoscopic diagram of the continuous monitoring system of the sterile environment based on RGB sensors; Figure 3 It is a flow chart of the method for continuous monitoring of sterile environment based on RGB sensor; Figure 4 This is the structure diagram of the outlet pipe condensation of the continuous monitoring sterile environment system based on RGB sensor; Figure 5 This is a schematic diagram of the application of a dehumidification filter for continuous monitoring of a sterile environment system based on an RGB sensor.

[0026] In the figure, 1. air inlet; 2. air sampling bottle; 3. air inlet pipe; 4. sterilizing filter; 5. air outlet pipe; 6. liquid culture medium; 7. filter membrane; 8. temperature control device; 9. RGB sensor; 10. dehumidification filter; 11. vacuum system; 12. microbial growth sensor; 51. inlet end; 52. contraction section; 53. narrow channel; 54. conical condensation wall; 55. air outlet. DETAILED DESCRIPTION

[0027] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0028] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0029] Embodiment 1 The present invention aims to propose a method for continuously monitoring a sterile environment based on an RGB sensor. Specifically, referring to Figure 1-Figure 5 , the method includes.

[0030] Installing an air sampling bottle 2 in a sterile environment device, wherein the air sampling bottle 2 contains a liquid culture medium 6; The air in the closed clean space is continuously sucked into the air sampling bottle 2 using the vacuum system 11 to mix the air with the liquid culture medium 6; Use a temperature control device 8 to control the temperature of the liquid culture medium 6 in the air sampling bottle 2 to keep it at a suitable culture temperature; Using the RGB sensor 9 to continuously collect the color change signal of the microbial growth sensor 12 at the bottom of the air sampling bottle 2; Transmitting the collected color change signal to a computer system; Use the control unit in the computer system to analyze the color change signal to determine whether the sterile environment is qualified; Among them, the control unit includes a data acquisition module, a data cleaning module, a feature extraction module, a model prediction and discrimination module and a model training module; The data acquisition module is used to obtain the collected color change signal as RGB data; the data cleaning module is used to filter the collected RGB data to reduce the impact of random noise; the feature extraction module converts the RGB value into the HSV color space, and calculates the color change rate to obtain the feature vector; the model prediction and discrimination module is used to output the discrimination result through the trained model; the model training module is used to use the feature vector as a data set to train the deep learning model so that it can accurately monitor and discriminate the sterile environment.

[0031] In this embodiment, after the continuous production is completed, the system stops the vacuum system 11 from pumping air, and the operator caps the sampling bottle air inlet 1 onto the sampling bottle air inlet 1. During the culture process, the RGB sensor 9 monitors the microbial growth sensor 12 in real time, and the system uses an artificial intelligence algorithm to read the color change trend of the microbial growth sensor 12, and automatically reads whether there is microbial growth in the liquid culture medium 6. If there is microbial growth, the sterile environment is judged to be unqualified, and an alarm is issued to remind the operator to check the environmental pollution problem and intervene to suspend the production process. If there is no microbial growth, the sterile environment is judged to be qualified.

[0032] In this embodiment, compared with the solution using image recognition, the use of RGB sensor 9 can save the interference processing of various image contents under the camera system. In this system, the core function of the AI ​​algorithm is to monitor the color change of the microbial growth sensor 12 in real time through the RGB sensor 9, so as to determine whether there is microbial growth in the liquid culture medium 6, and then evaluate the cleanliness of the sterile environment. The specific implementation of the algorithm covers data collection, data cleaning, feature extraction, model prediction, discrimination and training. The specific steps are as follows: Step 1: Data collection stage. It usually takes a certain amount of time for the growth of microorganisms to cause detectable color changes. According to the growth rate and metabolic activity of microorganisms in the culture medium, and considering the data processing capacity and storage space of the system, a 1-minute collection interval can effectively capture the key changes in the growth process of microorganisms while avoiding excessive storage and computing burdens. In addition to providing sufficient information, high-frequency collection can also help AI models to make state judgments earlier. At this point, we can assume that the data is continuous, one-dimensional time series data. This step will output 3 sets of time series: r_t{r_1,r_2,r_3,...,r_T}g_t{g_1,g_2,g_3,...,g_T}b_t{b_1,b_2,b_3,...,b_T}.

