A method and system for intelligently controlling the temperature of disinfectant production

Through the intelligent control system, the temperature is dynamically adjusted based on the process analysis of the disinfectant production process and the characteristics of the material composition, which solves the problem of inaccurate temperature control in the disinfectant production and improves product quality and consistency.

CN118331352BActive Publication Date: 2024-11-22JIANGSU YUNJI ZHIZAO HOUSEHOLD PROD CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410594938.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-14
Publication Date
2024-11-22
Estimated Expiration
2044-05-14

AI Technical Summary

Technical Problem

During the disinfectant production process, temperature control cannot accurately adapt to the specific temperature range of different materials, resulting in unstable product quality.

Method used

Using intelligent control methods and systems, through process analysis modules, goal determination modules, dynamic monitoring modules, temperature prediction modules and dynamic control modules, dynamic temperature adjustment based on material composition characteristics and real-time data, ensure that the temperature in each production stage is optimal. Within range.

Benefits of technology

It realizes accurate control of temperature during the disinfectant production process, improves product quality and consistency, reduces the loss of active ingredients caused by improper temperature, and improves the accuracy and timeliness of temperature control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118331352B_ABST
    Figure CN118331352B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of intelligent production control technology, and specifically includes an intelligent control method and system for disinfectant production temperature, comprising: in the disinfectant production process, for different stages, adjusting the first stage preset temperature to the target temperature based on the first material component, and collecting actual temperature and timing operation status data, predicting the temperature trend, and triggering the temperature control instruction when the predicted value deviates from the target temperature; generating temperature control decisions and performing dynamic temperature control to solve the technical problem that the disinfectant production temperature cannot accurately adapt to the specific temperature range required by various production materials in the disinfectant, resulting in unstable product quality, and achieving the goal of dynamically setting and maintaining the optimal target temperature of each stage based on the specificity of material components, accurately predicting the temperature change trend, and quickly generating control instructions when the predicted temperature deviates from the target temperature, effectively executing dynamic temperature adjustment, thereby ensuring the technical effect of product quality and consistency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field related to intelligent production control, and in particular to an intelligent control method and system for the production temperature of a disinfectant. Background Art

[0002] In the production process of disinfectants, temperature control is a crucial operating parameter. Commonly, the disinfectant production process usually relies on programmed temperature control. For example, temperature sensors such as thermocouples and thermistors are used to monitor the temperature inside the reactor in real time, and the data is transmitted to the control panel. Feedback control is performed based on the current temperature conditions, but the characteristics and temperature sensitivity of each raw material are ignored. In addition, the ingredients of various disinfectants are different, and the corresponding chemical reaction activity is significantly affected by temperature. Therefore, it is necessary to accurately and timely control the temperature in the production process to ensure that the active ingredients of the disinfectant can be effectively synthesized and not destroyed.

[0003] In summary, the prior art has a technical problem that the production temperature of the disinfectant cannot accurately adapt to the specific temperature range required by various production materials in the disinfectant, resulting in unstable product quality. Summary of the invention

[0004] The present application provides an intelligent control method and system for the production temperature of disinfectants, aiming to solve the technical problem in the prior art that the production temperature of disinfectants cannot accurately adapt to the specific temperature range required by various production materials in the disinfectants, resulting in unstable product quality.

[0005] In view of the above problems, the technical solution to implement this application is:

[0006] In one aspect, the present application provides an intelligent control method for disinfectant production temperature, wherein the method comprises: analyzing the disinfectant production process with a predetermined production temperature as a constraint, and dividing it to obtain a production stage set;

[0007] adjusting a first predetermined temperature of a first production stage based on first component characteristic information of a first production material to obtain a first target temperature, wherein the first production stage is any stage in the production stage set;

[0008] Dynamically monitoring the first actual temperature sequence of the first production stage by a temperature monitoring device group;

[0009] Dynamically monitoring the state monitoring equipment group to obtain a first operating state sequence of the first production equipment in the first production stage;

[0010] Analyze the first actual temperature time series and the first temperature control parameter time series in the first operating state time series through an intelligent temperature prediction model to obtain a first predicted temperature;

[0011] If the first predicted temperature does not meet the first target temperature, generating a first temperature control instruction;

[0012] The intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction, and the first temperature control decision is used to perform dynamic temperature control on the first production stage.

[0013] In another aspect, the present application provides an intelligent control system for disinfectant production temperature, wherein the system comprises: a process analysis module, for analyzing the disinfectant production process with a predetermined production temperature as a constraint, and dividing it into a production stage set;

[0014] a target determination module, configured to adjust a first predetermined temperature of a first production stage based on first component characteristic information of a first production material to obtain a first target temperature, wherein the first production stage is any stage in the production stage set;

[0015] A first dynamic monitoring module, configured to dynamically monitor a first actual temperature sequence of the first production stage through a temperature monitoring device group;

[0016] A second dynamic monitoring module, configured to dynamically monitor a first operating state sequence of a first production device in the first production stage through a state monitoring device group;

[0017] a temperature prediction module, configured to analyze the first actual temperature time series and the first temperature control parameter time series in the first operating state time series through an intelligent temperature prediction model to obtain a first predicted temperature;

[0018] An instruction generating module, configured to generate a first temperature control instruction if the first predicted temperature does not meet the first target temperature;

[0019] A dynamic control module is used for the intelligent temperature control model to generate a first temperature control decision based on the first temperature control instruction, and the first temperature control decision is used to perform dynamic temperature control on the first production stage.

