Method and system for optimizing temperature and pressure curve of medical high-pressure steam sterilizer

Abstract

The invention relates to the technical field of high-pressure steam sterilizers, in particular to a medical high-pressure steam sterilizer temperature and pressure curve optimization method and system. The method comprises the following steps: acquiring bacterial characteristic data and environmental parameters by adopting a sensor, and generating an original data sequence; performing data cleaning and standardization processing on the original data sequence to form a high-quality data set; based on the high-quality data set, a deep learning algorithm is utilized to train a sterilization process model, and temperature, pressure and time optimization curves suitable for different strains are generated; inputting the optimized curve into a real-time control system, and adjusting operation parameters of the high-pressure steam sterilizer; and dynamically adjusting the operation parameters according to the equipment operation data in the sterilization process, and generating a sterilization effect evaluation report. Through a deep learning algorithm and a real-time feedback mechanism, dynamic optimization of the sterilization process is realized, meanwhile, energy consumption is reduced, and the method has the beneficial effects of high sterilization efficiency, energy conservation, environmental protection, high adaptive capacity and the like.

Description

Technical Field

[0001] The invention relates to the technical field of high-pressure steam sterilizers, and in particular to a method and system for optimizing a temperature and pressure curve of a medical high-pressure steam sterilizer. Background Art

[0002] In the sterilization process of medical equipment, high-pressure steam sterilizer is one of the most commonly used sterilization equipment, which mainly kills various pathogens on the surface and inside the equipment through a high-temperature and high-pressure steam environment. However, in the prior art, high-pressure steam sterilizers generally use fixed temperature, pressure and time parameters for sterilization, and cannot be accurately adjusted according to the heat resistance and sterilization requirements of different strains of bacteria. This fixed parameter sterilization method may lead to incomplete sterilization effect, and cannot meet the needs of killing multiple strains of bacteria in complex medical scenarios. At the same time, it may cause unnecessary energy waste due to excessive heating.

[0003] With the development of medical technology and the improvement of hospital infection prevention and control standards, higher requirements are placed on sterilizers: on the one hand, it is necessary to ensure the effective killing of multiple drug-resistant bacteria by precisely controlling temperature, pressure and time parameters; on the other hand, it is necessary to optimize energy use and reduce sterilization costs and equipment energy consumption. Therefore, how to generate dynamic sterilization curves based on real-time collected bacterial characteristic data and environmental parameters using intelligent algorithms and achieve precise control through real-time feedback has become a core issue that needs to be solved in current technology. Summary of the invention

[0004] The present invention provides a method and system for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer, so as to solve the problem of how to generate dynamic temperature, pressure and time optimization curves through a deep learning algorithm based on bacterial characteristic data, environmental parameters and equipment operation data in the medical device, and adjust the operating parameters of the high-pressure steam sterilizer in real time to ensure the effective killing of different bacteria species and optimize energy utilization efficiency.

[0005] In order to solve the above technical problems, the present invention provides a method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer, comprising:

[0006] Using sensors to obtain bacterial characteristic data and environmental parameters to generate raw data sequences;

[0007] Performing data cleaning and standardization processing on the original data sequence to generate a high-quality data set;

[0008] Based on the high-quality data set, a deep learning algorithm is used to train a sterilization process model to generate temperature, pressure and time optimization curves suitable for different strains of bacteria;

[0009] Inputting the optimization curve into a real-time control system to adjust the operating parameters of the high-pressure steam sterilizer;

[0010] During the sterilization process, dynamic adjustments are made based on the equipment operation data, and a sterilization effect evaluation report is generated.

[0011] Furthermore, the step of obtaining bacterial characteristic data and environmental parameters includes:

[0012] The types, quantity and population density of bacteria are collected through sensors;

[0013] Obtain environmental parameters, including initial temperature, initial humidity and initial pressure;

[0014] The bacterial data and environmental parameters are integrated to form a complete raw data sequence.

[0015] Furthermore, the steps of data cleaning and standardization processing include:

[0016] removing noise and outliers from the raw data sequence;

[0017] Standardizing the data to convert data of different dimensions into a unified standard;

[0018] Generate datasets suitable for deep learning model training.

[0019] Furthermore, the step of training the sterilization process model includes:

[0020] Extracting key features from the data set, including strain type, strain heat resistance, and environmental characteristics;

[0021] Based on the extracted features, a sterilization process model is trained using a deep learning algorithm;

[0022] The optimized curves of temperature, pressure and time suitable for different strains of bacteria were obtained.

