Intelligent monitoring and quality control system for sterilizer

Abstract

The invention relates to the technical field of medical equipment, in particular to a sterilizer intelligent monitoring and quality control system which comprises a sterilization process data acquisition module, a sterilization parameter dynamic optimization module, a sterilization quality grade evaluation module, a sterilization process closed-loop regulation and control module, a biological monitoring data fusion module and a sterilization quality tracing report generation module. Wherein the sterilization process data acquisition module is used for acquiring a temperature value, a pressure value and sterilization duration in a sterilization cabin in real time; the sterilization parameter dynamic optimization module is used for correcting a temperature threshold value, a pressure threshold value and a time threshold value; the sterilization quality grade evaluation module is used for generating a sterilization process quality score; the sterilization process closed-loop regulation and control module is used for generating a PID control instruction; according to the high-temperature and high-pressure sterilizer, through intelligent monitoring, dynamic optimization and biological data fusion, the stability and reliability of the sterilization effect of the high-temperature and high-pressure sterilizer are improved, and automatic control, accurate evaluation and whole-process traceability are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to an intelligent monitoring and quality control system for a sterilizer. Background Art

[0002] The disinfection supply center is an indispensable part of hospitals, medical institutions and other sanitary facilities. Its main task is to disinfect and sterilize medical devices, instruments and other supplies to ensure their safety and hygiene. High-temperature and high-pressure sterilizers are one of the most commonly used equipment in disinfection supply centers and are widely used in sterilization and disinfection processes. Traditional high-temperature and high-pressure sterilizers achieve sterilization effects through heating, pressurization and time control.

[0003] However, most existing sterilizers rely on manually set standardized parameters, such as temperature, pressure and time, and lack real-time monitoring and dynamic adjustment mechanisms, resulting in poor stability and consistency of sterilization effects; this traditional control method cannot cope with actual changes under different sterilization loads and environmental conditions, and there is a risk of substandard sterilization effects or energy waste. In order to solve the above problems, the existing technology urgently needs a sterilizer intelligent monitoring and quality control system to solve the above problems. Summary of the invention

[0004] Based on the above objectives, the present invention provides a sterilizer intelligent monitoring and quality control system.

[0005] The sterilizer intelligent monitoring and quality control system includes a sterilization process data acquisition module, a sterilization parameter dynamic optimization module, a sterilization quality grade evaluation module, a sterilization process closed-loop control module, a biological monitoring data fusion module, and a sterilization quality traceability report generation module; among which:

[0006] Sterilization process data acquisition module: used to collect the temperature value, pressure value and sterilization duration in the sterilization chamber in real time, and generate the original data set of sterilization parameters;

[0007] Sterilization parameter dynamic optimization module: used to receive the original data set of sterilization parameters, dynamically correct the temperature threshold, pressure threshold and time threshold using the gradient descent algorithm based on the historical sterilization qualification rate data and the equipment operation time, and output the optimized sterilization parameter threshold set;

[0008] Sterilization quality grade assessment module: used to compare the original data set of sterilization parameters collected in real time with the optimized sterilization parameter threshold set, calculate the temperature compliance rate, pressure stability coefficient and time redundancy, and generate a sterilization process quality score;

[0009] Sterilization process closed-loop control module: Generates PID control instructions based on the sterilization process quality score, which is used to dynamically adjust the heater power and steam valve opening to compensate for parameter deviations;

[0010] Biological monitoring data fusion module: used to collect the fluorescence intensity value of the biological indicator after sterilization, and combine it with the sterilization process quality score to calculate the comprehensive sterilization effectiveness probability through the Bayesian network;

[0011] Sterilization quality traceability report generation module: used to integrate the original data set of sterilization parameters, the optimized sterilization parameter threshold set and the comprehensive sterilization effectiveness probability data, and generate an electronic report in XML format.

[0012] Optionally, the sterilization process data acquisition module includes a temperature acquisition unit, a pressure acquisition unit, a time recording unit and a data processing unit; wherein:

[0013] Temperature acquisition unit: used to collect temperature data of various points in the sterilization chamber in real time through a temperature sensor arranged in the sterilization chamber. The temperature sensor acquires temperature data at a preset sampling frequency of 10 times per second and transmits the collected temperature value to the data processing unit;

[0014] Pressure acquisition unit: used to collect pressure data in the sterilization chamber in real time through a pressure sensor arranged in the sterilization chamber. The pressure sensor acquires pressure data at a preset sampling frequency of 5 times per second and transmits the collected pressure value to the data processing unit;

[0015] Time recording unit: used to record the duration of the sterilization process through a built-in timer, which tracks the start time and end time of the sterilization process in real time, generates sterilization duration data and transmits it to the data processing unit;

[0016] Data processing unit: used to integrate the data transmitted by the temperature acquisition unit, pressure acquisition unit and time recording unit, specifically including time synchronization processing of temperature data, pressure data and time data, ensuring the consistency of the time axis between each data, and generating the original data set of sterilization parameters.