[0020] In summary, one or more technical solutions provided in this application achieve the goal of dynamically setting and maintaining the optimal target temperature at each stage based on the specificity of material components, accurately predict the temperature change trend through real-time monitoring and analysis of temperature timing and equipment operating status, and quickly generate control instructions when the predicted temperature deviates from the target temperature, effectively perform dynamic temperature adjustment, thereby ensuring the technical effect of product quality and consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A possible flow chart of a method for intelligently controlling the temperature of disinfectant production is provided for this application.

[0022] Figure 2 The present application provides a possible flow chart of a smart temperature prediction model in a smart control method for disinfectant production temperature.

[0023] Figure 3 A possible structural schematic diagram of an intelligent control system for disinfectant production temperature is provided for this application.

[0024] Explanation of the reference numerals: process analysis module M100 , target determination module M200 , first dynamic monitoring module M300 , second dynamic monitoring module M400 , temperature prediction module M500 , instruction generation module M600 , dynamic control module M700 . DETAILED DESCRIPTION

[0025] Embodiment 1

[0026] The present application is described in detail below with reference to the accompanying drawings. Figure 1 As shown, the present application provides an intelligent control method for the production temperature of a disinfectant, wherein the method comprises:

[0027] Step-1: Analyze the disinfectant production process with the predetermined production temperature as a constraint and divide it into a set of production stages;

[0028] Step-2: adjusting the first predetermined temperature of the first production stage based on the first component characteristic information of the first production material to obtain a first target temperature, wherein the first production stage is any stage in the production stage set;

[0029] It is known that although the existing disinfectant production equipment adopts program temperature control and combines temperature sensors for real-time monitoring, it may not be able to accurately adapt to the specific temperature range required by various production materials of the disinfectant in actual operation. In particular, for those reaction processes that are extremely sensitive to temperature, there may be hysteresis or overshoot, resulting in unstable quality of disinfectant products or loss of active ingredients;

[0030] Through the above description, further analysis is made: various production materials of disinfectants have their own physical and chemical properties and temperature sensitivity. These differences are not fully considered in the process of programmed temperature control, and there is a lack of ability to dynamically adjust the characteristics of different production materials; the chemical reaction rate in the preparation process of disinfectants will change significantly with temperature changes. The temperature change characteristics of chemical reactions are not fully considered in the process of programmed temperature control, and it is impossible to achieve efficient catalysis within the optimal temperature range and protect the active ingredients from high-temperature decomposition;

[0031] Based on this, the present application automatically adjusts the production temperature according to the various production materials and production material characteristics in the disinfectant formula, realizes precise control of the temperature during the disinfectant production process, ensures that the reaction conditions are always in the most suitable state, thereby improving the quality and consistency of the final product. Specifically, the predetermined production temperature is used as the control condition, and a detailed analysis is conducted in combination with the entire disinfectant production process. Further, the disinfectant production process is divided into a plurality of production stage sets with specific functions and temperature requirements, such as a first constant temperature stage, a first temperature change stage, a second constant temperature stage, etc.;

[0032] Further, exemplary: the first constant temperature stage is mostly used to process raw material preheating, and the initial preset temperature is set based on production experience. Further, based on the specific component characteristics of the first production material, especially the key component information that affects the reaction rate and product purity (such as part of the reaction catalyst), the first predetermined temperature of the first production stage is scientifically corrected, and the first target temperature that meets the first production material is calculated to ensure the best reaction conditions and product quality; in the first temperature change stage, the temperature needs to change according to a certain curve or procedure to adapt to the chemical reaction requirements. Similarly, considering the influence of the component characteristics of the first production material on the temperature change rate and the final temperature, the temperature change strategy is finely adjusted to match the temperature change strategy with the properties of the first production material, thereby ensuring a smooth and efficient reaction process; the second constant temperature stage, the second temperature change stage and the subsequent constant temperature / temperature change stages, similarly, for all subsequent production stages, whether it is a constant temperature maintenance or a temperature change process, the same method will be used, combined with the material component characteristics used in the corresponding stage, and the predetermined temperature of each stage will be personalized to make the temperature closer to the actual production requirements;

[0033] In summary, it includes: obtaining the component analysis information of the first production material, identifying the key factors affecting the production process in the component analysis information of the first production material (the first component characteristic information belongs to one of the component analysis information of the first production material, taking the first component characteristic information as an example, and at the same time, the items in the component analysis information of the first production material are arranged in descending order according to the critical degree of affecting the production process, wherein the first component characteristic information is ranked in the first position); using the expert knowledge base to analyze the relationship between the component characteristics of the first production material and the required temperature, and calculating the ideal target temperature of each stage (taking the first stage as an example, the first production stage is any stage in the production stage set), and taking the ideal target temperature corresponding to the first stage as the first target temperature, wherein the first predetermined temperature of the first production stage refers to the initial temperature information of the first production stage; dividing the disinfectant production process into multiple production stages, comparing each production stage, analyzing and determining the corresponding target temperature, and taking the target temperature obtained by analysis as the benchmark for subsequent intelligent regulation, and at the same time, taking the target temperature as the benchmark for intelligent regulation to improve the rationality of the benchmark.

