Sterilizer jacket condensate water discharge control method, system, equipment and medium
Through real-time monitoring and machine learning prediction models, dynamically adjust the operating parameters of the sterilizer, the problem of unstable condensate discharge of the sterilizer jacket is solved, and intelligent monitoring and control is realized to ensure compliance with the discharged water quality and environmental protection.
Patent Information
- Application Number
- CN202410994394.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2024-11-12
AI Technical Summary
The existing condensate water treatment methods for jacketed sterilizers lack real-time monitoring and control capabilities, resulting in unstable condensate discharge, unable to ensure environmental protection requirements, and fixed operating parameters cannot be adjusted dynamically, making it difficult to deal with problems in a timely manner.
Using temperature sensors, flowmeters and water quality sensors to monitor data in real time, build a real-time prediction model of condensed water yield and water quality through machine learning, combine optimization algorithms to dynamically adjust operating parameters, formulate intelligent emission control strategies, establish a condensate emission monitoring system, and live Determine whether the emission data meets the standards, issue an alarm and make adjustments.
Intelligent monitoring and control of condensate discharge of sterilizer jackets has been realized to ensure that the discharged water quality is compliant, improve production efficiency, and reduce environmental impact.
Smart Images

Figure CN118938672A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent monitoring and control technology, and in particular to a method, system, equipment and medium for controlling the discharge of condensate from a sterilizer jacket. Background Art
[0002] In pharmaceutical factories, sterilizers are vital equipment used to sterilize drugs and medical devices. Condensate produced by the sterilizer jacket during the sterilization process is a common byproduct. However, untreated condensate may contain pollutants such as organics, inorganics or microorganisms, which pose potential hazards to the environment and production equipment. The hazards may include traditional condensate treatment methods often rely on offline sampling and laboratory analysis, lack of real-time monitoring and control capabilities, and inability to detect and respond to problems in a timely manner; the operating parameters of most sterilizers are fixed and cannot be dynamically adjusted according to actual conditions, resulting in condensate discharge being difficult to control; and lack of real-time monitoring and control, the water quality of condensate discharge is often unstable, and it is impossible to ensure compliance with environmental protection requirements. Therefore, a comprehensive approach is needed to monitor and control condensate production and implement intelligent emission control to ensure compliance with emission water quality and minimize environmental impact. Summary of the invention
[0003] The purpose of the present invention is to provide a method, system, device and medium for controlling the discharge of condensed water from a sterilizer jacket to improve the above-mentioned problem. In order to achieve the above-mentioned purpose, the technical solution adopted by the present invention is as follows:
[0004] In a first aspect, the present application provides a method for controlling the discharge of condensate from a sterilizer jacket, comprising:
[0005] Collecting first monitoring data, wherein the first monitoring data includes jacket temperature, condensate flow rate and water quality components monitored in real time by a temperature sensor, flow meter and water quality sensor installed inside the sterilizer jacket;
[0006] Obtain historical data on the discharge of condensate from the sterilizer jacket, and use machine learning to build a real-time prediction model for the output and quality of condensate from the sterilizer jacket based on the historical data and the first monitoring data;
[0007] Combined with the real-time prediction model and optimization algorithm of the sterilizer jacket condensate production and water quality, the operating parameters of the sterilizer are dynamically adjusted;
[0008] Based on the operating parameters of the sterilizer, an intelligent emission control strategy is formulated and a condensate emission monitoring system is established to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm is issued. If it does not drop or exceed the preset threshold, monitoring continues.
[0009] Preferably, the historical data of the discharge of the condensate from the sterilizer jacket is obtained, and based on the historical data and the first monitoring data, a real-time prediction model of the output and water quality of the condensate from the sterilizer jacket is constructed by machine learning, which includes:
[0010] Based on the jacket temperature, condensate flow rate and water quality components monitored in real time by the temperature sensor, flow meter and water quality sensor inside the sterilizer jacket, the original data set of the sterilizer jacket condensate discharge for modeling is obtained through data cleaning and feature extraction;
[0011] Perform stationarity detection and differential processing on the original data set to obtain stable time series data;
[0012] Based on the time series data, the autoregressive moving average model is used to fit the model parameters, and the calculation formula is as follows:
[0013] X t =c+φ1X t-1 +φ2X t-2 +…+φ p X t-p +∈ t -θ1∈ t-1 -θ2∈ t-2 -…-θ q ∈ t-q
[0014] Where, X t is the observed value at time t, i.e., time series data, c is a constant term, representing the intercept of the model, φ1, φ2, ..., φ p is the autoregressive coefficient, which represents the linear relationship between the current observation and the past p observations, θ1, θ2, ..., θ q is the moving average coefficient, which represents the linear relationship between the previous observation and the past q residual terms, ∈t is white noise, which represents the random disturbance term and obeys the normal distribution with zero mean and constant variance;
[0015] According to the model parameters, after model identification and model fitting, the optimal real-time prediction model of the sterilizer jacket condensate production and water quality is obtained.
[0016] Preferably, the real-time prediction model and optimization algorithm for the output and quality of condensed water from the jacket of the sterilizer are combined to dynamically adjust the operating parameters of the sterilizer, including:
[0017] Using the real-time prediction model of the output and water quality of the sterilizer jacket condensate, combined with the real-time monitored jacket temperature, condensate flow and water quality composition data, the discharge parameters of the sterilizer jacket condensate in the future are predicted, where the discharge parameters include output and water quality;
[0018] According to the multi-objective optimization algorithm, the emission parameters are used as the objective function to determine the optimal emission control parameters;
[0019] Based on the optimal emission control parameters, through real-time monitoring data and feedback mechanism, a real-time emission control strategy is obtained;
[0020] According to the emission control strategy, the actual operating parameters of the sterilizer are obtained through the intelligent control system, thereby realizing real-time multi-objective emission control.