[0017] Optionally, the sterilization parameter dynamic optimization module includes a data receiving unit, a historical data storage unit, a gradient descent optimization unit and an optimization output unit; wherein:

[0018] Data receiving unit: used to receive the original data set of sterilization parameters from the sterilization process data acquisition module;

[0019] Historical data storage unit: used to store historical sterilization qualification rate data and equipment operation time data;

[0020] Gradient descent optimization unit: used to dynamically adjust the temperature threshold, pressure threshold and time threshold using a gradient descent algorithm based on the received sterilization parameter original data set and the sterilization qualification rate data and equipment operation time data in the historical data storage unit; the gradient descent algorithm adjusts the optimal value of the threshold by calculating the gradient of each parameter to minimize the error in the sterilization process;

[0021] Optimization output unit: used to output the optimized sterilization parameter threshold set, including the temperature threshold, pressure threshold and time threshold corrected by the gradient descent algorithm.

[0022] Optionally, the gradient descent optimization unit includes:

[0023] Initialization step: after receiving the original data set and historical data of sterilization parameters, initialize the temperature threshold, pressure threshold and time threshold;

[0024] Calculate the loss function: Based on the actual sterilization process data and historical data, define the loss function L(T,P,t), the expression is: Where N is the number of data points, T i ,P i ,t i are the actually collected temperature values, pressure values ​​and sterilization duration, respectively, and T, P, t are the temperature, pressure and time thresholds to be optimized;

[0025] Calculate the gradient: According to the loss function L(T,P,t), calculate the gradients of temperature, pressure and time thresholds respectively;

[0026] Update parameters: Update the temperature, pressure and time thresholds according to the update rules of the gradient descent method;

[0027] Iterative optimization: Repeat the above steps until the loss function L(T,P,t) converges to the minimum value, that is, the temperature, pressure and time thresholds no longer change.

[0028] Optionally, the sterilization quality grade assessment module includes a temperature compliance rate calculation unit, a pressure stability coefficient calculation unit, a time redundancy calculation unit, and a sterilization process quality score generation unit; wherein:

[0029] Temperature compliance rate calculation unit: used to compare the real-time collected temperature value with the optimized temperature threshold and calculate the temperature compliance rate R T ;

[0030] Pressure stability coefficient calculation unit: used to compare the real-time collected pressure value with the optimized pressure threshold and calculate the pressure stability coefficient S P ;

[0031] Time redundancy calculation unit: used to compare the sterilization duration collected in real time with the optimized time threshold and calculate the time redundancy R t ;

[0032] Sterilization process quality score generation unit: used to generate the quality score according to the temperature compliance rate R T , pressure stability coefficient S P and time redundancy R t Generate sterilization process quality score, calculation formula: Q = w T ·R T +w P ·S P +w t ·R t , where w T ,w P ,w t are the weight coefficients of temperature, pressure and time, respectively, satisfying w T +w P +w t =1, Q is the final sterilization process quality score.

[0033] Optionally, the sterilization process closed-loop control module includes a PID control instruction generation unit, a heater power adjustment unit and a steam valve opening adjustment unit; wherein:

[0034] PID control instruction generation unit: used to generate PID control instructions according to the quality score of the sterilization process;

[0035] Heater power adjustment unit: used to adjust the heater power according to the PID control instruction. When the temperature deviation is greater than the set threshold value ±2°C, the heater power is adjusted to increase or decrease by 10% to 30% to correct the temperature deviation and ensure that the temperature in the sterilization chamber reaches the optimized threshold value.

[0036] The steam valve opening adjustment unit is used to adjust the steam valve opening according to the PID control instruction. When the pressure deviation is greater than the set threshold value ±5Pa, the steam valve opening is adjusted to increase or decrease by 5% to 20% to ensure that the sterilization process is carried out within the optimal pressure range.

[0037] Optionally, the PID control instruction generating unit includes:

[0038] Error calculation steps: used to calculate the temperature error ε during sterilization T , pressure error ε P and time error ε t ;

[0039] Proportional control step: used to calculate the proportional control term P PID , through the proportionality factor K p Amplify the error and the calculation formula is: PPID =K p ·(ε T +ε P +ε t ), where K p is the proportionality coefficient;

[0040] Integral control step: used to calculate the integral control term I PID , through the integration coefficient K i The historical error is accumulated, and the formula is: I PID =K i ·∫(ε T +ε P +ε t )dt, where K i is the integration coefficient;

[0041] Derivative control step: used to calculate the differential control term D PID , through the differential coefficient K d Calculate the rate of change of the error using the formula: Among them, K d is the differential coefficient;

[0042] PID control instruction generation steps: Calculate the PID control instruction based on the proportional control term, integral control term and differential control term. The formula is: PID =P PID +I PID +D PID , where u PID is the generated PID control instruction, which represents the final adjustment signal.