[0034] Step-3: Dynamically monitor the first actual temperature sequence of the first production stage through the temperature monitoring equipment group;

[0035] Step-4: dynamically monitoring the state monitoring equipment group to obtain the first operating state sequence of the first production equipment in the first production stage;

[0036] Step-5: Analyze the first actual temperature time series and the first temperature control parameter time series in the first operating state time series through an intelligent temperature prediction model to obtain a first predicted temperature;

[0037] In the first production stage corresponding to the production of disinfectants, a temperature monitoring equipment group is installed and configured, such as thermocouples, infrared temperature sensors or wireless temperature sensor networks, to continuously collect actual temperature data of multiple key points in the first production stage (such as heating equipment, cooling equipment, agitators and other related disinfectant production equipment), and form a real-time first actual temperature time series record; similarly, in the first production stage, a status monitoring equipment group is installed and enabled to monitor and record various operating status parameters of multiple types of disinfectant production equipment, such as the power output of the heating equipment, the cooling efficiency of the cooling equipment, the speed of the agitator, etc., to form the first operating status time series data of the first production equipment;

[0038] Based on the timestamp information corresponding to the first actual temperature time series, in the first operating state time series of the first production equipment in the first production stage, the first temperature control parameter time series in the first operating state time series is located and obtained, the timestamp information of the first temperature control parameter time series is consistent with the timestamp information corresponding to the first actual temperature time series, and according to the corresponding relationship of the timestamp information (timestamp synchronization), the data in the first actual temperature time series is associated and integrated with the data in the first temperature control parameter time series, and then, the trained intelligent temperature prediction model is used, and the associated and integrated data is used as an input variable to analyze the dynamic relationship between the data in the first actual temperature time series and the data in the first temperature control parameter time series and the impact on the temperature change trend;

[0039] Exemplarily, based on the data in the monitored first actual temperature time series and the data in the predetermined first temperature control parameter time series, the temperature change in the next period of time is predicted. For example, the predetermined target temperature of the equipment is 300 degrees, but the currently monitored temperature is 180 degrees, and it is determined that the heating equipment is running at a certain power. The intelligent temperature prediction model will predict based on the existing data that the temperature will continue to rise until it reaches the predetermined target temperature of 300 degrees. The first predicted temperature refers to the predicted temperature corresponding to the next time node (if the acquisition frequency of the temperature monitoring equipment group and the state monitoring equipment group is 60Hz, the corresponding next time node is the next 1S). The first predicted temperature is closely related to the power of the heating equipment, the state of the cooling equipment, the speed of the agitator, and other environmental factors that may affect the temperature change (such as room temperature, humidity, etc.);

[0040] Furthermore, constructing an intelligent temperature prediction model also includes: collecting historical data, which includes but is not limited to actual temperature time series data of each production stage and various equipment temperature control parameters related to temperature control (such as heating equipment power, cooling equipment working status, agitator speed and other related disinfectant production equipment); extracting effective features from historical data, such as temperature change rate, equipment state switching frequency, temperature response curves under different states, etc., to construct time series features, such as lag terms (temperature at the previous time node), sliding window statistics (average temperature, maximum and minimum temperatures, etc.); selecting a suitable prediction model framework, which can be a common statistical method (such as autoregressive model AR, moving average model MA, autoregressive moving average model ARMA, autoregressive integrated moving average model ARIMA), or a modern machine learning algorithm (such as random forest, support vector machine, neural network), or a deep learning model specifically for time series (such as long short-term memory network LSTM, gated recurrent unit GRU, convolutional neural network CNN combined with recurrent network, etc.); further, dividing the training set and validation set, using the training set to train model parameters, and using the validation set for model selection and hyperparameter tuning to ensure model generalization ability. Based on the model's learning of historical data, the intelligent temperature prediction model can capture the nonlinear relationship and interaction between the heating equipment power, cooling equipment status, agitator speed and other factors that may affect temperature changes, and thus more accurately predict the temperature conditions at the next time node under the current operating status.

[0041] Step-6: If the first predicted temperature does not meet the first target temperature, generate a first temperature control instruction;

[0042] Step-7: The intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction, and the first temperature control decision is used to perform dynamic temperature control on the first production stage.

[0043] Compare the first predicted temperature obtained by the intelligent temperature prediction model with the predetermined first target temperature to determine whether there is a deviation and whether the magnitude of the deviation exceeds an allowable range; if it exceeds the allowable range, it indicates that the first predicted temperature does not meet the first target temperature, and generate a first temperature control instruction, for example, if the predicted temperature is lower than the target temperature, the first temperature control instruction may be to increase the output power of the heating source; conversely, if the predicted temperature is higher than the target temperature, the first temperature control instruction may be to reduce the power of the heating source or start the cooling system;

[0044] The generated first temperature control instruction is input into the intelligent temperature control model, and the intelligent temperature control model performs optimization operation based on multiple information such as the current equipment status, energy consumption data, and equipment loss history data. On the premise of meeting the first target temperature condition, the intelligent temperature control model analyzes how to adjust the equipment operation parameters to minimize energy consumption and equipment loss. Furthermore, it involves a multi-objective optimization problem, that is, simultaneously solving multiple goals such as improving temperature response speed and reducing energy consumption, and delaying aging of disinfectant production equipment;

[0045] After multi-objective optimization calculations, the intelligent temperature control model outputs the optimal first temperature control decision, which includes but is not limited to adjusting the working mode, frequency, and power level of the heating equipment, cooling equipment, and agitator; then, the first temperature control decision is sent to the heating equipment, cooling equipment, agitator and other related disinfectant production equipment that are communicated with the intelligent control system for disinfectant production temperature. After receiving the decision, the heating equipment, cooling equipment, agitator and other related disinfectant production equipment adjust the temperature control parameters of the first production stage in real time, thereby realizing real-time dynamic temperature control; after control, the temperature monitoring equipment group is used again to monitor the actual temperature changes, and the status monitoring equipment group is used to monitor the operating status changes of the disinfectant production equipment, and the new data is analyzed to form a closed-loop control to ensure that the temperature of each production stage in the production process is always stable within the target range, while maintaining the optimal energy efficiency and equipment health of the heating equipment, cooling equipment, agitator and other related disinfectant production equipment.