[0023] Furthermore, the deep learning algorithm includes a convolutional neural network and / or a long short-term memory network, the input of the sterilization process model is the characteristics of the bacterial strain and the environmental characteristics, and the output is an optimized temperature, pressure and time curve.

[0024] Furthermore, the step of inputting the optimization curve into the real-time control system includes:

[0025] The generated temperature, pressure and time optimization curves are input into the real-time control system of the high-pressure steam sterilizer;

[0026] The operating parameters of the sterilizer are initialized according to the optimization curve, including initial temperature, initial pressure and initial time.

[0027] Furthermore, the real-time control system comprises:

[0028] A sensor module that collects equipment operation data;

[0029] an execution module for adjusting the operating parameters of the device;

[0030] A processing module that updates the optimization curve based on device feedback data.

[0031] Furthermore, the step of dynamic adjustment includes:

[0032] Monitor the sterilizer operating status in real time and obtain equipment operating data, including temperature, pressure and humidity;

[0033] adjusting operating parameters according to the deviation between the equipment operation data and the optimization curve;

[0034] Through the feedback closed-loop mechanism, the optimization curve is dynamically updated and the equipment operation is adjusted.

[0035] Furthermore, the step of dynamic adjustment also includes:

[0036] Calculate the deviation between the actual sterilization effect and the target value and correct the operating parameters;

[0037] The corrected parameters are input into the real-time control system to update the equipment operating status.

[0038] Furthermore, a medical high-pressure steam sterilizer temperature and pressure curve optimization system is provided, the system comprising:

[0039] Data acquisition module, used to collect bacterial characteristic data, environmental parameters and equipment operation data through high-precision sensors;

[0040] A data processing module, used to clean and standardize the data and extract key features;

[0041] A deep learning modeling module for training the sterilization process model based on the processed data to generate temperature, pressure and time optimization curves;

[0042] A real-time control and feedback module, used to input the optimization curve into the equipment control system and adjust the operating parameters;

[0043] The data analysis and evaluation module is used to analyze equipment operation data, generate sterilization effect evaluation reports and provide optimization suggestions.

[0044] The following are its main beneficial effects:

[0045] (1) Dynamically adapt to the needs of killing multiple strains of bacteria. Based on bacterial characteristic data and environmental parameters, the present invention generates optimization curves adapted to different strains through a deep learning model, and can accurately adjust the operating parameters of the sterilizer. Compared with the traditional fixed parameter method, it can effectively kill strains with different heat resistance and pressure resistance, avoiding the problem of incomplete sterilization.

[0046] (2) Improve the accuracy and efficiency of the sterilization process. The present invention realizes closed-loop optimization control by real-time monitoring of equipment operation data and dynamic adjustment based on feedback. The optimized curve can accurately match the operating status of the equipment, reduce temperature or pressure deviation during the sterilization process, and improve the accuracy and efficiency of sterilization.

[0047] (3) By adopting a method of real-time adjustment and optimization of energy consumption, the energy consumption data of equipment operation is analyzed, and the heating and pressurization process is dynamically controlled, thereby reducing energy waste during the sterilization process. Compared with traditional methods, the present invention can significantly improve the energy utilization efficiency of sterilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic flow chart of a method for optimizing a temperature and pressure curve of a medical high-pressure steam sterilizer provided in an embodiment of the present application;

[0049] Figure 2 A structural block diagram of a temperature and pressure curve optimization system for a medical high-pressure steam sterilizer provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0051] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] Example 1: Reference Figure 1 , is a schematic flow chart of a method for optimizing a temperature and pressure curve of a medical high-pressure steam sterilizer provided by an embodiment of the present invention. The process may at least include steps S100-S500:

[0053] S100, using sensors to obtain bacterial characteristic data and environmental parameters to generate a raw data sequence.

[0054] S200: performing data cleaning and standardization processing on the original data sequence to generate a high-quality data set.

[0055] S300: Based on the high-quality data set, a deep learning algorithm is used to train a sterilization process model to generate temperature, pressure and time optimization curves suitable for different bacterial species.

[0056] S400, inputting the optimization curve into a real-time control system to adjust operating parameters of the high-pressure steam sterilizer.

[0057] S500, during the sterilization process, dynamic adjustments are made based on the equipment operation data, and a sterilization effect evaluation report is generated.

[0058] Step S100 at least includes steps S110-S130:

[0059] S110, obtaining the bacteria type and quantity data collected by the internal sensor of the medical device, and collecting environmental parameters at the same time, to obtain a complete original data sequence.