[0043] Optionally, the biological monitoring data fusion module includes a biological indicator fluorescence intensity acquisition unit and a Bayesian network calculation unit; wherein:

[0044] Biological indicator fluorescence intensity collection unit: used to collect the fluorescence intensity value of the biological indicator after sterilization after the sterilization process is completed. The fluorescence intensity value is collected in real time by a fluorescence sensor arranged in the sterilization chamber, and the fluorescence intensity value at each time point is obtained by regular sampling;

[0045] Bayesian network calculation unit: The Bayesian theorem is used to take the fluorescence intensity value and the sterilization process quality score as conditional inputs to build a probability model, and the comprehensive sterilization effectiveness probability is calculated based on the actual data.

[0046] Optionally, the Bayesian network computing unit includes:

[0047] Input data preparation: The fluorescence intensity value of the biological indicator and the sterilization process quality score are used as conditional inputs. The fluorescence intensity value is F i, the quality score of the sterilization process is Q;

[0048] Construct conditional probability distribution: Based on historical data and actual measurements, construct the joint probability distribution P(F i , Q);

[0049] Application of Bayesian theorem: According to Bayesian theorem, the posterior probability P(E|F i , Q), the expression is: Among them, P(F i , Q|E) is the conditional probability of fluorescence intensity and quality score when sterilization effectiveness E is established; E represents the event of sterilization effectiveness; P(E) is the prior probability of the sterilization effectiveness event;

[0050] Comprehensive sterilization effectiveness probability calculation: By calculating all collected fluorescence intensity values ​​and quality scores, combined with the posterior probability P(E|F i , Q), and obtain the comprehensive sterilization effectiveness probability P(E).

[0051] Optionally, the sterilization quality traceability report generation module includes a data integration unit and a report generation unit; wherein:

[0052] Data integration unit: used to integrate the original data set of sterilization parameters from the sterilization process data acquisition module, the optimized sterilization parameter threshold set from the sterilization parameter dynamic optimization module, and the comprehensive sterilization effectiveness probability generated by the biological monitoring data fusion module, integrate these data in chronological order, ensure the relevance and timeliness of all data, and generate a complete sterilization process record;

[0053] Report generation unit: used to convert the integrated data into an electronic report in XML format, which includes various parameter data of the sterilization process, optimized parameter thresholds and comprehensive sterilization effectiveness probability; it also includes timestamp, equipment number and operator information.

[0054] Beneficial effects of the present invention:

[0055] The present invention can effectively improve the stability and consistency of the sterilization effect through real-time monitoring and dynamic optimization of temperature, pressure, time and biological indicators during the sterilization process; the system uses intelligent data collection and analysis methods, combines historical data and real-time feedback, and dynamically adjusts the temperature, pressure and time thresholds through advanced technologies such as gradient descent algorithms to ensure that the sterilization process is always in the optimal state, thereby effectively avoiding sterilization failure or energy waste caused by human operation or equipment instability in traditional sterilizers.

[0056] The present invention uses a Bayesian network to perform fusion analysis on biological monitoring data, comprehensively evaluates the effectiveness of the sterilization process, and further enhances the accuracy and reliability of sterilization quality control; the generated sterilization quality traceability report not only ensures the traceability and transparency of the process, but also facilitates quality supervision and equipment maintenance; through this intelligent and automated monitoring and control solution, the quality management level of sterilization operations in the disinfection supply center is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 Schematic diagram of a sterilizer intelligent monitoring and quality control system according to an embodiment of the present invention;

[0059] Figure 2 Schematic diagram of a closed-loop control module for the sterilization process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0061] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0062] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0063] like Figure 1-Figure 2 As shown, the sterilizer intelligent monitoring and quality control system includes a sterilization process data acquisition module, a sterilization parameter dynamic optimization module, a sterilization quality grade evaluation module, a sterilization process closed-loop control module, a biological monitoring data fusion module, and a sterilization quality traceability report generation module; among which:

[0064] Sterilization process data acquisition module: used to collect the temperature value, pressure value and sterilization duration in the sterilization chamber in real time, and generate the original data set of sterilization parameters;

[0065] Sterilization parameter dynamic optimization module: used to receive the original data set of sterilization parameters, dynamically correct the temperature threshold, pressure threshold and time threshold using the gradient descent algorithm based on the historical sterilization qualification rate data and the equipment operation time, and output the optimized sterilization parameter threshold set;

[0066] Sterilization quality grade assessment module: used to compare the original data set of sterilization parameters collected in real time with the optimized sterilization parameter threshold set, calculate the temperature compliance rate, pressure stability coefficient and time redundancy, and generate a sterilization process quality score;

[0067] Sterilization process closed-loop control module: Generates PID control instructions based on the sterilization process quality score, which is used to dynamically adjust the heater power and steam valve opening to compensate for parameter deviations;

[0068] Biological monitoring data fusion module: used to collect the fluorescence intensity value of the biological indicator after sterilization, and combine it with the sterilization process quality score to calculate the comprehensive sterilization effectiveness probability through the Bayesian network;

[0069] Sterilization quality traceability report generation module: used to integrate the original data set of sterilization parameters, the optimized sterilization parameter threshold set and the comprehensive sterilization effectiveness probability data, and generate an electronic report in XML format.