[0046] Furthermore, it includes: using simulation software (Maya (software name), Rhino (software name), Blender (software name) or other any modeling software) to simulate different disinfectant production conditions and temperature control scenarios, and build an intelligent temperature control model. Furthermore, considering the coupling between temperature control and other process parameters (such as pressure, stirring speed, material concentration, etc.), the intelligent temperature control model needs to have the ability to handle multi-parameter linkage, so as to adjust the temperature while taking into account the reasonable control of other important process parameters; using real-time collected data streams, online learning and dynamic optimization, as the disinfectant production process progresses, continuously improve the understanding and grasp of temperature control laws, and adapt to slight changes and uncertainties in production conditions.

[0047] Further, based on the first component characteristic information of the first production material, the first predetermined temperature of the first production stage is adjusted to obtain the first target temperature. The method of the present application includes:

[0048] Acquire the first production material of the first production stage, where the first production material includes multiple material components;

[0049] Sequentially extracting a first material component and a second material component from the plurality of material components;

[0050] In the disinfectant material database, sequentially traverse to obtain a first temperature resistance characteristic of the first material component and a second temperature resistance characteristic of the second material component;

[0051] The first target temperature is determined according to the first temperature resistance characteristic and the second temperature resistance characteristic.

[0052] Determine that the current stage is the first production stage, and identify the materials to be processed in the first production stage. The materials to be processed in the first production stage refer to the materials processed in the first production stage, that is, the finished products of the previous production stage of the first production stage. For example, the intermediate product B after the initial processing of raw material A, the intermediate product B will enter the next link to continue to be processed into a disinfectant product. If the first production stage is the intermediate product B after the initial processing of raw material A, then the first production material in the first production stage is raw material A;

[0053] Obtaining detailed material composition information of a first production material in a first production stage, wherein the first production material includes a plurality of different material components. Similarly, identifying and extracting a first material component and a second material component in the first production material, respectively, wherein the first material component and the second material component are the two material components with the largest proportion in the first production material;

[0054] For each extracted material component: the disinfectant material database is the detailed data of various materials required for disinfectant production recorded in the production process of the same disinfectant, including but not limited to material component information (basic raw material name, chemical structure, purity, concentration, active ingredient content and other detailed chemical property data), material temperature sensitivity (material stability at different temperatures, melting point, boiling point, decomposition temperature, reaction activation energy and other temperature characteristic parameters), reaction characteristics between materials (reaction rate constant, reaction heat, reaction equilibrium constant, reaction kinetics data between different materials, etc.); search for relevant data of the first material component in the known disinfectant material database to obtain the first temperature resistance characteristic corresponding to the first material component, such as the maximum tolerable temperature, the minimum safe operating temperature, etc.; similarly, search and determine the corresponding second temperature resistance characteristic for the second material component in the disinfectant material database;

[0055] Compare and analyze the temperature resistance ranges of the first material component and the second material component, and find the intersection between the temperature resistance range of the first material component and the temperature resistance range of the second material component; similarly, the first production material includes multiple material components, each of the multiple material components corresponds to a temperature resistance range, and the multiple temperature resistance ranges corresponding to the multiple material components in the first production material are comprehensively analyzed to determine the intersection between the multiple temperature resistance ranges corresponding to the multiple material components in the first production material, and finally find the material temperature resistance intersection range corresponding to the multiple material components in the first production material (to ensure that the multiple material components in the first production material will not mutate or performance will not change during the production process). loss); the material temperature resistance intersection range corresponding to the various material components in the first production material may be multiple temperature ranges. In the multiple temperature ranges of the material temperature resistance intersection range, combined with the production process requirements (such as GB / T38503-2020 "Good Manufacturing Practice for Disinfectants" and other relevant standards and specifications), a first target temperature that can ensure that the material performance is not destroyed and meet the process requirements is finally determined; then, the obtained first target temperature is applied to the first production stage, and the original first predetermined temperature is adjusted to replace it with the first target temperature, so as to ensure that all material components in the first production stage can be effectively and safely processed.

[0056] Further, the first actual temperature time series and the first temperature control parameter time series in the first operating state time series are analyzed by an intelligent temperature prediction model to obtain a first predicted temperature. Before this, the method of the present application includes:

[0057] Obtain historical disinfectant production temperature records;

[0058] If the first target temperature is a constant temperature, extracting the historical constant temperature production record in the historical disinfectant production temperature record;

[0059] A first data group is formed based on a first historical actual temperature, a first historical temperature control parameter, and a first historical temperature after temperature control in a first historical record in the historical constant temperature production record;

[0060] The first data set is subjected to supervised learning and verified to obtain a constant temperature prediction layer.

[0061] Obtain historical disinfectant production temperature records, which contain various temperature data and equipment operation status information in previous production processes; in the historical disinfectant production temperature records, if the first target temperature is a constant temperature, according to the requirement that the first target temperature is a constant temperature, filter out the corresponding historical constant temperature production record subset, and the historical constant temperature production records in the historical disinfectant production temperature records reflect the actual temperature, temperature control parameters, and temperature changes after temperature control under constant temperature conditions;

[0062] Select representative samples from the selected historical constant temperature production records to construct a first data group, wherein each data group in the first data group includes three main data: the first historical actual temperature in the first historical record (real-time temperature record during the production process), the first historical temperature control parameter (such as heating power, cooling intensity, etc.), and the first historical temperature after temperature control (the stable temperature reached after adjusting the temperature control parameters); perform necessary cleaning and formatting on the constructed data group, such as removing outliers, filling missing values, and standardizing values, etc., to ensure data quality;

[0063] Use a supervised learning algorithm (such as a neural network, a support vector machine, a random forest, etc.), take the first historical actual temperature and the first historical temperature control parameter as input variables, and the first historical temperature after temperature control as the output variable, and perform supervised learning on the first data group. After the training is completed, a part of the intelligent temperature prediction model (called the constant temperature prediction layer) is obtained. The constant temperature prediction layer can predict the possible future temperature under constant temperature conditions based on the input temperature and temperature control parameters; further, the prediction accuracy of the constant temperature prediction layer is tested through cross-validation, test set evaluation, etc. to ensure the effectiveness of the constant temperature prediction layer.