[0021] Preferably, the emission parameters are used as objective functions according to the multi-objective optimization algorithm to determine the optimal emission control parameters, which include:
[0022] Define the two parts of production and water quality as the objective function;
[0023] The objective function is normalized to obtain the first objective function and the second objective function, and their calculation formulas are as follows:
[0024]
[0025] In the formula, f 1’ is the first objective function after normalization, i.e. the normalized value of condensate production; f 2’ is the normalized second objective function, i.e., the normalized value of water quality; f1 is the original first objective function, i.e., the condensate output; f2 is the original second objective function, i.e., water quality; min(f1) is the minimum value of the first objective function; max(f1) is the maximum value of the first objective function; min(f2) is the minimum value of the second objective function; max(f2) is the maximum value of the second objective function;
[0026] Based on the first objective function and the second objective function, a fitness function is designed, and a set of initial operating parameter combinations are randomly generated as the initial individuals of the population. The calculation formula of the fitness function is as follows:
[0027] Fitness=w1×f′1+w2×f′2
[0028] In the formula, Fitness is the fitness of the individual, W1 is the weight of the first objective function, W2 is the weight of the second objective function, and f 1’ is the normalized value of condensate production, f 2’ is the normalized value of water quality;
[0029] According to the initial individuals, their fitness values are calculated through crossover and mutation operations, and the roulette wheel selection algorithm is used to select excellent individuals as the parents of the next generation population. The iterative optimization is carried out until the stopping condition is reached, and the final output is used as the optimal emission control parameter, where the stopping condition is reaching the maximum number of iterations or satisfying the convergence condition.
[0030] Preferably, based on the operating parameters of the sterilizer, an intelligent emission control strategy is formulated and a condensate emission monitoring system is established to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm is issued. If it does not drop or exceed the preset threshold, monitoring continues, including:
[0031] Based on the sterilizer’s operating parameters and historical data, an optimization algorithm is used to design an intelligent emission control strategy;
[0032] Establish a condensate discharge monitoring system to monitor real-time discharge data, transmit the real-time discharge data to a central processing unit for analysis and processing, and obtain processing results, wherein the condensate discharge monitoring system includes sensors, data acquisition equipment, and data storage systems;
[0033] Based on the comparison between the processing results and the pre-set standards, the system determines whether the emission data is within the expected range by comparing the monitored data with the standard value; if the monitored emission data drops or exceeds the preset threshold, the system will issue an alarm to prompt the operator to process or adjust; if the emission data is within the expected range, the system will continue to monitor and update the intelligent emission control strategy as needed.
[0034] In a second aspect, the present application also provides a sterilizer jacket condensate discharge control system, comprising:
[0035] Acquisition module: used to collect first monitoring data, wherein the first monitoring data includes jacket temperature, condensate flow rate and water quality components monitored in real time by a temperature sensor, flow meter and water quality sensor installed inside the sterilizer jacket;
[0036] Construction module: used to obtain historical data of sterilizer jacket condensate discharge, and build a real-time prediction model of sterilizer jacket condensate output and water quality by machine learning based on historical data and first monitoring data;
[0037] Adjustment module: used to dynamically adjust the operating parameters of the sterilizer by combining the real-time prediction model and optimization algorithm of the condensate output and water quality of the sterilizer jacket;
[0038] Establishment module: It is used to formulate intelligent emission control strategies based on the operating parameters of the sterilizer and establish a condensate emission monitoring system to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm will be issued. If it does not drop or exceed the preset threshold, monitoring will continue.
[0039] In a third aspect, the present application also provides a sterilizer jacket condensate discharge control device, comprising:
[0040] Memory for storing computer programs;
[0041] A processor is used to implement the steps of the sterilizer jacket condensate discharge control method when executing the computer program.
[0042] In a fourth aspect, the present application further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned method for controlling condensate discharge based on the sterilizer jacket are implemented.
[0043] The beneficial effects of the present invention are:
[0044] The present invention utilizes temperature sensors, flow meters and water quality sensors installed inside the sterilizer jacket to collect first monitoring data such as jacket temperature, condensate flow and water quality composition in real time. These data are cleaned and feature extracted to obtain original data sets for modeling. The original data sets are subjected to stationarity detection and differential processing to obtain stable time series data, providing a basis for subsequent modeling and prediction.
[0045] The present invention adopts machine learning or optimization algorithm to construct a real-time prediction model for the production and water quality of sterilizer jacket condensate, wherein commonly used time series analysis methods such as ARIMA model can be used to predict the production of condensate, and machine learning-based algorithms such as random forest or neural network can be used to predict water quality. These models are trained and optimized based on historical data and real-time monitoring data to predict the condensate discharge parameters in the future, including production and water quality.
[0046] Based on the prediction model, the present invention adopts a multi-objective optimization algorithm (such as a multi-objective genetic algorithm or a multi-objective particle swarm optimization algorithm), takes the emission parameters as the objective function, determines the optimal emission control parameters, and balances the relationship between multiple indicators through the optimization algorithm to formulate the optimal emission control strategy to achieve intelligent multi-indicator emission control and ensure that the emission parameters remain within the expected range; the present invention realizes intelligent monitoring and control of the condensate discharge of the sterilizer jacket, which can effectively improve production efficiency, ensure the discharge water quality and protect the environment.
[0047] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.