[0070] The sterilization process data acquisition module includes a temperature acquisition unit, a pressure acquisition unit, a time recording unit and a data processing unit; wherein:

[0071] Temperature acquisition unit: used to collect temperature data of each point in the sterilization chamber in real time through the temperature sensor set in the sterilization chamber. The temperature sensor obtains temperature data at a preset sampling frequency of 10 times per second and transmits the collected temperature value to the data processing unit;

[0072] Pressure acquisition unit: used to collect pressure data in the sterilization chamber in real time through a pressure sensor arranged in the sterilization chamber. The pressure sensor acquires pressure data at a preset sampling frequency of 5 times per second and transmits the collected pressure value to the data processing unit;

[0073] Time recording unit: used to record the duration of the sterilization process through a built-in timer, which tracks the start and end time of the sterilization process in real time, generates sterilization duration data and transmits it to the data processing unit;

[0074] Data processing unit: used to integrate the data transmitted by the temperature acquisition unit, pressure acquisition unit and time recording unit, specifically including time synchronization processing of temperature data, pressure data and time data to ensure the consistency of the time axis between the data, and generate the original data set of sterilization parameters; through the collaborative work of the above units, the sterilization process data acquisition module can accurately and real-time collect the temperature, pressure and time data in the sterilization chamber, and generate the original data set of sterilization parameters, providing data support for subsequent sterilization parameter optimization and quality evaluation.

[0075] The dynamic optimization module of sterilization parameters includes a data receiving unit, a historical data storage unit, a gradient descent optimization unit and an optimization output unit; wherein:

[0076] Data receiving unit: used to receive the original data set of sterilization parameters from the sterilization process data acquisition module, the data set including the real-time collected temperature value, pressure value and sterilization duration data;

[0077] Historical data storage unit: used to store historical sterilization qualified rate data and equipment running time data. The historical sterilization qualified rate data includes the qualified rate of the sterilization process in each time period, and the equipment running time data records the running time of the equipment in each sterilization process;

[0078] Gradient descent optimization unit: used to dynamically adjust the temperature threshold, pressure threshold and time threshold using the gradient descent algorithm based on the received sterilization parameter original data set and the sterilization qualification rate data and equipment operation time data in the historical data storage unit; the gradient descent algorithm adjusts the optimal value of the threshold by calculating the gradient of each parameter to minimize the error in the sterilization process;

[0079] Optimization output unit: used to output the optimized sterilization parameter threshold set, including the temperature threshold, pressure threshold and time threshold corrected by the gradient descent algorithm. The optimized threshold set will be transmitted to the sterilization quality grade assessment module for subsequent evaluation; the above unit can use the gradient descent algorithm to perform efficient dynamic optimization adjustments based on the sterilization data and historical data collected in real time to ensure that key parameters such as temperature, pressure and time reach the optimal values, maximize the pass rate of the sterilization process and the equipment operation efficiency, and not only enhance the system's adaptability, but also through the guidance of historical data, effectively avoid parameter deviations caused by changes in equipment status or environmental factors.

[0080] The gradient descent optimization unit includes:

[0081] Initialization step: after receiving the original data set and historical data of sterilization parameters, initialize the temperature threshold, pressure threshold and time threshold;

[0082] Calculate the loss function: Based on the actual sterilization process data and historical data, define the loss function L(T,P,t), the expression is: Where N is the number of data points, T i ,P i ,t i are the actual collected temperature value, pressure value and sterilization duration, T, P, t are the temperature, pressure and time thresholds to be optimized; the loss function L(T, P, t) measures the error between each threshold and the actual data, and the goal is to minimize the loss function and achieve the optimal parameters;

[0083] Calculate the gradient: According to the loss function L(T,P,t), calculate the gradient of the temperature, pressure and time thresholds respectively. The formula is as follows:

[0084]

[0085] in, and They are the gradients of the temperature threshold, pressure threshold, and time threshold, respectively, indicating the change in the error between each threshold and the actual data;

[0086] Update parameters: According to the update rule of the gradient descent method, the temperature, pressure and time thresholds are updated using the following formulas:

[0087] Among them, η is the learning rate, which controls the amplitude of each update. After each update, the new threshold T new ,P new ,t new will be closer to the optimal value;

[0088] Iterative optimization: Repeat the above steps until the loss function L(T,P,t) converges to the minimum value, that is, the temperature, pressure and time thresholds no longer change.