[0064] Furthermore, if Figure 2 As shown, supervised learning is performed on the first data group, and a constant temperature prediction layer is obtained by verification. After that, the method of the present application includes:

[0065] If the first target temperature is a variable temperature, extracting the historical variable temperature production record in the historical disinfectant production temperature record;

[0066] A second data group is formed based on the second historical actual temperature, the second historical temperature control parameter, and the second historical temperature after temperature control in the second historical record in the historical temperature-changing production record;

[0067] Performing supervised learning on the second data group and verifying to obtain a temperature change prediction layer;

[0068] The constant temperature prediction layer and the variable temperature prediction layer constitute the intelligent temperature prediction model.

[0069] In the existing historical disinfectant production temperature records, the production records related to the temperature change process, i.e., the historical temperature change production records, are screened out. The historical temperature change production records reflect the actual temperature change, the adjustment of the temperature control parameters, and the new temperature reached after the temperature control during the heating or cooling process; representative samples are selected from the screened historical temperature change production records to construct a second data group, which also includes three core variables: the second historical actual temperature in the second historical records, the second historical temperature control parameters (e.g., heating rate, cooling rate, etc.), and the second historical temperature after temperature control (i.e., the temperature change target temperature reached after adjusting the temperature control parameters); necessary data cleaning and preprocessing are performed on the second data group to ensure data quality, so as to facilitate the next step of supervised learning training;

[0070] Similarly, the second data set is trained using the same supervised learning algorithm to construct a part of the intelligent temperature prediction model (called the variable temperature prediction layer). The variable temperature prediction layer can predict the temperature changes during the variable temperature process. Furthermore, the accuracy and generalization ability of the model prediction are also tested through the validation set and test set.

[0071] After completing the training and verification of the constant temperature prediction layer and the variable temperature prediction layer, the constant temperature prediction layer and the variable temperature prediction layer are connected to form an intelligent temperature prediction model together; regardless of whether the target temperature in the production process is constant or needs to be changed, the intelligent temperature prediction model can accurately predict the temperature trend at the next moment based on the real-time collected temperature and temperature control parameter data; in addition, in the actual production process, the intelligent temperature prediction model receives the first actual temperature time series and the first temperature control parameter time series in the first operating state time series in real time, and performs temperature prediction through the corresponding prediction layer according to the target temperature requirements (constant temperature requirements or variable temperature requirements), generates temperature control instructions, and optimizes the temperature control in the entire production process.

[0072] Furthermore, the intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction. The method of the present application includes:

[0073] Extracting a first temperature at a first time in the first actual temperature time series;

[0074] If the first target temperature is a constant temperature, activating the first control layer in the intelligent temperature control model;

[0075] If the first temperature is greater than the first target temperature, calculating a first deviation between the first temperature and the first target temperature;

[0076] Adding the first unit energy consumption rate of the matched first deviation value and normalizing the result to obtain a first energy consumption index;

[0077] The first regulation layer generates the first temperature regulation decision based on the constraint that the first energy consumption index is minimized.

[0078] The actual temperature value at the current time node (first time) is obtained from the first actual temperature time series as the basis for the intelligent temperature control model to make decisions; it is determined whether the first target temperature required for the current production stage is a constant temperature; if it is a constant temperature condition, the first control layer (constant temperature prediction layer) in the intelligent temperature control model is activated to maintain a constant temperature. In addition, if the first target temperature is a constant temperature and the actual temperature is greater than the first target temperature, the temperature deviation value between the actual temperature and the first target temperature is calculated. The temperature deviation value between the actual temperature and the first target temperature is the first deviation value, and the first deviation value represents the difference between the current actual temperature and the first target temperature;

[0079] Based on the first deviation value, according to the pre-set unit energy consumption rate information (such as the heating energy consumption information required to increase 1°C or the cooling energy consumption information required to decrease 1°C), the first deviation value is mapped to the corresponding energy consumption level, that is, the first unit energy consumption rate corresponding to each deviation value is calculated; all the matched unit energy consumption rates are accumulated, and then the accumulated energy consumption is normalized to form a first energy consumption index, wherein the normalization process is to ensure that energy consumption of different magnitudes can be compared and adapt to a unified decision range;

[0080] Unit energy consumption rate information refers to the heating energy consumption information required to increase 1°C or the cooling energy consumption information required to decrease 1°C. For example, assuming that the unit energy consumption rate is ΔE / ΔT (unit: joule / degree Celsius), and the first deviation value is ΔT1 (unit: degree Celsius), the single deviation energy consumption data calculated according to the first deviation value ΔT1 is: ΔE=ΔE / ΔT×ΔT1; if there are multiple first deviation values ​​in a time series, the energy consumption data corresponding to each deviation value is accumulated to obtain the total deviation energy consumption data;

[0081] Based on the first energy consumption index, the first control layer adopts any optimization algorithm (such as linear programming, dynamic programming, etc.) to generate a first temperature control decision for the first actual temperature with the goal of minimizing the first energy consumption index while meeting the temperature control requirements. The first temperature control decision includes specific measures such as adjusting the working intensity and operating time of the heating or cooling equipment, aiming to make the actual temperature approach the target constant temperature as quickly and smoothly as possible while minimizing energy consumption.