[0049] Figure 1 It is a schematic diagram of the process of the sterilizer jacket condensate discharge control method described in an embodiment of the present invention;
[0050] Figure 2 It is a schematic diagram of the structure of the sterilizer jacket condensate discharge control system described in an embodiment of the present invention;
[0051] Figure 3 It is a schematic diagram of the structure of the sterilizer jacket condensate discharge control device described in an embodiment of the present invention.
[0052] In the figure: 701, acquisition module; 702, construction module; 7021, preprocessing unit; 7022, processing unit; 7023, first fitting unit; 7024, second fitting unit; 703, adjustment module; 7031, prediction unit; 7032, determination unit; 7033, strategy formulation unit; 7034, calculation unit; 70341, definition unit; 70342, normalization processing unit; 70343, design unit; 70344, iteration unit; 704, establishment module; 7041, design strategy unit; 7042, monitoring unit; 7043, judgment unit; 800, sterilizer jacket condensate discharge control device; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION
[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.
[0054] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0055] Embodiment 1:
[0056] This embodiment provides a method for controlling the discharge of condensed water from a sterilizer jacket.
[0057] See also Figure 1 , the figure shows that the method includes step S100, step S200, step S300 and step S400.
[0058] S100. Collecting first monitoring data, wherein the first monitoring data includes jacket temperature, condensate flow rate and water quality components monitored in real time by a temperature sensor, flow meter and water quality sensor installed inside the sterilizer jacket.
[0059] It is understood that in this step, it is assumed that a sterilizer for pharmaceutical production is being processed, and its jacket is equipped with a temperature sensor, a flow meter and a water quality sensor. These sensors monitor various parameters inside the sterilizer jacket in real time. The temperature sensor is responsible for monitoring the temperature of the jacket, the flow meter is used to measure the flow of condensed water, and the water quality sensor monitors the water quality components of the condensed water, such as pH value, dissolved oxygen content, etc. In the process of collecting the first monitoring data, it is first necessary to ensure the normal operation of the sensor. Then, the real-time monitored jacket temperature, condensed water flow rate and water quality components are obtained by reading the data of the sensor. These data are usually stored in digital form, such as temperature in degrees Celsius (℃), flow in liters / minute, and water quality components may be expressed in various different measurement units. After obtaining the data, further processing and analysis can be performed. For example, the average temperature of the condensed water, the total flow rate, and the average value or concentration of various water quality components can be calculated. These calculations can be based on simple statistical methods, such as summation and average calculation, or they can be processed using more complex mathematical models, such as linear regression, time series analysis, etc. These calculations can help understand the operating status of the sterilizer, detect abnormal conditions in a timely manner, and provide data support for subsequent intelligent emission control strategies. In summary, in the process of collecting the first monitoring data, real-time monitoring information inside the sterilizer jacket was obtained by reading the data from the temperature sensor, flow meter, and water quality sensor. Then, these data were processed and analyzed to generate a series of variables and indicators related to the operating status of the sterilizer, providing a data basis for subsequent intelligent emission control.
[0060] S200. Obtain historical data of sterilizer jacket condensate discharge, and use machine learning to build a real-time prediction model for sterilizer jacket condensate production and water quality based on the historical data and the first monitoring data.
[0061] It can be understood that step S200 includes S201, S202, S203 and S204, wherein:
[0062] S201, based on the jacket temperature, condensate flow rate and water quality components monitored in real time by the temperature sensor, flow meter and water quality sensor inside the sterilizer jacket, after data cleaning and feature extraction, an original data set of condensate discharge from the sterilizer jacket for modeling is obtained;
[0063] It should be noted that, first of all, after data cleaning, outliers, missing values and noise in the data are processed to ensure the accuracy and consistency of the data. For example, abnormal temperature values are removed, missing flow data are filled, and water quality data is smoothed to reduce the impact of noise. Next, feature extraction is performed to extract relevant features from the original data for model building. These features can be statistics of single sensor data or correlations or cross-features between different sensors. The following are some calculation formulas and feature extraction processes that may be used, including but not limited to statistical features: Calculate the mean, variance, maximum, minimum and other statistics of jacket temperature, condensate flow and water quality components to describe their distribution and range of variation; Time series features: For time series data (such as temperature and flow), the moving average or moving standard deviation within the sliding window can be calculated to capture its trend and periodicity; Correlation features: Calculate the correlation coefficient between different sensors, such as the correlation between jacket temperature and condensate flow, to evaluate the degree of association between them; Time series pattern features: Use machine learning or time series analysis methods to identify and extract specific time series patterns, such as periodic patterns, trend patterns, etc., to describe the characteristics of sterilizer operation, etc. Through these feature extraction processes, the original real-time monitoring data are converted into feature sets with rich information, providing strong support for subsequent modeling and analysis.
[0064] S202, performing stationarity detection and differential processing on the original data set to obtain stationary time series data;
[0065] It should be noted that according to the original data sets of jacket temperature, condensate flow rate and water quality components monitored in real time by the temperature sensor, flow meter and water quality sensor inside the sterilizer jacket, stationarity detection and differential processing are performed to ensure the stationarity of the time series data and provide a reliable basis for subsequent modeling and analysis. First, a stationarity test is performed on each time series data. The stationarity test aims to determine whether the time series data has a stable mean and variance. Commonly used stationarity test methods include unit root tests (such as ADF tests) and statistical tests based on sliding windows (such as moving average methods). Assume that the time series data of jacket temperature, condensate flow rate and water quality components in the original data set are obtained, denoted as T t 、F t and Q t Next, if the original data sequence is not stationary, it will be differentiated to obtain a stationary time series data; the differential processing can be achieved by calculating the first-order difference (i.e., the difference between the current value and the previous moment value) or the second-order difference of the sequence. The first-order difference is usually used to process a sequence with a linear trend, while the second-order difference is used for a stronger nonlinear trend. The time series data after differential processing is recorded as T t’ 、F t’ and Qt’ .