[0089] The sterilization quality grade assessment module includes a temperature compliance rate calculation unit, a pressure stability coefficient calculation unit, a time redundancy calculation unit, and a sterilization process quality score generation unit; among which:

[0090] Temperature compliance rate calculation unit: used to compare the real-time collected temperature value with the optimized temperature threshold and calculate the temperature compliance rate R T , the formula is: Where Θ(x) is a unit step function. When x ≥ 0, Θ(x) = 1, otherwise Θ(x) = 0. Ti is the temperature value collected in real time, T new is the optimized temperature threshold, R T is the temperature compliance rate, which indicates the degree of compliance between the collected temperature value and the optimized temperature threshold;

[0091] Pressure stability coefficient calculation unit: used to compare the real-time collected pressure value with the optimized pressure threshold and calculate the pressure stability coefficient S P , the formula is: Among them, P i is the pressure value collected in real time, P new is the optimized pressure threshold, S P is the pressure stability coefficient, which indicates the stability and error range of the collected pressure value and the optimized pressure threshold;

[0092] Time redundancy calculation unit: used to compare the sterilization duration collected in real time with the optimized time threshold and calculate the time redundancy R t ; The formula is: Among them, t i is the sterilization duration collected in real time, t new is the optimized time threshold, R t is the time redundancy, which indicates the difference between the collected time value and the optimized time threshold;

[0093] Sterilization process quality score generation unit: used to generate the quality score according to the temperature compliance rate R T , pressure stability coefficient S P and time redundancy R t Generate sterilization process quality score, calculation formula: Q = w T ·R T +w P ·S P +w t ·R t , where w T ,w P ,w t are the weight coefficients of temperature, pressure and time, respectively, satisfying w T +w P +w t=1, which is used to adjust the contribution of each indicator to the quality score. Q is the final sterilization process quality score, which indicates the overall quality level of the sterilization process. By weighted combination of various indicators, a comprehensive score is obtained to evaluate the overall quality of the sterilization process. The weight coefficient of each indicator can be set according to actual needs. The temperature compliance rate mainly reflects the accuracy of temperature control, the pressure stability coefficient evaluates the stability of pressure control, and the time redundancy measures the time control and optimization of the sterilization process. By combining these three indicators, the generated quality score can accurately reflect the effect of the sterilization process and provide a basis for subsequent regulation and optimization.

[0094] The sterilization process closed-loop control module includes a PID control instruction generation unit, a heater power adjustment unit, and a steam valve opening adjustment unit; wherein:

[0095] PID control instruction generation unit: used to generate PID control instructions according to the quality score of the sterilization process;

[0096] Heater power adjustment unit: used to adjust the heater power according to the PID control instruction. When the temperature deviation is greater than the set threshold value ±2°C, the heater power is adjusted to increase or decrease by 10% to 30% to correct the temperature deviation and ensure that the temperature in the sterilization chamber reaches the optimized threshold value.

[0097] The steam valve opening adjustment unit is used to adjust the steam valve opening according to the PID control instruction. When the pressure deviation is greater than the set threshold value of ±5Pa, the steam valve opening is adjusted by 5% to 20% to ensure that the sterilization process is carried out within the optimal pressure range. Through the closed-loop regulation of the above unit based on the PID control algorithm, the heater power and steam valve opening can be dynamically adjusted according to the real-time quality score. The specific adjustment range and threshold ensure the rapid correction of temperature and pressure, so that the sterilization process is always kept within the optimal range, thereby improving the sterilization efficiency and quality, and avoiding problems such as overheating or unstable pressure.

[0098] The PID control instruction generation unit includes:

[0099] Error calculation steps: used to calculate the temperature error ε during sterilization T , pressure error ε P and time error ε t , respectively calculated by the following formula: T =T new -T i ; ε P =T new -P i ; ε t =t new -t i , where T new is the optimized temperature threshold, Ti is the temperature value collected in real time; P new is the optimized pressure threshold, P i is the pressure value collected in real time; t new is the optimized time threshold, t i The sterilization time is collected in real time;

[0100] Proportional control step: used to calculate the proportional control term P PID , through the proportionality factor K p Amplify the error and the calculation formula is: P PID =K p ·(ε T +ε P +ε t ), where K p is the proportional coefficient, which adjusts the response speed of the control system;

[0101] Integral control step: used to calculate the integral control term I PID , through the integration coefficient K i The historical error is accumulated, and the formula is: I PID =K i ·∫(ε T +ε P +ε t )dt, where K i is the integration coefficient, and the accumulated error helps to eliminate long-term deviations in the system;

[0102] Derivative control step: used to calculate the differential control term D PID , through the differential coefficient K d Calculate the rate of change of the error using the formula: Among them, K d is the differential coefficient, which controls the rapidity of the control system response, predicts the error trend and avoids over-adjustment;

[0103] PID control instruction generation steps: Calculate the PID control instruction based on the proportional control term, integral control term and differential control term. The formula is: PID =P PID +I PID +D PID , where u PID The generated PID control instruction represents the final adjustment signal, which is input into the heater power adjustment unit and the steam valve opening adjustment unit to adjust the working state of the equipment to compensate for the deviations in temperature, pressure and time. Through the above steps, the control signal can be accurately adjusted according to the various errors in the sterilization process, so that the system can respond to temperature, pressure and time deviations in real time and accurately, avoid over-adjustment or response delay, and ensure that the sterilization process always remains within the optimal control range.