[0060] First, based on the data collected by the sensors inside the medical device, the types, quantity and growth of bacteria in the environment are obtained. The data is measured in real time by high-precision sensors, recording the density, type (such as the class and genus name of the bacteria), and the number of bacteria at the current stage. The sensor data is input into the system in the form of a data stream.

[0061] Set the data output by the sensor to D bacteria ={b1,b2,…,b n}, where b i represents the number or density of the i-th bacteria, n represents the number of bacterial species, D bacteria The distribution and quantity characteristics of bacteria in the environment are the core input data for optimizing sterilization parameters. Bacterial species are represented by classification codes, and each type of bacteria has its own specific identifier.

[0062] At the same time, the sensors inside the equipment will also collect environmental parameter data, such as temperature, humidity, pressure, etc. The environmental factors have a greater impact on the sterilization process. Set the environmental data to D env ={T,H,P}, where T represents temperature, H represents humidity, and P represents pressure. Through the real-time monitoring system, the data is collected into the system and together with the bacteria data, a complete raw data sequence is formed. That is:

[0063] D raw ={D bacteria ,D env}={b1,b2,…,b n ,T,H,P};

[0064] All bacterial data and environmental data are integrated into a raw data sequence D raw , this sequence contains various types of input data as the basis for subsequent processing. This data sequence will be passed to the next step of data preprocessing.

[0065] S120, removing noise and outliers from the original data, standardizing the data, and obtaining a high-quality data set suitable for deep learning model training.

[0066] From the original data sequence D raw In the process of noise and outliers detection and elimination, we firstly perform noise and outliers detection and elimination. In order to improve the data quality, we use appropriate algorithms (such as mean deviation method, Z-score standardization, etc.) to remove outliers that are beyond the normal range. bacteria If some values ​​are significantly higher or lower than the normal range, they are marked as outliers and removed. env ,If the temperature, humidity and pressure values ​​exceed the set threshold range, they are considered abnormal and ,corrected or eliminated.

[0067] For data X, by calculating its standard deviation σ X and mean μ X , use the Z-score method to filter out outliers:

[0068]

[0069] Set the threshold to Z X >3 or Z X When <-3, the data are considered abnormal.

[0070] After removing outliers, the data is standardized. Standardization is to convert data of different dimensions into a unified standard so that it can be input into the deep learning model. Specifically, for the bacterial count data b i , temperature data T, humidity data H and pressure data P are standardized by subtracting the mean from the data and dividing by the standard deviation:

[0071]

[0072] Among them, μ X is the mean of each data dimension, σ X is the standard deviation, b' i is the standardized bacterial data, and T', H', and P' are the standardized environmental parameter data.

[0073] Through the above processing, we get a high-quality data set after denoising and standardization, denoted as D cleaned ={b'1,b'2,…,b' n,T',H',P'}, this dataset can be used as input data for subsequent deep learning model training.

[0074] S130: extract key features from the high-quality data and annotate them to obtain a feature data set for deep learning model training.

[0075] From the standardized high-quality dataset D cleaned In the above example, the key features that are highly related to the sterilization process are extracted. For the bacterial data b' i , characteristics can be extracted according to the growth rules of different bacterial species, such as bacterial species type (classification data), changing trend of bacterial quantity, high temperature resistance of bacterial species, etc.; for environmental data T′, H′, P′, the influence characteristics of temperature and humidity changes on the sterilization process can be extracted.

[0076] Specifically, for temperature and humidity data, the sliding window method is used to calculate its statistical characteristics such as mean, standard deviation and maximum value, and the temperature and humidity change characteristics f are obtained. T ,f H For bacterial data, time series features can be extracted through changes in bacterial density and species variation. b :

[0077] f T =mean(T′),f H =std(H),f b =trend(b′ i );

[0078] Among them, mean represents the calculated mean, std represents the standard deviation, and trend represents the time series trend analysis.

[0079] The extracted feature data is annotated, and the annotated information includes the sterilization curves and environmental parameter ranges corresponding to different strains. Based on historical sterilization experimental data and combined with known bacterial sterilization standards, the labels of each sample data are annotated, such as the sterilization effects corresponding to different sterilization temperatures, pressures, and times. The annotated data will become an important basis for subsequent deep learning model training.

[0080] After feature extraction and annotation, the feature dataset D for deep learning model training is obtained. features ={f b ,f T ,f H ,f P}, the dataset contains characteristic information of bacterial species, environmental changes, and sterilization effects, and is ready to be passed to the next model training stage.