[0082] Furthermore, the intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction, and the method of the present application further includes:

[0083] If the first target temperature is a variable temperature, the second control layer in the intelligent temperature control model is activated, and the first target temperature includes a first target initial temperature and a first target end temperature;

[0084] Calculating the first target initial temperature and the first target termination temperature to obtain a first target temperature change threshold;

[0085] Combining the first production duration of the first production stage with the first target temperature change threshold to obtain a first target temperature change speed;

[0086] Combining the first time with the first target temperature changing speed to obtain a first target temperature changing temperature, and calculating a second deviation value between the first temperature and the first target temperature changing temperature;

[0087] Adding and normalizing the second unit energy consumption rate of the matched second deviation value to obtain a second energy consumption index;

[0088] The second regulation layer generates the first temperature regulation decision based on the constraint that the second energy consumption index is minimized.

[0089] If the first target temperature is a variable temperature, the second control layer (variable temperature prediction layer) in the intelligent temperature control model will be activated. At this time, the first target temperature includes two key data points: the first target initial temperature and the first target end temperature. The difference between the first target initial temperature and the first target end temperature is calculated to obtain the required temperature change threshold in the corresponding production stage. The first target temperature change threshold is calculated to determine the total temperature difference that needs to be changed.

[0090] Combined with the calculated first target temperature change threshold, calculate the first target temperature change speed required in the corresponding production stage in an average or specified time period, wherein the first target temperature change speed refers to the expected temperature change rate per unit time in the corresponding production stage; calculate the theoretical first target temperature change temperature at the current moment according to the current time point (first time) and the known first target temperature change speed; calculate the temperature difference between the current actual first temperature and the inferred first target temperature change temperature, and use the temperature difference between the first temperature and the first target temperature change temperature as the second deviation value;

[0091] Similarly, the second deviation value is multiplied and accumulated with the corresponding second unit energy consumption rate, and then the accumulated energy consumption index is normalized to obtain the second energy consumption index; the second control layer uses the second energy consumption index as an optimization constraint, and uses an intelligent algorithm to find a control strategy that minimizes the second energy consumption index while ensuring that the temperature changes at the expected temperature change rate, thereby obtaining the first temperature control decision under variable temperature conditions, including but not limited to adjusting the power of the equipment and switching the working mode. When the target temperature is the variable temperature, the variable temperature is dynamically adjusted in accordance with the actual temperature and energy consumption information to ensure that in the process of the temperature smoothly transitioning from the initial target temperature to the terminal target temperature, it can not only meet the temperature requirements of the chemical reaction process, but also save energy and reduce equipment losses to the maximum extent.

[0092] Furthermore, the present application method also includes:

[0093] Adding the first device loss rate of the matched second deviation value and normalizing the result to obtain a first loss index;

[0094] Performing weighted calculation on the second energy consumption index and the first loss index to obtain a first comprehensive index;

[0095] The first comprehensive index replaces the second energy consumption index as the optimal control constraint of the second control layer.

[0096] Match each calculated second deviation value with the first equipment loss rate of the corresponding production stage, and accumulate the matched loss rates to reflect the overall equipment loss situation; normalize the accumulated total equipment loss amount and convert it into a standardized first loss index to facilitate analysis of various equipment loss indicators on the same scale;

[0097] The second energy consumption index calculated previously and the first loss index after normalization are weighted and summed, and the weight can be set according to factors such as equipment service life and equipment component damage, and finally a first comprehensive index is obtained, which comprehensively reflects the energy consumption and equipment loss factors in the temperature control process;

[0098] In the original second control layer, the optimization constraint is changed from a simple second energy consumption index to a first comprehensive index, that is, when generating the first temperature control decision, not only the minimization of energy consumption should be considered, but also the impact of equipment loss should be taken into account; the optimization control is carried out with the optimal first comprehensive index as the goal, which can optimize energy consumption and equipment loss more evenly while meeting the temperature control target, thereby formulating a more scientific temperature control strategy. For example, when deciding whether to increase the heating power to speed up the heating rate, the second control layer in the intelligent temperature control model will not only consider the increase in energy consumption, but also take into account the equipment loss and component damage during equipment operation, thereby pursuing production efficiency and ensuring product quality while extending the service life of the equipment and achieving efficient, stable and sustainable operation of disinfectant production.

[0099] In summary, the beneficial effects of the embodiments of the present application are:

[0100] 1. Intelligently analyze the composition characteristics of production materials at different stages and automatically adjust the preset temperature at each stage to ensure that all materials react within the appropriate temperature range and avoid product quality degradation due to improper temperature.

[0101] 2. The temperature monitoring equipment group and the condition monitoring equipment group are used to monitor the production site data in real time, and combined with the prediction of temperature change trends, the accuracy and timeliness of temperature control are improved.

[0102] 3. By comparing the temperature control instructions, we can find the optimal control decision with the lowest energy consumption and equipment loss rate, thus realizing the refined management of the disinfectant production process.

[0103] 4. Integrate historical production data and use machine learning algorithms to establish a prediction model to more accurately predict the temperature requirements in the constant temperature and variable temperature stages, further improving the scientificity and reliability of regulation.

[0104] 5. Since the first production material of the first production stage is obtained, the first production material includes multiple material components; the first material component and the second material component of the multiple material components are extracted in sequence; the first temperature resistance characteristic of the first material component and the second temperature resistance characteristic of the second material component are traversed in sequence in the disinfectant material database; the first target temperature is determined according to the first temperature resistance characteristic and the second temperature resistance characteristic. A first target temperature is determined that can ensure that the material performance is not destroyed and can meet the process requirements, thereby ensuring that all material components in the first production stage can be effectively and safely processed.