[0066] S203, based on the time series data, the autoregressive moving average model is used for fitting to obtain model parameters, and the calculation formula is as follows:
[0067] X t =c+φ1X t-1 +φ2X t-2 +…+φ p X t-p +∈ t -θ1∈ t-1 -θ2∈ t-2 -…-θ q ∈ t-q
[0068] In the formula, X t is the observed value at time t, i.e., time series data, c is a constant term, representing the intercept of the model, φ1, φ2, ..., φ p is the autoregressive coefficient, which represents the linear relationship between the current observation and the past p observations, θ1, θ2, ..., θ q is the moving average coefficient, which represents the linear relationship between the previous observation and the past q residual terms, ∈t is white noise, which represents the random disturbance term and obeys the normal distribution with zero mean and constant variance;
[0069] S204. According to the model parameters, after model identification and model fitting, an optimal real-time prediction model for the output and water quality of the condensate of the sterilizer jacket is obtained.
[0070] It is understandable that the model identification of the processed time series data is first performed using machine learning or statistical models. According to the data in the scenario, a suitable prediction model can be selected, such as the autoregressive moving average model (ARIMA), seasonal decomposition model, long short-term memory network, etc. Assume that the ARIMA model is selected for modeling. Next, through the model fitting process, the parameters of the model are estimated so that the model can best fit the historical data and accurately predict the future condensate production and water quality. The ARIMA model is usually represented by three parameters: autoregressive order (p), difference order (d), and moving average order (q). Optimization algorithms, such as grid search or Bayesian optimization, will be used to search for the optimal (p, d, q) combination to maximize the model's fit and prediction accuracy. Through model identification and parameter estimation, the optimal ARIMA model can be obtained, which can accurately predict the changing trend of the sterilizer jacket condensate production and water quality, and provide reliable prediction support for intelligent emission control.
[0071] S300, combines the real-time prediction model and optimization algorithm of the sterilizer jacket condensate production and water quality to dynamically adjust the sterilizer operating parameters.
[0072] It can be understood that step S300 includes S301, S302, S303 and S304, wherein:
[0073] S301. Using the real-time prediction model of the output and water quality of the sterilizer jacket condensate, combined with the real-time monitored jacket temperature, condensate flow rate and water quality component data, the discharge parameters of the sterilizer jacket condensate in the future period are predicted, wherein the discharge parameters include the output and water quality;
[0074] S302, according to a multi-objective optimization algorithm, using the emission parameters as the objective function to determine the optimal emission control parameters;
[0075] It should be noted that the established real-time prediction model is first used to predict the production and water quality of the sterilizer jacket condensate in the future period of time in combination with the real-time monitored jacket temperature, condensate flow rate and water quality composition data. Assuming that the ARIMA model is used for prediction, the predicted value for the future period of time can be obtained based on historical data and real-time monitoring data. Next, the optimal emission control parameters can be determined by taking the predicted sterilizer jacket condensate production and water quality as the objective function and combining it with a multi-objective optimization algorithm. The predicted sterilizer jacket condensate production and water quality are used as the objective function. Considering that emission control needs to consider multiple indicators of production and water quality at the same time, multi-objective optimization algorithms can be used, such as multi-objective genetic algorithms or multi-objective particle swarm optimization algorithms. These algorithms can search for a set of optimal emission control parameters so that the production and water quality of the sterilizer jacket condensate can achieve the best comprehensive effect.
[0076] Specifically, the objective functions of production and water quality can be normalized so as to be uniformly processed in the multi-objective optimization algorithm, and a set of optimal emission control parameters can be searched using the multi-objective optimization algorithm to realize intelligent multi-index emission control.
[0077] S303, based on the optimal emission control parameters, obtaining a real-time emission control strategy through real-time monitoring data and feedback mechanism;
[0078] It is understandable that the determined optimal emission control parameters, combined with the real-time monitored jacket temperature, condensate flow and water quality composition data, are used for real-time analysis and feedback through the intelligent control system. According to the currently monitored data and optimal parameters, the emission control strategy is dynamically adjusted to ensure that the output and water quality of the sterilizer jacket condensate are within the preset target range.
[0079] S304. According to the emission control strategy, the actual operating parameters of the sterilizer are obtained through the intelligent control system, thereby realizing real-time multi-objective emission control.
[0080] It should be noted that, according to the real-time emission control strategy, the intelligent control system adjusts the operating parameters of the sterilizer, including temperature, pressure, ventilation rate, etc., to achieve multi-objective emission control of the output and water quality of the sterilizer jacket condensate. Through real-time monitoring and adjustment of the intelligent control system, the actual operating parameters of the sterilizer can dynamically respond to changes in the emission control strategy to ensure that the discharged water quality and output meet the expected targets.