[0081] Step S200 at least includes steps S210-S230:

[0082] S210. Based on the cleaned and preprocessed data set and the extracted features thereof, a deep learning algorithm is used to train a sterilization process model to obtain a preliminary model of temperature, pressure and time optimization curves that can adapt to different bacterial species.

[0083] In this step, based on the aforementioned high-quality dataset D cleaned ={b'1,b'2,…,b' n ,T',H',P'}, and the key features D extracted from the data features ={f b ,f T ,f H ,f P}, trained by deep learning algorithms (such as convolutional neural networks, long short-term memory networks, etc.). The model is designed to generate temperature, pressure and time optimization curves that can adapt to different strains.

[0084] Specifically, the input data D features This will be input as a training data set into the deep learning model, which will learn the nonlinear relationship between bacterial strain characteristics and environmental parameters to optimize the temperature, pressure, and time during the sterilization process.

[0085] Assume that the deep learning model is f model , the input of the model is f model (f b ,f T ,f H ,f P ), the output is the corresponding temperature, pressure and time curve parameters, denoted as T opt ,P opt ,τ opt , respectively represent the optimized temperature, pressure and time curves.

[0086] {T opt ,P opt ,τ opt} = f model (f b ,f T ,f H ,f P );

[0087] Get the initially trained model: After completing the training of the deep learning algorithm, the generated model is the initially trained sterilization process model The model can predict the appropriate sterilization temperature, pressure and time curve based on the characteristic data of different bacterial species.

[0088] Model evaluation and validation: During the training process, the preliminary model is evaluated using the validation data set to ensure that the model can produce reasonable temperature, pressure, and time curves to meet the requirements of different sterilization conditions.

[0089] S220. Based on the deep learning model obtained by the preliminary training, tuning is performed to optimize its parameters and architecture to obtain an optimized deep learning model.

[0090] Parameter optimization: After obtaining the initially trained model, further optimize the model parameters. The goal of optimization is to reduce the training error and improve the generalization ability of the model on new data. The model performance can be improved by adjusting the model's hyperparameters, such as learning rate, number of layers, number of nodes, etc., and using optimization algorithms such as Adam and RMSprop.

[0091] Assume that the optimized model is The key to the optimization process is to optimize the weight and bias parameters w through the back propagation algorithm and gradient descent method. i and b i , to minimize the loss function L(f model ), the loss function is defined as the error measure between the model output and the actual target (i.e., the sterilization effect curve):

[0092]

[0093] Among them, y i is the target value, x i is the input feature, is the optimized deep learning model, and L is the loss function, which represents the error between the model output and the target.

[0094] Model architecture optimization: According to the performance of the deep learning model, adjust the model architecture (such as increasing or decreasing the number of network layers, changing the activation function, etc.) to ensure that the model can better adapt to the characteristics of different types of bacteria and environmental changes.

[0095] Furthermore, the optimized architecture was evaluated using a validation dataset to ensure that it could generate sterilization curves more accurately and achieve the intended goals.

[0096] Get the optimized deep learning model: After the optimization process, get the optimized deep learning model This model can predict more accurate temperature, pressure and time curves during the sterilization process based on different bacterial species and environmental characteristics.

[0097] S230, inputting different bacterial strain data into the optimized model, verifying the output effect of the model, and evaluating its performance and reliability under different sterilization conditions.

[0098] Input data from different strains for model prediction: Input data from different strains into the optimized deep learning model The input data includes the characteristic data of different strains. b ,f T ,f H ,f P The model will output different temperature, pressure and time curves based on the characteristics. The curves will be provided to the equipment system as the optimized parameters in the sterilization process.

[0099]

[0100] Verify the effect of model output: Compare the temperature, pressure and time curves output by the model with the results of the actual sterilization experiment to verify whether the output effect meets expectations. Specifically, compare the differences between the curves predicted by the model and the experimental data to evaluate the adaptability and accuracy of the model under different strains and sterilization conditions.

[0101] Experimental data of different bacterial species were used for verification to ensure that the model could generate a reasonable sterilization curve for each bacterial species and that the sterilization process could completely kill all bacteria.

[0102] Evaluate the reliability of the model: Comprehensively evaluate the reliability of the model, especially its performance under different sterilization conditions, such as the impact of environmental changes such as temperature and pressure on the sterilization effect. Through multiple verifications, ensure the stability and accuracy of the model, and evaluate its applicability and generalization ability.

[0103] Model evaluation formula:

[0104]

[0105] Among them, y i is the actual sterilization result, x i To input feature data, is the optimized model, Error is the prediction error, and N is the number of validation samples.