[0105] Embodiment 2

[0106] Based on the same inventive concept as the intelligent control method for disinfectant production temperature in the aforementioned embodiment, Figure 3As shown, the embodiment of the present application provides an intelligent control system for the production temperature of a disinfectant, wherein the system comprises:

[0107] The process analysis module M100 is used to analyze the disinfectant production process with the predetermined production temperature as a constraint and divide it into a production stage set;

[0108] A target determination module M200, configured to adjust a first predetermined temperature of a first production stage based on first component characteristic information of a first production material to obtain a first target temperature, wherein the first production stage is any stage in the production stage set;

[0109] A first dynamic monitoring module M300, configured to obtain a first actual temperature sequence of the first production stage through dynamic monitoring by a temperature monitoring device group;

[0110] A second dynamic monitoring module M400, configured to dynamically monitor a first operating state sequence of a first production device in the first production stage through a state monitoring device group;

[0111] The temperature prediction module M500 is used to analyze the first actual temperature time series and the first temperature control parameter time series in the first operating state time series through an intelligent temperature prediction model to obtain a first predicted temperature;

[0112] An instruction generating module M600 is used to generate a first temperature control instruction if the first predicted temperature does not meet the first target temperature;

[0113] The dynamic control module M700 is used for the intelligent temperature control model to generate a first temperature control decision based on the first temperature control instruction, and the first temperature control decision is used to perform dynamic temperature control on the first production stage.

[0114] Furthermore, the target determination module M200 is used to execute the following method:

[0115] Acquire the first production material of the first production stage, where the first production material includes multiple material components;

[0116] Sequentially extracting a first material component and a second material component from the plurality of material components;

[0117] In the disinfectant material database, sequentially traverse to obtain a first temperature resistance characteristic of the first material component and a second temperature resistance characteristic of the second material component;

[0118] The first target temperature is determined according to the first temperature resistance characteristic and the second temperature resistance characteristic.

[0119] Furthermore, the temperature prediction module M500 is used to perform the following method:

[0120] Obtain historical disinfectant production temperature records;

[0121] If the first target temperature is a constant temperature, extracting the historical constant temperature production record in the historical disinfectant production temperature record;

[0122] A first data group is formed based on a first historical actual temperature, a first historical temperature control parameter, and a first historical temperature after temperature control in a first historical record in the historical constant temperature production record;

[0123] The first data set is subjected to supervised learning and verified to obtain a constant temperature prediction layer.

[0124] Furthermore, the temperature prediction module M500 is also used to perform the following method:

[0125] If the first target temperature is a variable temperature, extracting the historical variable temperature production record in the historical disinfectant production temperature record;

[0126] A second data group is formed based on the second historical actual temperature, the second historical temperature control parameter, and the second historical temperature after temperature control in the second historical record in the historical temperature-changing production record;

[0127] Performing supervised learning on the second data group and verifying to obtain a temperature change prediction layer;

[0128] The constant temperature prediction layer and the variable temperature prediction layer constitute the intelligent temperature prediction model.

[0129] Furthermore, the dynamic control module M700 is used to execute the following method:

[0130] Extracting a first temperature at a first time in the first actual temperature time series;

[0131] If the first target temperature is a constant temperature, activating the first control layer in the intelligent temperature control model;

[0132] If the first temperature is greater than the first target temperature, calculating a first deviation between the first temperature and the first target temperature;

[0133] Adding the first unit energy consumption rate of the matched first deviation value and normalizing the result to obtain a first energy consumption index;

[0134] The first regulation layer generates the first temperature regulation decision based on the constraint that the first energy consumption index is minimized.

[0135] Furthermore, the dynamic control module M700 is also used to execute the following method:

[0136] If the first target temperature is a variable temperature, the second control layer in the intelligent temperature control model is activated, and the first target temperature includes a first target initial temperature and a first target end temperature;

[0137] Calculating the first target initial temperature and the first target termination temperature to obtain a first target temperature change threshold;

[0138] Combining the first production duration of the first production stage with the first target temperature change threshold to obtain a first target temperature change speed;

[0139] Combining the first time with the first target temperature changing speed to obtain a first target temperature changing temperature, and calculating a second deviation value between the first temperature and the first target temperature changing temperature;

[0140] Adding and normalizing the second unit energy consumption rate of the matched second deviation value to obtain a second energy consumption index;

[0141] The second regulation layer generates the first temperature regulation decision based on the constraint that the second energy consumption index is minimized.

[0142] Furthermore, the dynamic control module M700 is also used to execute the following method:

[0143] Adding the first device loss rate of the matched second deviation value and normalizing the result to obtain a first loss index;

[0144] Performing weighted calculation on the second energy consumption index and the first loss index to obtain a first comprehensive index;

[0145] The first comprehensive index replaces the second energy consumption index as the optimal control constraint of the second control layer.

[0146] In summary, any step can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor, and no unnecessary restrictions are made here.

[0147] Furthermore, the above-mentioned technical scheme only reflects the preferred technical scheme of the technical scheme of the embodiment of the present application. Some changes that may be made to some parts thereof by technicians in this technical field all reflect the novel principles of the embodiment of the present application. Obviously, technicians in this field can make various changes and modifications to the present application without departing from the scope of the present application.