[0081] It can be understood that step S304 includes S3041, S3042, S3043 and S3044, wherein:
[0082] S3041. Define two parts of production and water quality as objective functions;
[0083] S3042, normalize the objective function to obtain the first objective function and the second objective function, whose calculation formulas are as follows:
[0084]
[0085] In the formula, f 1’ is the first objective function after normalization, i.e. the normalized value of condensate production; f 2’ is the normalized second objective function, i.e., the normalized value of water quality; f1 is the original first objective function, i.e., the condensate output; f2 is the original second objective function, i.e., water quality; min(f1) is the minimum value of the first objective function; max(f1) is the maximum value of the first objective function; min(f2) is the minimum value of the second objective function; max(f2) is the maximum value of the second objective function;
[0086] S3043. Based on the first objective function and the second objective function, a fitness function is designed, and a set of initial operation parameter combinations are randomly generated as initial individuals of the population, wherein the fitness function is calculated as follows:
[0087] Fitness=w1×f′1+w2×f′2
[0088] In the formula, Fitness is the fitness of the individual, W1 is the weight of the first objective function, W2 is the weight of the second objective function, and f 1’ is the normalized value of condensate production, f 2’ is the normalized value of water quality;
[0089] S3044. Based on the initial individuals, their fitness values are calculated through crossover and mutation operations, and the roulette wheel selection algorithm is used to select excellent individuals as the parents of the next generation population, and iterative optimization is performed until the stopping condition is reached, and the final output is used as the optimal emission control parameter, where the stopping condition is reaching the maximum number of iterations or satisfying the convergence condition.
[0090] It should be noted that, in this embodiment, the yield and water quality are the targets we need to control and optimize, and the yield and water quality are defined as two parts of the objective function, wherein the yield can be represented by the yield function, and the water quality can be represented by the water quality function. The yield function and the water quality function need to be normalized so that they can be uniformly processed in the optimization algorithm. After normalization, the first objective function (the normalized result of the yield function) and the second objective function (the normalized result of the water quality function) are obtained, and the fitness function is designed to combine the optimization targets of the yield and the water quality. Here, the weighted sum can be used to balance the relationship between the yield and the water quality; then a set of initial operating parameter combinations are randomly generated as the initial individuals of the population; in each generation, the individuals in the population are crossover and mutation operations are performed to generate new individuals; then, the fitness value of each individual is calculated, and the roulette selection algorithm is used to select excellent individuals as the parents of the next generation of the population, and this process is repeated until the stopping condition is reached, and the stopping condition can be reaching the maximum number of iterations or satisfying the convergence condition. The individuals finally obtained are the optimal emission control parameters to achieve multi-objective emission control of sterilizer jacket condensate.
[0091] S400. Based on the operating parameters of the sterilizer, formulate an intelligent emission control strategy and establish a condensate emission monitoring system to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm will be issued. If it does not drop or exceed the preset threshold, monitoring will continue.
[0092] It can be understood that the step S400 includes S401, S402 and S403, wherein:
[0093] S401. Design intelligent emission control strategy using optimization algorithm based on sterilizer operating parameters and historical data;
[0094] It should be noted that in this embodiment, the operating parameters and historical data of the sterilizer are used to design an intelligent emission control strategy through an optimization algorithm. A multi-objective optimization algorithm can be used, such as a multi-objective genetic algorithm or a multi-objective particle swarm optimization algorithm; the optimization algorithm can be used to balance the relationship between multiple indicators such as condensate production and water quality, and formulate an optimal emission control strategy. Among them, the selection of the optimization algorithm is crucial, and a variety of optimization algorithms can be used, such as genetic algorithms, particle swarm optimization algorithms or simulated annealing algorithms; these algorithms can search for the optimal combination of operating parameters based on given objective functions and constraints, thereby achieving the best emission control effect.
[0095] Specifically, the operating parameters of the sterilizer can be used as variables, and indicators such as condensate production and water quality can be used as objective functions. The optimal operating parameter settings can be solved through the optimization algorithm, so that an intelligent emission control strategy can be formulated to achieve efficient emission management of sterilizer jacket condensate, ensure compliance with emission water quality, and minimize the impact on the environment.
[0096] S402, establishing a condensate discharge monitoring system to monitor real-time discharge data, and transmitting the real-time discharge data to a central processing unit for analysis and processing to obtain processing results, wherein the condensate discharge monitoring system includes sensors, data acquisition equipment, and a data storage system;
[0097] It should be noted that in order to achieve intelligent emission control, it is necessary to establish a condensate emission monitoring system, which includes a sensor installed inside the sterilizer jacket for real-time monitoring of the jacket temperature, condensate flow rate and water quality composition; the real-time emission data monitored is transmitted to the central processing unit through the data acquisition device for analysis and processing; the data acquisition device stores the real-time data in the data storage system, and the central processing unit processes and analyzes the data to obtain processing results for formulating intelligent emission control strategies.
[0098] S403. Based on the comparison of the processing results with the pre-set standards, by comparing the monitoring data with the standard value, it is determined whether the emission data is within the expected range; if the monitored emission data drops or exceeds the preset threshold, the system will issue an alarm to prompt the operator to process or adjust; if the emission data is within the expected range, the system will continue to monitor and update the intelligent emission control strategy as needed.
[0099] It should be noted that, based on the comparison of the treatment results with the preset standards, the system will analyze whether the real-time monitored emission data is within the expected range. This includes comparison with pre-set standard values to ensure that parameters such as discharge water quality and output meet the specified requirements. If the monitored emission data is abnormal, such as a drop or exceeding the preset threshold, the system will immediately trigger an alarm to prompt the operator to handle or adjust to prevent the problem from further deteriorating; if the emission data is within the expected range, the system will continue to monitor and update the intelligent emission control strategy as needed. This means that the system will continuously analyze and evaluate the monitoring data to adjust the emission control strategy in a timely manner to adapt to environmental changes or optimize the emission effect. Through such a monitoring and feedback mechanism, the system can ensure that the discharge of the sterilizer jacket condensate is always in compliance with the standards, thereby ensuring the smooth progress of the production process while minimizing the impact on the environment.