[0106] Step S300 at least includes steps S310-S330:

[0107] S310. According to the optimized deep learning model, characteristic data of different types of bacteria are input to obtain temperature, pressure and time curves suitable for the bacteria.

[0108] Input characteristic data of different strains: According to the optimized deep learning model Input the feature data of different types of bacteria. Specifically, the input data includes the key features f extracted from the previous step b ,f T ,fH ,f P ,in:

[0109] f b Characteristics indicating bacterial species, bacterial numbers, or density;

[0110] f T Indicates temperature-related characteristics (such as average temperature, temperature fluctuation, etc.);

[0111] f H Indicates humidity related features;

[0112] f P Indicates pressure-related characteristics.

[0113] Input data f b ,f T ,f H ,f P The optimized model Calculate and generate the adaptation temperature, pressure and time curve required for the strain in:

[0114] To adapt to the optimized temperature curve of this strain;

[0115] To adapt to the optimized pressure curve of this strain;

[0116] To adapt to the optimized time curve of this strain.

[0117]

[0118] Generate a temperature, pressure, and time curve suitable for the strain: Through the output results of the deep learning model, the temperature, pressure, and time optimization curve required for each strain is obtained. The curve will be used in the control system in the subsequent sterilization process to ensure that the sterilization process can be accurately executed and achieve the desired effect.

[0119] S320: Based on the input data, calculate and generate temperature, pressure and time optimization curves suitable for the sterilization process of different bacteria species.

[0120] Calculate based on the input bacterial species characteristic data: Further, the input different bacterial species characteristic data f b ,f T ,f H ,f P Perform in-depth calculations to generate temperature, pressure, and time optimization curves for each strain. The characteristic data of each bacterial species will correspond to a unique sterilization curve. The output obtained through the calculation is the optimized parameters of each bacterial species, specifically:

[0121] An optimized temperature curve generated based on input data;

[0122] is an optimized pressure curve generated based on the input data;

[0123] is the optimization time curve generated based on the input data.

[0124] Calculate the optimized curve: Use mathematical formulas to calculate the sterilization curve suitable for each strain. This calculation combines strain characteristics with environmental parameters such as temperature and humidity to ensure that the generated sterilization curve can cope with different strains and provide accurate sterilization effects. The formula calculation here will use the previously obtained optimized parameters and characteristic data:

[0125]

[0126] The optimization curve will be transmitted to the real-time control system for execution.

[0127] Generate an optimization curve for the sterilization process: Integrate it into the operating system of the sterilization process to ensure that the temperature, pressure and time can be adjusted in real time according to the needs of different bacteria species during the sterilization process.

[0128] S330, fine-tuning the generated sterilization curve according to the real-time environmental feedback information.

[0129] Obtain real-time environmental feedback information: During the actual sterilization process, obtain real-time environmental feedback information, such as parameters such as temperature, pressure and humidity inside the equipment. Use sensors to monitor the operating status of the sterilizer in real time and collect real-time data about the sterilization process. The feedback information includes but is not limited to:

[0130] T env The temperature inside the device is measured in real time;

[0131] P env It is the pressure inside the equipment measured in real time;

[0132] H env Real-time measurement of humidity.

[0133] This real-time feedback serves as a dynamic input for fine-tuning previously generated sterilization profiles.

[0134] Fine-tuning the sterilization curve: based on real-time feedback information env ,P env ,Henv , adjust the previously generated sterilization curve. Specifically, if the temperature, pressure or humidity in the equipment deviates from the preset range, the system will adjust the temperature based on the feedback information. pressure and time value to ensure that the sterilization process is still carried out under optimized conditions.

[0135] For example, if the temperature T measured at a certain time env If the temperature exceeds the preset value, the system will adjust the temperature curve To compensate for temperature changes.

[0136] Update and generate a new sterilization curve: Finally, the system will regenerate and update the sterilization curve according to the real-time adjusted parameters, so that the sterilization process can adapt to real-time environmental changes at every moment, ensuring the consistency and reliability of the sterilization effect. Adjusted curve It will be input into the real-time control system of the equipment to ensure the precise execution of the sterilization process.

[0137] Step S400 at least includes steps S410-S430:

[0138] S410, inputting the temperature, pressure and time curves generated in the S300 module into the real-time control system of the high-pressure steam sterilizer to adjust the equipment operating parameters.