[0104] The biological monitoring data fusion module includes a biological indicator fluorescence intensity acquisition unit and a Bayesian network calculation unit; wherein:

[0105] Biological indicator fluorescence intensity acquisition unit: used to collect the fluorescence intensity value of the biological indicator after sterilization after the sterilization process is completed. The fluorescence intensity value is collected in real time by the fluorescence sensor installed in the sterilization chamber, and the fluorescence intensity value at each time point is obtained through regular sampling as a biological indicator of whether the sterilization process is successful; the fluorescence intensity value is positively correlated with the survival of microorganisms after sterilization. The higher the intensity value, the greater the possibility of microorganism survival, and vice versa, the better the sterilization effect;

[0106] Bayesian network calculation unit: Bayesian theorem is used to take the fluorescence intensity value and the sterilization process quality score as conditional inputs, to construct a probability model, and to calculate the comprehensive sterilization effectiveness probability based on actual data; the above unit combines the fluorescence intensity value of the biological indicator with the sterilization process quality score, and uses the Bayesian network for comprehensive calculation, which can accurately evaluate the effectiveness of the sterilization process; this process can provide higher-precision verification of the sterilization results, ensuring that the sterilization process not only meets the standards in terms of physical parameters (such as temperature, pressure, and time), but can also provide further effectiveness verification through biological monitoring, thereby improving the reliability of the sterilization process.

[0107] The Bayesian network computing unit includes:

[0108] Input data preparation: The fluorescence intensity value of the biological indicator and the sterilization process quality score are used as conditional inputs. The fluorescence intensity value is F i , the quality score of the sterilization process is Q;

[0109] Construct conditional probability distribution: Based on historical data and actual measurements, construct the joint probability distribution P(F i , Q); joint probability P(F i , Q) represents the fluorescence intensity value F i The probability of sterilization effectiveness under the condition of quality score Q; the conditional probability of each node in the Bayesian network model can be obtained through historical experimental data or statistical analysis, and the specific expression is: P(F i , Q)=P(F i |Q)·P(Q), where P(F i |Q) is given a quality score Q i Under the condition of i The conditional probability of , P(Q) is the marginal probability of the quality score Q;

[0110] Application of Bayesian theorem: According to Bayesian theorem, the posterior probability P(E|F i , Q), the expression is: Among them, P(F i , Q|E) is the conditional probability of fluorescence intensity and quality score when sterilization effectiveness E is established; E represents the event of sterilization effectiveness; P(E) is the prior probability of the sterilization effectiveness event; P(F i , Q) is the joint probability of the fluorescence intensity value and the quality score;

[0111] Comprehensive sterilization effectiveness probability calculation: By calculating all collected fluorescence intensity values ​​and quality scores, combined with the posterior probability P(E|F i , Q), and obtain the comprehensive sterilization effectiveness probability P(E), which represents the overall effectiveness of the sterilization process, and the final output is a numerical value, reflecting the success rate and effectiveness of the sterilization process; the above steps can accurately evaluate the effectiveness of the sterilization process by combining the fluorescence intensity value and the sterilization process quality score with the Bayesian network for comprehensive analysis; the application of Bayesian theorem can effectively integrate biological monitoring and process quality information by processing the dependency relationship between different variables, thereby providing a more accurate probability evaluation for the effect of the sterilization process and ensuring the reliability and safety of the sterilization process.

[0112] The sterilization quality traceability report generation module includes a data integration unit and a report generation unit; wherein:

[0113] Data integration unit: used to integrate the original data set of sterilization parameters from the sterilization process data acquisition module, the optimized sterilization parameter threshold set from the sterilization parameter dynamic optimization module, and the comprehensive sterilization effectiveness probability generated by the biological monitoring data fusion module, integrate these data in chronological order, ensure the relevance and timeliness of all data, and generate a complete sterilization process record;

[0114] Report generation unit: used to convert the integrated data into an electronic report in XML format. The electronic report in XML format includes various parameter data of the sterilization process (such as temperature, pressure, time, etc.), optimized parameter thresholds and comprehensive sterilization effectiveness probability; it also includes timestamp, equipment number and operator information; the above unit can comprehensively record all key information in the sterilization process and integrate it into a standardized electronic report in XML format to ensure the integrity and accuracy of the data. By adding timestamp, equipment number, operator and other information, it provides a complete traceability function to ensure the traceability of the sterilization process.