[0100] Embodiment 2:
[0101] like Figure 2 As shown, this embodiment provides a sterilizer jacket condensate discharge control system, see Figure 2 The system comprises:
[0102] Collection module 701: used to collect first monitoring data, wherein the first monitoring data includes jacket temperature, condensate flow rate and water quality components monitored in real time by a temperature sensor, flow meter and water quality sensor installed inside the sterilizer jacket;
[0103] Construction module 702: used to obtain historical data of the discharge of condensed water from the sterilizer jacket, and to construct a real-time prediction model of the output and water quality of the condensed water from the sterilizer jacket by using machine learning based on the historical data and the first monitoring data;
[0104] Adjustment module 703: used to dynamically adjust the operating parameters of the sterilizer by combining the real-time prediction model and optimization algorithm of the condensate output and water quality of the sterilizer jacket;
[0105] Establish module 704: used to formulate intelligent emission control strategies based on the operating parameters of the sterilizer and establish a condensate emission monitoring system to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm is issued; if it does not drop or exceed the preset threshold, monitoring continues.
[0106] Specifically, the building block 702 includes:
[0107] Preprocessing unit 7021: used to obtain the original data set of the sterilizer jacket condensate discharge for modeling based on the jacket temperature, condensate flow rate and water quality components monitored in real time by the temperature sensor, flow meter and water quality sensor inside the sterilizer jacket, through data cleaning and feature extraction;
[0108] Processing unit 7022: used to perform stationarity detection and differential processing on the original data set to obtain stable time series data;
[0109] The first fitting unit 7023 is used to fit the time series data through the autoregressive moving average model to obtain model parameters, and the calculation formula is as follows:
[0110] X t =c+φ1X t-1 +φ2X t-2 +…+φ p X t-p +∈ t -θ1∈ t-1 -θ2∈ t-2 …-θ q ∈ t-q
[0111] In the formula, X t is the observed value at time t, i.e., time series data, c is a constant term, representing the intercept of the model, φ1, φ2, ..., φ p is the autoregressive coefficient, which represents the linear relationship between the current observation and the past p observations, θ1, θ2, ..., θ q is the moving average coefficient, which represents the linear relationship between the previous observation and the past q residual terms, ∈t is white noise, which represents the random disturbance term and obeys the normal distribution with zero mean and constant variance;
[0112] The second fitting unit 7024 is used to obtain the optimal real-time prediction model of the sterilizer jacket condensate output and water quality according to the model parameters through model identification and model fitting.
[0113] Specifically, the adjustment module 703 includes:
[0114] Prediction unit 7031: used to use the real-time prediction model of the output and water quality of the sterilizer jacket condensate, combined with the real-time monitored jacket temperature, condensate flow and water quality component data, to predict the discharge parameters of the sterilizer jacket condensate in the future period, wherein the discharge parameters include the output and water quality;
[0115] Determining unit 7032: used to determine the optimal emission control parameter according to the multi-objective optimization algorithm, taking the emission parameter as the objective function;
[0116] Strategy formulation unit 7033: used to obtain real-time emission control strategy based on optimal emission control parameters through real-time monitoring data and feedback mechanism;
[0117] Calculation unit 7034: used to obtain the actual operating parameters of the sterilizer through the intelligent control system according to the emission control strategy, so as to achieve real-time multi-objective emission control.
[0118] Specifically, the computing unit 7034 includes:
[0119] Definition unit 70341: used to define two parts of the yield and water quality conditions as the objective function;
[0120] Normalization processing unit 70342: used to normalize the objective function to obtain the first objective function and the second objective function, and the calculation formula is as follows:
[0121]
[0122] In the formula, f 1’ is the first objective function after normalization, i.e. the normalized value of condensate production; f 2’ is the normalized second objective function, i.e., the normalized value of water quality; f1 is the original first objective function, i.e., the condensate output; f2 is the original second objective function, i.e., water quality; min(f1) is the minimum value of the first objective function; max(f1) is the maximum value of the first objective function; min(f2) is the minimum value of the second objective function; max(f2) is the maximum value of the second objective function;
[0123] Design unit 70343: used to design a fitness function based on the first objective function and the second objective function, and randomly generate a set of initial operation parameter combinations as initial individuals of the population, wherein the fitness function is calculated as follows:
[0124] Fitness=w1×f′1+w2×f′2
[0125] In the formula, Fitness is the fitness of the individual, W1 is the weight of the first objective function, W2 is the weight of the second objective function, and f 1’ is the normalized value of condensate production, f 2’ is the normalized value of water quality;
[0126] Iteration unit 70344: used to calculate the fitness value of the initial individuals through crossover and mutation operations, select excellent individuals as the parents of the next generation population using the roulette selection algorithm, and perform iterative optimization until the stopping condition is reached, and use the final output as the optimal emission control parameter, wherein the stopping condition is reaching the maximum number of iterations or satisfying the convergence condition.
[0127] Specifically, the establishment module 704 includes:
[0128] Design strategy unit 7041: used to design intelligent emission control strategies based on the sterilizer's operating parameters and historical data using optimization algorithms;
[0129] Monitoring unit 7042: used to establish a condensate discharge monitoring system, monitor real-time discharge data, and transmit the real-time discharge data to the central processing unit 7022 for analysis and processing to obtain processing results, wherein the condensate discharge monitoring system includes sensors, data acquisition equipment and data storage systems;
[0130] Judgment unit 7043: used to compare the processing results with the pre-set standards, and judge whether the emission data is within the expected range by comparing the monitored data with the standard value; if the monitored emission data drops or exceeds the preset threshold, the system will issue an alarm to prompt the operator to process or adjust; if the emission data is within the expected range, the system will continue to monitor and update the intelligent emission control strategy as needed.