[0139] Input optimization curve into real-time control system: Optimized temperature, pressure and time curve generated by the S300 module The optimized parameters are input into the real-time control system of the high-pressure steam sterilizer. Specifically, the optimization curve provides the key control parameters in the sterilization process, which correspond to the set temperature T when the sterilizer is running. set 、Pressure P set and duration τ set ,Right now:

[0140]

[0141] Equipment parameter initialization: The real-time control system initializes the equipment operating parameters according to the input optimization curve, sets the initial temperature, pressure and sterilization time of the high-pressure steam sterilizer, and enables the corresponding control algorithm to ensure that the equipment operates according to the optimization curve.

[0142] Parameter transfer connection: Each point in the optimization curve is used as the dynamic input of the equipment to ensure that the sterilizer can accurately perform temperature and pressure adjustments at each time point and keep pace with the sterilization time. Throughout the process, the real-time control system continuously obtains the current target parameters from the curve to control the operation of the sterilizer.

[0143] S420. During the sterilization process, monitor the equipment status of the high-pressure steam sterilizer in real time and provide feedback on the equipment operation status.

[0144] Real-time monitoring of equipment status: During the sterilization process, the built-in sensors and monitoring system of the equipment are used to collect the operating status parameters of the sterilizer in real time, including the actual temperature T actual , actual pressure P actual , Steam flow F actual Etc. The collected data forms a real-time feedback sequence:

[0145] D feedback ={T actual ,P actual ,F actual}

[0146] Compare the set value with the actual value: feedback and the target parameter T in the optimization curve set ,P set ,τ set Real-time comparisons are made and deviations are calculated to assess the accuracy of equipment operation.

[0147] Assume that the deviation is calculated as:

[0148] ΔT=T actual -T set ,ΔP=P actual -P set ;

[0149] Where ΔT and ΔP are the deviations of temperature and pressure, respectively.

[0150] Feedback data recording: All feedback data and their corresponding time points are recorded during real-time monitoring to form a time series for subsequent dynamic adjustment steps. The data will be analyzed in real time and dynamically adjusted through the control system.

[0151] S430: Dynamically adjust the operating parameters of the equipment according to the real-time feedback data.

[0152] Analyze real-time feedback data: Based on the feedback data collected by S420 module D feedback The deviations ΔT and ΔP from the target values ​​of the optimization curve are used to analyze the operating status of the equipment. If the deviation exceeds the set threshold, the operating parameters of the equipment need to be adjusted to make the actual operating status close to the target value of the optimization curve.

[0153] Assume the adjustment formula is:

[0154] T adjust =T set -k T ·ΔT,Padjust =P set -k P ΔP;

[0155] Among them, k T and k P is the adjustment factor for temperature and pressure, T adjust and P adjust are the adjusted temperature and pressure set points, respectively.

[0156] Dynamically adjust equipment parameters: adjust the temperature T adjust and pressure P adjust Input into the real-time control system to update the equipment's operating parameters, ensuring that the equipment can follow the optimization curve in real time. The dynamically adjusted parameter sequence is continuously updated over time.

[0157] Feedback closed-loop control: After the adjustment is completed, the operating status parameters D of the equipment are collected again feedback , and repeatedly compare the deviation from the target value of the optimization curve to form a closed-loop control process. This iterative adjustment ensures that the actual operation of the sterilizer is always close to the optimization curve.

[0158] Step S500 at least includes steps S510-S530:

[0159] S510. During the sterilization process, collect all relevant operation data.

[0160] Data collection and storage: During the sterilization process, high-precision sensors and data acquisition systems are used to collect equipment operation data in real time, including but not limited to:

[0161] Actual temperature data T actual (t): The temperature monitored in real time inside the device.

[0162] Actual pressure data P actual (t): Real-time pressure inside the device.

[0163] Humidity data H actual (t): Ambient humidity information.

[0164] Equipment status data device (t): The operating status, operation mode and operation cycle of the equipment.

[0165] Energy consumption data actual (t): Real-time energy consumption of the equipment during the sterilization process.

[0166] The data is recorded in the form of time series, forming a complete sterilization process data set:

[0167] D process ={T actual(t),P actual (t),H actual (t),S device (t),E actual (t)};

[0168] Data storage and formatting: Format the collected data into standardized data sequences for further data analysis and model evaluation.

[0169] S520. Based on the collected sterilization process data, analyze the sterilization effect and energy-saving effect, evaluate whether the sterilization has achieved the expected goal, and optimize the energy efficiency.

[0170] Data preprocessing and analysis preparation: The collected sterilization process data D process Input into the data analysis module, remove possible outliers, and standardize the data to ensure that the data is within a unified dimension.

[0171] Assume that the data normalization formula is as follows:

[0172]

[0173] Where X(t) represents the operating data (such as temperature, pressure, etc.). X Represents the mean of the data.