[0115] The present invention covers any alternatives, modifications, equivalent methods, and solutions made to the essence and scope of the present invention. For the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention even without the description of these details. Additionally, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0116] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. Sterilizer intelligent monitoring and quality control system, characterized by: It includes sterilization process data acquisition module, sterilization parameter dynamic optimization module, sterilization quality grade assessment module, sterilization process closed-loop control module, biological monitoring data fusion module and sterilization quality traceability report generation module; among which: Sterilization process data acquisition module: used to collect the temperature value, pressure value and sterilization duration in the sterilization chamber in real time, and generate the original data set of sterilization parameters; Sterilization parameter dynamic optimization module: used to receive the original data set of sterilization parameters, dynamically correct the temperature threshold, pressure threshold and time threshold using the gradient descent algorithm based on the historical sterilization qualification rate data and the equipment operation time, and output the optimized sterilization parameter threshold set; Sterilization quality grade assessment module: used to compare the original data set of sterilization parameters collected in real time with the optimized sterilization parameter threshold set, calculate the temperature compliance rate, pressure stability coefficient and time redundancy, and generate a sterilization process quality score; Sterilization process closed-loop control module: Generates PID control instructions based on the sterilization process quality score, which is used to dynamically adjust the heater power and steam valve opening to compensate for parameter deviations; Biological monitoring data fusion module: used to collect the fluorescence intensity value of the biological indicator after sterilization, and combine it with the sterilization process quality score to calculate the comprehensive sterilization effectiveness probability through the Bayesian network; Sterilization quality traceability report generation module: used to integrate the original data set of sterilization parameters, the optimized sterilization parameter threshold set and the comprehensive sterilization effectiveness probability data, and generate an electronic report in XML format.

2. The sterilizer intelligent monitoring and quality control system according to claim 1 is characterized in that: The sterilization process data acquisition module includes a temperature acquisition unit, a pressure acquisition unit, a time recording unit and a data processing unit; wherein: Temperature acquisition unit: used to collect temperature data of various points in the sterilization chamber in real time through a temperature sensor arranged in the sterilization chamber. The temperature sensor acquires temperature data at a preset sampling frequency of 10 times per second and transmits the collected temperature value to the data processing unit; Pressure acquisition unit: used to collect pressure data in the sterilization chamber in real time through a pressure sensor arranged in the sterilization chamber. The pressure sensor acquires pressure data at a preset sampling frequency of 5 times per second and transmits the collected pressure value to the data processing unit; Time recording unit: used to record the duration of the sterilization process through a built-in timer, which tracks the start time and end time of the sterilization process in real time, generates sterilization duration data and transmits it to the data processing unit; Data processing unit: used to integrate the data transmitted by the temperature acquisition unit, pressure acquisition unit and time recording unit, specifically including time synchronization processing of temperature data, pressure data and time data, ensuring the consistency of the time axis between each data, and generating the original data set of sterilization parameters.

3. The sterilizer intelligent monitoring and quality control system according to claim 1 is characterized in that: The sterilization parameter dynamic optimization module includes a data receiving unit, a historical data storage unit, a gradient descent optimization unit and an optimization output unit; wherein: Data receiving unit: used to receive the original data set of sterilization parameters from the sterilization process data acquisition module; Historical data storage unit: used to store historical sterilization qualification rate data and equipment operation time data; Gradient descent optimization unit: used to dynamically adjust the temperature threshold, pressure threshold and time threshold using a gradient descent algorithm based on the received sterilization parameter original data set and the sterilization qualification rate data and equipment operation time data in the historical data storage unit; the gradient descent algorithm adjusts the optimal value of the threshold by calculating the gradient of each parameter to minimize the error in the sterilization process; Optimization output unit: used to output the optimized sterilization parameter threshold set, including the temperature threshold, pressure threshold and time threshold corrected by the gradient descent algorithm.

4. The sterilizer intelligent monitoring and quality control system according to claim 3 is characterized in that: The gradient descent optimization unit comprises: Initialization step: after receiving the original data set and historical data of sterilization parameters, initialize the temperature threshold, pressure threshold and time threshold; Calculate the loss function: Based on the actual sterilization process data and historical data, define the loss function L(T,P,t), the expression is: Where N is the number of data points, T i ,P i ,t i are the actually collected temperature values, pressure values ​​and sterilization duration, respectively, and T, P, t are the temperature, pressure and time thresholds to be optimized; Calculate the gradient: According to the loss function L(T,P,t), calculate the gradients of temperature, pressure and time thresholds respectively; Update parameters: Update the temperature, pressure and time thresholds according to the update rules of the gradient descent method; Iterative optimization: Repeat the above steps until the loss function L(T,P,t) converges to the minimum value, that is, the temperature, pressure and time thresholds no longer change.

5. The sterilizer intelligent monitoring and quality control system according to claim 1 is characterized in that: The sterilization quality grade assessment module includes a temperature compliance rate calculation unit, a pressure stability coefficient calculation unit, a time redundancy calculation unit and a sterilization process quality score generation unit; wherein: Temperature compliance rate calculation unit: used to compare the real-time collected temperature value with the optimized temperature threshold and calculate the temperature compliance rate R T ; Pressure stability coefficient calculation unit: used to compare the real-time collected pressure value with the optimized pressure threshold and calculate the pressure stability coefficient S P ; Time redundancy calculation unit: used to compare the sterilization duration collected in real time with the optimized time threshold and calculate the time redundancy R t ; Sterilization process quality score generation unit: used to generate the quality score according to the temperature compliance rate R T , pressure stability coefficient S P and time redundancy R t Generate sterilization process quality score, calculation formula: Q = w T ·R T +w P ·S P +w t ·R t , where w T ,w P ,w t are the weight coefficients of temperature, pressure and time, respectively, satisfying w T +w P +w t =1, Q is the final sterilization process quality score.