[0033] Step 2: Data cleaning: RGB sensor 9 data may be affected by changes in ambient light, electrical noise, temperature, etc., resulting in noise and outliers in the data (although there is also an impact, the impact is significantly less than that of image recognition). These non-ideal data will have an adverse effect on model training and prediction. The acquired data can be processed by moving average filtering for noise reduction, specifically by calculating the average value of the data in a certain window before and after the current point to reduce the impact of random noise. Since the color change caused by microbial growth is a relatively slow process, a certain degree of signal smoothing is acceptable. Therefore, the size of the moving window will be selected based on 5 as the benchmark ([i-2, i-1, i, i+1, i+2]). The specific value will be adjusted in combination with the experiment.

[0034] Step 3: The detection method of timing anomalies can be detected through sliding windows: For each time point t, the mean μt and standard deviation σt of the data within the window are calculated, If |R_t−μt|>k×σt, it is judged as an outlier, and k is a preset constant. In a normal distribution, the probability that the data falls within the range of two times the standard deviation of the mean is about 95%, and the probability that it falls within the range of three times the standard deviation is about 99.7%. Therefore, choosing k=3 can effectively detect outliers under the condition of minimal misjudgment.

[0035] For detected outliers, directly removing them may cause discontinuity in the data, so we can use interpolation: linear interpolation to replace the outliers. At this point, we get three sets of cleaned values: r_tg_tb_t Step 4: Feature extraction: Although RGB readings can be directly used as feature input, RGB values ​​themselves are easily affected by light, so further processing is required to separate the light channel. In addition, microorganisms may experience changes in hue and saturation during rapid growth, so consider using color space conversion to convert RGB values ​​into HSV (Hue, Saturation, Value) color space as an additional feature. This color space controls color through hue and saturation, and uses the V channel to control brightness. At this time, the RGB three-color channels are no longer independent of each other due to color space conversion, which enhances data correlation. Since there is a time correlation between data, this feature can be captured by calculating the color change rate: For example, dR_t=R_t-R_{t-1} Through the above feature extraction steps, we will get 9 sets of feature vectors: r_tg_tb_t,h_ts_tv_t,dr_t,dg_t,db_t[9*k]. Combine the features to get the final feature matrix xm:{xm_1,xm_2,xm_3,...,xm_T} Step 5: Model prediction step: The AI ​​model will be used to analyze the input data and output the discrimination results. Considering that the input of this system is a sequence with continuous time association, the long short-term memory method (LSTM) is considered to be used as the discrimination model.

[0036] The advantage of LSTM is that it can process long sequence data and capture the long-term and short-term dependencies between sequences. The input of LSTM will be the feature sequence {xm_1, xm_2, xm_3, ..., xm_T} obtained in the previous step. Considering that the LSTM model has requirements for the size of a single unit input (the input must be a 1-dimensional vector). Therefore, it is necessary to further process the current 9*k feature dimension vector into 1 dimension. Therefore, a fully connected layer (DenseLayer) can be nested in the LSTM model to compress the 2-dimensional result through a nested small model. The output result of the LSTM model will be the hidden state of the last time step, and through the Sigmoid activation function, the Sigmoid function will output a value of 1 between 0 and 1, which can intuitively express the probability value in the binary classification problem, so it is very suitable for judging whether the sterile environment is qualified. This category probability will be used as the final indicator for judging the sterile environment. The specific discrimination threshold needs to be obtained in combination with the experiment, usually 90%. For the design of the model structure, LSTM allows custom addition of hidden units (HiddenUnit), that is, the number of computing neurons used in each intermediate step. Increasing this number can increase model performance at the cost of computational complexity. Considering the limited computing resources used by this platform, it is believed based on experience that selecting 32 as the number of units meets the requirements of this project.