[0174] σ X Indicates the standard deviation of the data. Sterilization effect analysis formula: According to the sterilization curve and actual operation data, the sterilization effect parameters are calculated, such as the sterilization factor F0(t), and the formula is:

[0175]

[0176] Among them, T actual (t) represents the actual measured temperature sequence. ref represents the reference temperature. z represents the heat resistance coefficient of the strain. τ set is the duration of the sterilization cycle.

[0177] The target value of the sterilization process is like The sterilization effect is considered to have met the standard.

[0178] Energy saving data calculation: Energy consumption E actual (t) Analyze and calculate the total energy consumption:

[0179]

[0180] And calculate the energy efficiency coefficient EefficiencyE of the sterilization process efficiency Efficiency:

[0181]

[0182] If the energy efficiency factor E efficiency If the energy-saving effect exceeds the energy-saving target value set by the system, the energy-saving effect is considered to have met the target.

[0183] S530, integrating the sterilization results obtained through analysis with the energy-saving data to generate a detailed sterilization effect evaluation report.

[0184] Data integration and report generation: Integrate sterilization effect analysis results (such as F0(t), sterilization target achievement rate, equipment operation time, etc.) with energy saving data (such as E total , energy efficiency) to generate a unified data report.

[0185] The sterilization effect report should include the following:

[0186] Overview of the sterilization process: record basic parameters such as equipment operating time, sterilization cycle, target temperature and pressure.

[0187] Operation data summary: lists the key indicators of the actual operation of the equipment, including the average value and fluctuation range of temperature, pressure, energy consumption, etc.

[0188] Sterilization effect analysis: Display the time variation curve of the sterilization factor F0(t) to confirm whether the sterilization effect meets the standard.

[0189] Energy saving analysis report: Calculate energy saving efficiency E efficiency , compare the theoretical energy consumption of the equipment with the actual energy consumption.

[0190] Optimization suggestions: Based on the operating data, analyze the potential optimization space, such as reducing unnecessary heating time, reducing steam loss, etc.

[0191] Report output and storage:

[0192] The sterilization effect evaluation report is output in the form of an electronic document or equipment operation log and stored in the equipment management system for subsequent analysis and improvement.

[0193] Embodiment 2: Figure 2 FIG. 2 shows a structural block diagram of a temperature and pressure curve optimization system for a medical high-pressure steam sterilizer according to an embodiment of the present invention. Figure 2 As shown, the system may include:

[0194] The data acquisition module 10 collects data related to the sterilization process through high-precision sensors, including bacterial characteristic data, environmental data and equipment operation data.

[0195] Obtain real-time data on the type and quantity of bacteria inside medical equipment, and record the characteristics and density of bacterial species.

[0196] Collect environmental parameters including temperature, humidity and pressure as input references for the sterilization process.

[0197] Integrate bacterial and environmental data to form a complete raw data sequence for subsequent data processing.

[0198] The data processing module 20 cleans and standardizes the collected raw data, extracts key features and generates high-quality data sets.

[0199] Remove noise and outliers to ensure data validity and consistency.

[0200] Standardize the data and convert data of different dimensions into a unified standard.

[0201] Extract key features (such as heat resistance of bacterial strains, temperature and humidity change trends, etc.), and mark the target parameters corresponding to different sterilization conditions.

[0202] The deep learning modeling module 30 trains the deep learning model of the sterilization process based on the processed high-quality data set and generates temperature, pressure and time optimization curves suitable for different bacterial species.

[0203] Using high-quality datasets and feature sets, a sterilization process optimization model was constructed using a deep learning algorithm.

[0204] Optimize model parameters and architecture to generate sterilization optimization curves suitable for different bacterial species.

[0205] Verify the model output to ensure that the model can reliably predict the temperature, pressure and time curves under different sterilization conditions.

[0206] The real-time control and feedback module 40 inputs the generated optimization curve into the real-time control system of the high-pressure steam sterilizer and dynamically adjusts the operating parameters according to the real-time feedback.

[0207] Input the optimization curve into the control system and set the initial operating parameters of the sterilizer.

[0208] Monitor the operating status of equipment in real time and collect operating data (such as temperature, pressure, humidity, etc.).

[0209] Adjust operating parameters according to equipment feedback, dynamically update the sterilization curve, and form a closed-loop control.

[0210] The data analysis and reporting module 50 analyzes the actual operation data and energy-saving effect of the sterilization process and generates a sterilization effect evaluation report.

[0211] Collect and analyze actual operating data during the sterilization process (such as sterilization factors, energy consumption data, etc.).