Claims

1. An intelligent control method for disinfectant production temperature, characterized in that: include: The disinfectant production process is analyzed with the predetermined production temperature as a constraint, and the production stage set is obtained; adjusting a first predetermined temperature of a first production stage based on first component characteristic information of a first production material to obtain a first target temperature, wherein the first production stage is any stage in the production stage set; Dynamically monitoring the first actual temperature sequence of the first production stage by a temperature monitoring device group; Dynamically monitoring the state monitoring equipment group to obtain a first operating state sequence of the first production equipment in the first production stage; Analyze the first actual temperature time series and the first temperature control parameter time series in the first operating state time series through an intelligent temperature prediction model to obtain a first predicted temperature; If the first predicted temperature does not meet the first target temperature, generating a first temperature control instruction; The intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction, and the first temperature control decision is used to perform dynamic temperature control on the first production stage.

2. The intelligent control method for disinfectant production temperature according to claim 1, characterized in that: Adjusting a first predetermined temperature of a first production stage based on first component characteristic information of a first production material to obtain a first target temperature includes: Acquire the first production material of the first production stage, where the first production material includes a plurality of material components; Sequentially extracting a first material component and a second material component from the plurality of material components; In the disinfectant material database, sequentially traverse to obtain a first temperature resistance characteristic of the first material component and a second temperature resistance characteristic of the second material component; The first target temperature is determined according to the first temperature resistance characteristic and the second temperature resistance characteristic.

3. The intelligent control method for disinfectant production temperature according to claim 1, characterized in that: The first actual temperature time series and the first temperature control parameter time series in the first operating state time series are analyzed by an intelligent temperature prediction model to obtain a first predicted temperature, which includes: Obtain historical disinfectant production temperature records; If the first target temperature is a constant temperature, extracting the historical constant temperature production record in the historical disinfectant production temperature record; A first data group is formed based on a first historical actual temperature, a first historical temperature control parameter, and a first historical temperature after temperature control in a first historical record in the historical constant temperature production record; The first data set is subjected to supervised learning and verified to obtain a constant temperature prediction layer.

4. The intelligent control method for disinfectant production temperature according to claim 3, characterized in that: The first data set is subjected to supervised learning and verified to obtain a constant temperature prediction layer, followed by: Obtain historical disinfectant production temperature records; If the first target temperature is a variable temperature, extracting the historical variable temperature production record in the historical disinfectant production temperature record; A second data group is formed based on the second historical actual temperature, the second historical temperature control parameter, and the second historical temperature after temperature control in the second historical record in the historical temperature-changing production record; Performing supervised learning on the second data group and verifying to obtain a temperature change prediction layer; The constant temperature prediction layer and the variable temperature prediction layer constitute the intelligent temperature prediction model.

5. The intelligent control method for disinfectant production temperature according to claim 1, characterized in that: The intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction, including: Extracting a first temperature at a first time in the first actual temperature time series; If the first target temperature is a constant temperature, activating the first control layer in the intelligent temperature control model; If the first temperature is greater than the first target temperature, calculating a first deviation between the first temperature and the first target temperature; Adding a first unit energy consumption rate of the matched first deviation value, where the first unit energy consumption rate is the product of the unit energy consumption rate and the first deviation value, and normalizing them to obtain a first energy consumption index; The first regulation layer generates the first temperature regulation decision based on the constraint that the first energy consumption index is minimized.

6. The intelligent control method for disinfectant production temperature according to claim 5, characterized in that: The intelligent temperature control model generates a first temperature control decision based on the first temperature control instruction, further comprising: If the first target temperature is a variable temperature, the second control layer in the intelligent temperature control model is activated, and the first target temperature includes a first target initial temperature and a first target end temperature; Calculating the first target initial temperature and the first target termination temperature to obtain a first target temperature change threshold; Combining the first production duration of the first production stage with the first target temperature change threshold to obtain a first target temperature change speed; Combining the first time with the first target temperature changing speed to obtain a first target temperature changing temperature, and calculating a second deviation value between the first temperature and the first target temperature changing temperature; Adding a second unit energy consumption rate of the matched second deviation value, where the second unit energy consumption rate is the product of the unit energy consumption rate and the second deviation value, and normalizing them to obtain a second energy consumption index; The second regulation layer generates the first temperature regulation decision based on the constraint that the second energy consumption index is minimized.

7. The intelligent control method for disinfectant production temperature according to claim 6, characterized in that: The method also includes: Adding the first device loss rate of the matched second deviation value and normalizing the result to obtain a first loss index; Performing weighted calculation on the second energy consumption index and the first loss index to obtain a first comprehensive index; The first comprehensive index replaces the second energy consumption index as the optimal control constraint of the second control layer.

8. An intelligent control system for disinfectant production temperature, characterized in that: A method for intelligently controlling the temperature of disinfectant production according to any one of claims 1 to 7, the system comprising: A process analysis module is used to analyze the disinfectant production process with a predetermined production temperature as a constraint and divide it into a set of production stages; a target determination module, configured to adjust a first predetermined temperature of a first production stage based on first component characteristic information of a first production material to obtain a first target temperature, wherein the first production stage is any stage in the production stage set; A first dynamic monitoring module, configured to dynamically monitor a first actual temperature sequence of the first production stage through a temperature monitoring device group; A second dynamic monitoring module, configured to dynamically monitor a first operating state sequence of a first production device in the first production stage through a state monitoring device group; a temperature prediction module, configured to analyze the first actual temperature time series and the first temperature control parameter time series in the first operating state time series through an intelligent temperature prediction model to obtain a first predicted temperature; An instruction generating module, configured to generate a first temperature control instruction if the first predicted temperature does not meet the first target temperature; A dynamic control module is used for the intelligent temperature control model to generate a first temperature control decision based on the first temperature control instruction, and the first temperature control decision is used to perform dynamic temperature control on the first production stage.