[0037] The LSTM model training will be implemented using a dataset consisting of multiple feature matrices {xm_1, xm_2, xm_3, ..., xm_T}. The dataset will be divided into training set, validation set and test set in an 8:1:1 ratio. Each set of data is normalized by subtracting the mean and dividing by the standard deviation. The training process will be controlled by three dimensions: batch size, number of training rounds, and validation set results. Since it is a classification task, binary_crossentropy binary cross entropy will be used as the loss function to evaluate the error between the predicted label and the true label.

[0038] During the training process, the model performance will be evaluated using precision (Precision: the proportion of samples predicted as positive that are actually positive), accuracy (Accuracy: the proportion of samples predicted correctly to the total samples), and recall (Recal: the proportion of samples actually positive that are correctly predicted to be positive) . The above data are combined to draw the ROC curve to calculate the AUC value. The size of this value ([0,1]) directly reflects the model's ability to classify data pairs when different thresholds are selected, thereby helping us better select the value selection basis for using Sigmoid for classification in the previous step.

[0039] Embodiment 2 Based on the same concept, the present invention also proposes a continuous monitoring sterile environment system based on RGB sensor, comprising: The air sampling bottle 2 comprises an air inlet pipe 3, a liquid culture medium 6, a filter membrane 7 is provided below the liquid surface of the liquid culture medium 6, and a microbial growth sensor 12 is provided at the bottom. The air sampling bottle 2 is provided with an air outlet pipe 5, and the air outlet pipe 5 is connected to the sterilizing filter 4; The RGB sensor 9 is disposed below the air sampling bottle 2 and is used to detect the color change of the microbial growth sensor 12; The temperature control device 8 (which can be a combination of a heater and a cooler, and can accurately control the temperature through a temperature sensor) is used to heat and culture the air sampling bottle 2, and can heat the culture medium in the air sampling bottle 2 from room temperature to 37 degrees Celsius at most; The control unit (which may be a common PLC or working computer or MCU or other processing element) is connected to the RGB sensor 9 for communication, and is equipped with a method for continuously monitoring a sterile environment based on the RGB sensor 9 of the first embodiment, and is used to analyze and interpret the data collected by the RGB sensor; The vacuum system 11 is connected to the air inlet pipe 3 of the air sampling bottle 2 and is used to draw the gas in the sterile environment into the air sampling bottle 2. The vacuum system 11 here is a supporting device including a vacuum pump.

[0040] Among them, see Appendix Figure 4 , in order to prevent the sterilizing filter 4 from being wetted by humid gas and affecting the microbial barrier effect. The outlet pipe 5 is provided with a contraction section 52, a narrow passage 53, a conical condensation wall 54, and an air outlet 55. The conical condensation wall 54 is made of an easily condensable metal material. When bubbles emerge from the liquid culture medium 6, they pass through the inlet end 51 of the outlet pipe 5, the contraction section 52, the narrow passage 53 and the air outlet 55 of the outlet pipe 5 in sequence. When the gas flow channel changes from coarse to fine, the gas flow rate will accelerate rapidly. The liquid aerosol part in the gas will condense on the inside and outside of the conical condensation wall 54, and the condensed liquid will drip into the liquid culture medium 6 below, thereby drying the gas and preventing condensation at the sterilizing filter 4 from affecting the microbial barrier performance.

[0041] As a preference, Figure 5 A dehumidification filter 10 may be added between the air outlet pipe 5 and the sterilizing filter 4 to prevent the sterilizing filter 4 from being wetted by humid gas and affecting the microbial barrier effect.

[0042] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0043] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0044] Embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, at this point, it should be noted that, for example, Figure 3 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or storage blocks implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. Physical media are non-transitory media.