[0212] Calculate the sterilization target achievement rate and energy efficiency coefficient, and evaluate the sterilization effect and energy-saving performance.

[0213] Integrate analysis results, generate sterilization effect evaluation report, and provide optimization suggestions.

[0214] Beneficial effects: (1) High-precision sterilization: The optimization model trained by the deep learning algorithm can dynamically adjust the temperature, pressure and time parameters to ensure that the sterilization process is accurate and effective.

[0215] (2) Energy saving and environmental protection: By analyzing sterilization energy efficiency data, the sterilization process is optimized and energy consumption is significantly reduced.

[0216] (3) Strong adaptability: Based on a real-time feedback mechanism, the system can dynamically adjust sterilization parameters to adapt to different bacterial species and environmental changes, thereby improving the consistency and reliability of the sterilization effect.

[0217] (4) Data support optimization: The sterilization effect evaluation report provides detailed data support and provides a reference for subsequent equipment optimization and improvement.

[0218] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing the embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to replace some of the technical features therein with equivalents. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer, characterized in that: The method comprises: Using sensors to obtain bacterial characteristic data and environmental parameters to generate raw data sequences; Performing data cleaning and standardization processing on the original data sequence to generate a high-quality data set; Based on the high-quality data set, a deep learning algorithm is used to train a sterilization process model to generate temperature, pressure and time optimization curves suitable for different strains of bacteria; Inputting the optimization curve into a real-time control system to adjust the operating parameters of the high-pressure steam sterilizer; During the sterilization process, dynamic adjustments are made based on the equipment operation data, and a sterilization effect evaluation report is generated.

2. The method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer according to claim 1, characterized in that: The step of obtaining bacterial characteristic data and environmental parameters comprises: The types, quantity and population density of bacteria are collected through sensors; Obtain environmental parameters, including initial temperature, initial humidity and initial pressure; The bacterial data and environmental parameters are integrated to form a complete raw data sequence.

3. The method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer according to claim 1, characterized in that: The steps of data cleaning and standardization processing include: removing noise and outliers from the raw data sequence; Standardizing the data to convert data of different dimensions into a unified standard; Generate datasets suitable for deep learning model training.

4. The method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer according to claim 1, characterized in that: The steps of training the sterilization process model include: Extracting key features from the data set, including strain type, strain heat resistance, and environmental characteristics; Based on the extracted features, a sterilization process model is trained using a deep learning algorithm; The optimized curves of temperature, pressure and time suitable for different strains of bacteria were obtained.

5. The method according to claim 4, characterized in that The deep learning algorithm includes a convolutional neural network and / or a long short-term memory network. The input of the sterilization process model is the characteristics of the bacterial strain and the environmental characteristics, and the output is an optimized temperature, pressure and time curve.

6. The method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer according to claim 1, characterized in that: The step of inputting the optimization curve into the real-time control system comprises: The generated temperature, pressure and time optimization curves are input into the real-time control system of the high-pressure steam sterilizer; The operating parameters of the sterilizer are initialized according to the optimization curve, including initial temperature, initial pressure and initial time.

7. The method according to claim 6, characterized in that The real-time control system comprises: A sensor module that collects equipment operation data; an execution module for adjusting the operating parameters of the device; A processing module that updates the optimization curve based on device feedback data.

8. The method for optimizing the temperature and pressure curve of a medical high-pressure steam sterilizer according to claim 1, characterized in that: The steps of dynamic adjustment include: Monitor the sterilizer operating status in real time and obtain equipment operating data, including temperature, pressure and humidity; adjusting operating parameters according to the deviation between the equipment operation data and the optimization curve; Through the feedback closed-loop mechanism, the optimization curve is dynamically updated and the equipment operation is adjusted.

9. The method according to claim 8, characterized in that The step of dynamic adjustment also includes: Calculate the deviation between the actual sterilization effect and the target value and correct the operating parameters; The corrected parameters are input into the real-time control system to update the equipment operating status.

10. A medical high-pressure steam sterilizer temperature and pressure curve optimization system, characterized in that: The system comprises: Data acquisition module, used to collect bacterial characteristic data, environmental parameters and equipment operation data through high-precision sensors; A data processing module, used to clean and standardize the data and extract key features; A deep learning modeling module for training the sterilization process model based on the processed data to generate temperature, pressure and time optimization curves; A real-time control and feedback module, used to input the optimization curve into the equipment control system and adjust the operating parameters; The data analysis and evaluation module is used to analyze equipment operation data, generate sterilization effect evaluation reports and provide optimization suggestions.

Images