[0131] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0132] Embodiment 3:
[0133] Corresponding to the above method embodiment, a sterilizer jacket condensate discharge control device is also provided in this embodiment. The sterilizer jacket condensate discharge control device described below and the sterilizer jacket condensate discharge control method described above can be referred to each other.
[0134] Figure 3 FIG. 8 is a block diagram of a sterilizer jacket condensate discharge control device 800 according to an exemplary embodiment. Figure 3 As shown, the sterilizer jacket condensate discharge control device 800 includes: a processor 801 and a memory 802. The sterilizer jacket condensate discharge control device 800 also includes one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.
[0135] The processor 801 is used to control the overall operation of the sterilizer jacket condensate discharge control device 800 to complete all or part of the steps in the above-mentioned sterilizer jacket condensate discharge control method. The memory 802 is used to store various types of data to support the operation of the sterilizer jacket condensate discharge control device 800, and these data may include, for example, instructions for any application or method operated on the sterilizer jacket condensate discharge control device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be a keyboard, a mouse or buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the sterilizer jacket condensate discharge control device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: a Wi-Fi module, a Bluetooth module or an NFC module.
[0136] In an exemplary embodiment, the sterilizer jacket condensate discharge control device 800 can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processing Device, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned sterilizer jacket condensate discharge control method.
[0137] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned sterilizer jacket condensate discharge control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the sterilizer jacket condensate discharge control device 800 to complete the above-mentioned sterilizer jacket condensate discharge control method.
[0138] Embodiment 4:
[0139] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the sterilizer jacket condensate discharge control method described above can refer to each other.
[0140] A computer program is stored on the readable storage medium, and when the computer program is executed by the processor, the steps of the sterilizer jacket condensate discharge control method of the above method embodiment are implemented.
[0141] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.
[0142] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
[0143] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
Claims
1. A method for controlling the discharge of condensed water from a sterilizer jacket, characterized in that: include: Collecting first monitoring data, wherein the first monitoring data includes jacket temperature, condensate flow rate and water quality components monitored in real time by a temperature sensor, flow meter and water quality sensor installed inside the sterilizer jacket; Obtain historical data on the discharge of condensate from the sterilizer jacket, and use machine learning to build a real-time prediction model for the output and quality of condensate from the sterilizer jacket based on the historical data and the first monitoring data; Combined with the real-time prediction model and optimization algorithm of the sterilizer jacket condensate production and water quality, the operating parameters of the sterilizer are dynamically adjusted; Based on the operating parameters of the sterilizer, an intelligent emission control strategy is formulated and a condensate emission monitoring system is established to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm is issued. If it does not drop or exceed the preset threshold, monitoring continues.
2. The method for controlling the discharge of condensed water from the sterilizer jacket according to claim 1, characterized in that: The method obtains historical data of the discharge of the condensed water from the sterilizer jacket, and uses machine learning to construct a real-time prediction model for the output and water quality of the condensed water from the sterilizer jacket based on the historical data and the first monitoring data, including: Based on the jacket temperature, condensate flow rate and water quality components monitored in real time by the temperature sensor, flow meter and water quality sensor inside the sterilizer jacket, the original data set of the sterilizer jacket condensate discharge for modeling is obtained through data cleaning and feature extraction; Perform stationarity detection and differential processing on the original data set to obtain stable time series data; Based on the time series data, the autoregressive moving average model is used to fit the model parameters, and the calculation formula is as follows: X t =c+φ1X t-1 +φ2X t-2 +…+φ p X t-p +∈ t -θ1∈ t-1 -θ2∈ t-2 -…-θ q ∈ t-q Where, X t is the observed value at time t, i.e., time series data, c is a constant term, representing the intercept of the model, φ1, φ2, ..., φ p is the autoregressive coefficient, which represents the linear relationship between the current observation and the past p observations, θ1, θ2, ..., θ q is the moving average coefficient, which represents the linear relationship between the previous observation and the past q residual terms, ∈t is white noise, which represents the random disturbance term and obeys the normal distribution with zero mean and constant variance; According to the model parameters, after model identification and model fitting, the optimal real-time prediction model of the sterilizer jacket condensate production and water quality is obtained.
3. The method for controlling the discharge of condensed water from the sterilizer jacket according to claim 1, characterized in that: The real-time prediction model and optimization algorithm for the production and quality of condensate from the jacket of the sterilizer are combined to dynamically adjust the operating parameters of the sterilizer, including: Using the real-time prediction model of the output and water quality of the sterilizer jacket condensate, combined with the real-time monitored jacket temperature, condensate flow and water quality composition data, the discharge parameters of the sterilizer jacket condensate in the future are predicted, where the discharge parameters include output and water quality; According to the multi-objective optimization algorithm, the emission parameters are used as the objective function to determine the optimal emission control parameters; Based on the optimal emission control parameters, through real-time monitoring data and feedback mechanism, a real-time emission control strategy is obtained; According to the emission control strategy, the actual operating parameters of the sterilizer are obtained through the intelligent control system, thereby realizing real-time multi-objective emission control.