[0045] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0046] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. A method for continuously monitoring a sterile environment based on an RGB sensor, characterized in that: The following steps are involved: Installing an air sampling bottle in a sterile environment device, wherein the air sampling bottle contains a liquid culture medium; The air in the closed clean space is continuously sucked into the air sampling bottle to mix the air with the liquid culture medium; Control the temperature of the liquid culture medium in the air sampling bottle to keep it at a suitable culture temperature; Use RGB sensor to continuously collect the color change signal of the microbial growth sensor at the bottom of the air sampling bottle; Transmitting the collected color change signal to a computer system; Use the control unit in the computer system to analyze the color change signal to determine whether the sterile environment is qualified; Wherein, the control unit includes a data acquisition module, a data cleaning module, a feature extraction module, a model prediction and discrimination module and a model training module; The data acquisition module is used to obtain the collected color change signal as RGB data; the data cleaning module is used to filter the collected RGB data to reduce the influence of random noise; The feature extraction module is used to convert the RGB value into the HSV color space and calculate the color change rate to obtain the feature vector; the model prediction and discrimination module is used to output the discrimination result through the trained model; the model training module is used to use the feature vector as a data set to train the deep learning model so that it can accurately monitor and discriminate the sterile environment.

2. A method for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 1, characterized in that: The data cleaning module processes the RGB data by moving average filtering and interpolation.

3. A method for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 1, characterized in that: The model prediction and discrimination module adopts the long short-term memory method as the discrimination model and outputs the discrimination result through the Sigmoid activation function.

4. A method for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 1, characterized in that: The control unit also includes an outlier detection module and an outlier processing module. The outlier detection module is used to perform outlier detection on the RGB data after data cleaning. The outlier processing module uses linear interpolation to replace the detected outliers to ensure data continuity.

5. A method for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 4, characterized in that: The outlier detection module performs outlier detection on the RGB data after data cleaning by using a sliding window detection method.

6. A method for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 1, characterized in that: The collection interval of the RGB sensor is once per minute.

7. A method for continuously monitoring a sterile environment based on an RGB sensor as described in any one of claims 1 to 6, characterized in that: The model training step of the control unit includes: A data set consisting of multiple sets of feature matrices {xm_1, xm_2, xm_3, ..., xm_T} is used, and the data set is divided into a training set, a validation set, and a test set in a preset ratio; wherein xm_1~xm_T are feature vectors combined to obtain the final feature matrix; Each set of data is normalized by subtracting the mean and dividing by the standard deviation; The long short-term memory method is used as the discriminant model, and the overall training process is controlled by three dimensions: batch size, number of training rounds, and validation set results; Use binary_crossentropy as the loss function to evaluate the error between the predicted label and the true label; During the training process, precision, accuracy, and recall are used to evaluate model performance; The precision, accuracy and recall are combined to draw the ROC curve and calculate the AUC value to assist in selecting the value basis for using Sigmoid for classification; Complete model training.

8. A continuous monitoring system for sterile environment based on RGB sensor, characterized in that: include: The air sampling bottle comprises an air inlet pipe, a liquid culture medium, a filter membrane is provided below the liquid surface of the liquid culture medium, a microbial growth sensor is provided at the bottom, and the air sampling bottle is provided with an air outlet pipe, and the air outlet pipe is connected to a sterilizing filter; an RGB sensor, disposed below the air sampling bottle, for detecting a color change of the microbial growth sensor; A temperature control device, used for heating and culturing the air sampling bottle; A control unit, connected to the RGB sensor, equipped with a method for continuously monitoring a sterile environment based on an RGB sensor according to any one of claims 1 to 7, and used for analyzing and interpreting data collected by the RGB sensor; The vacuum system is connected to the air inlet pipe of the air sampling bottle and is used to draw the gas in the sterile environment into the air sampling bottle.

9. A system for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 8, characterized in that: The air outlet pipe is provided with a contraction section, a narrow passage, a conical condensation wall and an inlet end. The narrow passage is located between the contraction section and the conical condensation wall. The conical condensation wall is provided with an air outlet. When bubbles emerge from the liquid culture medium, they pass through the inlet end, the contraction section, the narrow passage and the air outlet in sequence.

10. A system for continuously monitoring a sterile environment based on an RGB sensor as claimed in claim 8, characterized in that: A dehumidification filter is provided between the air outlet pipe and the sterilization filter.

Images