6. The sterilizer intelligent monitoring and quality control system according to claim 1, characterized in that: The sterilization process closed-loop control module includes a PID control instruction generation unit, a heater power adjustment unit and a steam valve opening adjustment unit; wherein: PID control instruction generation unit: used to generate PID control instructions according to the quality score of the sterilization process; Heater power adjustment unit: used to adjust the heater power according to the PID control instruction. When the temperature deviation is greater than the set threshold value ±2°C, the heater power is adjusted to increase or decrease by 10% to 30% to correct the temperature deviation and ensure that the temperature in the sterilization chamber reaches the optimized threshold value. The steam valve opening adjustment unit is used to adjust the steam valve opening according to the PID control instruction. When the pressure deviation is greater than the set threshold value ±5Pa, the steam valve opening is adjusted to increase or decrease by 5% to 20% to ensure that the sterilization process is carried out within the optimal pressure range.

7. The sterilizer intelligent monitoring and quality control system according to claim 6, characterized in that: The PID control instruction generating unit comprises: Error calculation steps: used to calculate the temperature error ε during sterilization T , pressure error ε P and time error ε t ; Proportional control step: used to calculate the proportional control term P PID , through the proportionality factor K p Amplify the error and the calculation formula is: P PID =K p ·(ε T +ε P +ε t ), where K p is the proportionality coefficient; Integral control step: used to calculate the integral control term I PID , through the integration coefficient K i The historical error is accumulated, and the formula is: I PID =K i ∫(ε T +ε P +ε t )dt, where K i is the integration coefficient; Derivative control step: used to calculate the differential control term D PID , through the differential coefficient K d Calculate the rate of change of the error using the formula: Among them, K d is the differential coefficient; PID control instruction generation steps: Calculate the PID control instruction based on the proportional control term, integral control term and differential control term. The formula is: PID =P PID +I PID +D PID , where u PID is the generated PID control instruction, which represents the final adjustment signal.

8. The sterilizer intelligent monitoring and quality control system according to claim 1, characterized in that: The biological monitoring data fusion module includes a biological indicator fluorescence intensity acquisition unit and a Bayesian network calculation unit; wherein: Biological indicator fluorescence intensity collection unit: used to collect the fluorescence intensity value of the biological indicator after sterilization after the sterilization process is completed. The fluorescence intensity value is collected in real time by a fluorescence sensor arranged in the sterilization chamber, and the fluorescence intensity value at each time point is obtained by regular sampling; Bayesian network calculation unit: The Bayesian theorem is used to take the fluorescence intensity value and the sterilization process quality score as conditional inputs to build a probability model, and the comprehensive sterilization effectiveness probability is calculated based on the actual data.

9. The sterilizer intelligent monitoring and quality control system according to claim 8, characterized in that: The Bayesian network computing unit comprises: Input data preparation: The fluorescence intensity value of the biological indicator and the sterilization process quality score are used as conditional inputs. The fluorescence intensity value is F i , the quality score of the sterilization process is Q; Construct conditional probability distribution: Based on historical data and actual measurements, construct the joint probability distribution P(F i , Q); Application of Bayesian theorem: According to Bayesian theorem, the posterior probability P(E|F i , Q), the expression is: Among them, P(F i , Q|E) is the conditional probability of fluorescence intensity and quality score when sterilization effectiveness E is established; E represents the event of sterilization effectiveness; P(E) is the prior probability of the sterilization effectiveness event; Comprehensive sterilization effectiveness probability calculation: By calculating all collected fluorescence intensity values ​​and quality scores, combined with the posterior probability P(E|F i , Q), and obtain the comprehensive sterilization effectiveness probability P(E).

10. The sterilizer intelligent monitoring and quality control system according to claim 1, characterized in that: The sterilization quality traceability report generation module includes a data integration unit and a report generation unit; wherein: Data integration unit: used to integrate the original data set of sterilization parameters from the sterilization process data acquisition module, the optimized sterilization parameter threshold set from the sterilization parameter dynamic optimization module, and the comprehensive sterilization effectiveness probability generated by the biological monitoring data fusion module, integrate these data in chronological order, ensure the relevance and timeliness of all data, and generate a complete sterilization process record; Report generation unit: used to convert the integrated data into an electronic report in XML format, which includes various parameter data of the sterilization process, optimized parameter thresholds and comprehensive sterilization effectiveness probability; it also includes timestamp, equipment number and operator information.

Images