4. The method for controlling the discharge of condensed water from the sterilizer jacket according to claim 3, characterized in that: According to the multi-objective optimization algorithm, the emission parameters are used as the objective function to determine the optimal emission control parameters, including: Define the two parts of production and water quality as the objective function; The objective function is normalized to obtain the first objective function and the second objective function, and their calculation formulas are as follows: In the formula, f 1’ is the first objective function after normalization, i.e. the normalized value of condensate production; f 2’ is the normalized second objective function, i.e., the normalized value of water quality; f1 is the original first objective function, i.e., the condensate output; f2 is the original second objective function, i.e., water quality; min(f1) is the minimum value of the first objective function; max(f1) is the maximum value of the first objective function; min(f2) is the minimum value of the second objective function; max(f2) is the maximum value of the second objective function; Based on the first objective function and the second objective function, a fitness function is designed, and a set of initial operating parameter combinations are randomly generated as the initial individuals of the population. The calculation formula of the fitness function is as follows: Fitness=w1×f′1+w2×f′2 In the formula, Fitness is the fitness of the individual, W1 is the weight of the first objective function, W2 is the weight of the second objective function, and f 1’ is the normalized value of condensate production, f 2’ is the normalized value of water quality; According to the initial individuals, their fitness values are calculated through crossover and mutation operations, and the roulette wheel selection algorithm is used to select excellent individuals as the parents of the next generation population. The iterative optimization is carried out until the stopping condition is reached, and the final output is used as the optimal emission control parameter, where the stopping condition is reaching the maximum number of iterations or satisfying the convergence condition.
5. The method for controlling the discharge of condensed water from the sterilizer jacket according to claim 1, characterized in that: Based on the operating parameters of the sterilizer, an intelligent emission control strategy is formulated and a condensate emission monitoring system is established to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm is issued. If it does not drop or exceed the preset threshold, monitoring continues, including: Based on the sterilizer's operating parameters and historical data, an optimization algorithm is used to design an intelligent emission control strategy; Establish a condensate discharge monitoring system to monitor real-time discharge data, transmit the real-time discharge data to a central processing unit for analysis and processing, and obtain processing results, wherein the condensate discharge monitoring system includes sensors, data acquisition equipment, and data storage systems; Based on the comparison between the processing results and the pre-set standards, the system determines whether the emission data is within the expected range by comparing the monitored data with the standard value; if the monitored emission data drops or exceeds the preset threshold, the system will issue an alarm to prompt the operator to process or adjust; if the emission data is within the expected range, the system will continue to monitor and update the intelligent emission control strategy as needed.
6. A sterilizer jacket condensate discharge control system, based on the sterilizer jacket condensate discharge control method according to claim 1, characterized in that: include: Acquisition module: used to collect first monitoring data, wherein the first monitoring data includes jacket temperature, condensate flow rate and water quality components monitored in real time by a temperature sensor, flow meter and water quality sensor installed inside the sterilizer jacket; Construction module: used to obtain historical data of sterilizer jacket condensate discharge, and build a real-time prediction model of sterilizer jacket condensate output and water quality by machine learning based on historical data and first monitoring data; Adjustment module: used to dynamically adjust the operating parameters of the sterilizer by combining the real-time prediction model and optimization algorithm of the sterilizer jacket condensate production and water quality; Establishment module: It is used to formulate intelligent emission control strategies based on the operating parameters of the sterilizer and establish a condensate emission monitoring system to determine whether the monitored emission data meets the standards. If it drops or exceeds the preset threshold, an alarm will be issued. If it does not drop or exceed the preset threshold, monitoring will continue.
7. The sterilizer jacket condensate discharge control system according to claim 6, characterized in that: The building blocks include: Preprocessing unit: used to obtain the original data set of the sterilizer jacket condensate discharge for modeling based on the jacket temperature, condensate flow rate and water quality components monitored in real time by the temperature sensor, flow meter and water quality sensor inside the sterilizer jacket, through data cleaning and feature extraction; Processing unit: used to perform stationarity detection and differential processing on the original data set to obtain stable time series data; The first fitting unit is used to fit the time series data through the autoregressive moving average model to obtain the model parameters. The calculation formula is as follows: X t =c+φ1X t-1 +φ2X t-2 +…+φ p X t-p +∈ t -θ1∈ t-1 -θ2∈ t-2 -…-θ q ∈ t-q Where, X t is the observed value at time t, i.e., time series data, c is a constant term, representing the intercept of the model, φ1, φ2, ..., φ p is the autoregressive coefficient, which represents the linear relationship between the current observation and the past p observations, θ1, θ2, ..., θ q is the moving average coefficient, which represents the linear relationship between the previous observation and the past q residual terms, ∈t is white noise, which represents the random disturbance term and obeys the normal distribution with zero mean and constant variance; The second fitting unit is used to obtain the optimal real-time prediction model of the sterilizer jacket condensate output and water quality according to the model parameters through model identification and model fitting.
8. The sterilizer jacket condensate discharge control system according to claim 6, characterized in that: The adjustment module includes: Prediction unit: used to use the real-time prediction model of the output and water quality of the sterilizer jacket condensate, combined with the real-time monitored jacket temperature, condensate flow and water quality composition data, to predict the discharge parameters of the sterilizer jacket condensate in the future, where the discharge parameters include output and water quality; Determination unit: used to determine the optimal emission control parameters according to the multi-objective optimization algorithm, taking the emission parameters as the objective function; Strategy formulation unit: used to obtain real-time emission control strategies based on optimal emission control parameters through real-time monitoring data and feedback mechanism; Calculation unit: used to obtain the actual operating parameters of the sterilizer through the intelligent control system according to the emission control strategy, so as to achieve real-time multi-objective emission control.
9. A sterilizer jacket condensate discharge control device, characterized in that: include: Memory for storing computer programs; A processor, used to implement the sterilizer jacket condensate discharge control method as described in any one of claims 1 to 5 when executing the computer program.
10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for controlling the discharge of condensate from a sterilizer jacket as claimed in any one of claims 1 to 5 is implemented.
