Manufacturing parameter regulation and control decision-making system and method for energetic material

Abstract

The invention discloses an energetic material-oriented manufacturing parameter regulation and control decision system and method, and belongs to the technical field of parameter regulation and control, and the method comprises the steps: collecting reaction records of a nitration reaction, and storing the reaction records in a database to form a training set; a deep learning model is established, and training of the deep learning model is completed; obtaining a reaction starting moment and a temperature change chart of the current nitration reaction, and analyzing a cooling starting moment, a first temperature characteristic and a prediction characteristic of the current nitration reaction; according to the prediction characteristics of the current nitration reaction, judging whether the current nitration reaction needs to be subjected to primary regulation or not, and adjusting a preset flow rate; analyzing the actual second temperature characteristic of the current nitration reaction, judging whether the current nitration reaction needs to be subjected to secondary regulation or not, and carrying out secondary regulation; according to the invention, intelligent regulation and control of manufacturing parameters are realized, the problems of response lag and insufficient regulation and control precision in the prior art are overcome, and the reliability and adaptability of the energetic material manufacturing process are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of parameter regulation, and specifically relates to a manufacturing parameter regulation decision system and method for energetic materials. Background Technique

[0002] The manufacturing process of energetic materials involves multiple links such as nitrification, mixing, pressing, coating, drying, etc. The manufacturing parameters include temperature, pressure, acid concentration, stirring rate, etc. Precise regulation of manufacturing parameters during the manufacturing process of energetic materials is crucial for product quality and safety. However, due to the complexity of chemical reactions and the uncertainty of environmental factors, the traditional manufacturing mode has the following problems: lack of an intelligent adjustment mechanism, resulting in a lag in parameter regulation response. Especially in the nitrification link, it is impossible to accurately control the temperature of the nitrification reaction based on real-time data, leading to poor stability of the manufactured energetic materials and relatively high safety risks. Therefore, there is an urgent need for a manufacturing parameter regulation decision system for energetic materials to solve the above problems. Summary of the Invention

[0003] The purpose of the present invention is to provide a manufacturing parameter regulation decision system for energetic materials to solve the problems raised in the above background technique.

[0004] To solve the above technical problems, the present invention provides the following technical solutions: A manufacturing parameter regulation decision method for energetic materials, the method includes the following steps: S1. Collect the reaction records of the nitrification reaction and store them in the database; screen the reaction records in the database, analyze the first temperature feature and the second temperature feature of the reaction records, and form a training set; establish a deep learning model, and complete the training of the deep learning model through the training set. S2. Obtain the reaction start time and temperature change diagram of the current nitrification reaction, and analyze the cooling start time and the first temperature feature of the current nitrification reaction; extract the raw material dosage, the initial temperature and the preset flow rate of the coolant in the current nitrification reaction from the database, and combine with the deep learning model to analyze the prediction features of the current nitrification reaction. S3. According to the prediction features of the current nitrification reaction, judge whether it is necessary to perform a first regulation on the current nitrification reaction; if it is necessary to perform a first regulation on the current nitrification reaction, analyze the flow rate adjustment value of the first regulation, and adjust the preset flow rate. S4. According to the temperature change diagram of the current nitrification reaction, analyze the actual second temperature feature of the current nitrification reaction, judge whether it is necessary to perform a second regulation on the current nitrification reaction, and perform the second regulation.

[0005] According to the above technical solution, the step S1 includes: S1-1. Each time a nitration reaction is carried out, a reaction record is generated and stored in the database; the reaction record includes the raw material dosage, the start time of the reaction, the start time of cooling, the initial temperature of the coolant, the average flow rate of the coolant, the end time of the reaction, the end time of cooling, and the temperature change diagram; S1-2. Extract the standard temperature range of the nitration reaction from the database, extract the maximum and minimum temperatures from the temperature change diagrams in each reaction record, and screen out the reaction records in which the maximum and minimum temperatures are within the standard temperature range of the nitration reaction to form a first record set; S1-3. According to the first record set, obtain the temperature difference between the start time of cooling and the start time of the reaction from the temperature change diagram of a certain reaction record in the first record set, and obtain the time interval from the start time of the reaction to the start time of cooling in this reaction record. Take the ratio between the temperature difference between the start time of cooling and the start time of the reaction and the time interval from the start time of the reaction to the start time of cooling in this reaction record as the first temperature feature of this reaction record; S1-4. According to the first record set, extract the temperature at the start time of cooling for each reaction record in the first record set, and take the average value of the temperatures at the start time of cooling for all reaction records in the first record set as the first temperature threshold; Obtain the time interval from the start time of cooling to the end time of cooling for each reaction record in the first record set, and take the average value of the time intervals from the start time of cooling to the end time of cooling for all reaction records in the first record set as the first time parameter; Calculate the ratio between the temperature difference between the end time of cooling and the start time of cooling in a certain reaction record and the time interval from the start time of cooling to the end time of cooling in this reaction record as the second temperature feature of this reaction record; Take the raw material dosage, the initial temperature of the coolant, the average flow rate of the coolant, and the first temperature feature of each reaction record in the first record set as the input quantities of the training set; take the second temperature feature of each reaction record in the first record set as the output quantity of the training set to form a training set; S1-5. Establish a deep learning model and complete the training of the deep learning model through the training set; Train the model through the screened and calculated data to improve the prediction accuracy of the temperature change in the nitration reaction, form an intelligent model that can be used for decision-making, improve the automation level of the manufacturing process, and make the parameter regulation no longer rely on fixed experience but on intelligent judgment based on historical data.

[0006] According to the above technical solution, the step S2 includes: S2-1. Obtain the reaction start time and temperature change graph of the current nitrification reaction through a sensing device. If the temperature at a certain moment after the reaction start time of the current nitrification reaction is greater than or equal to the first temperature threshold, take this moment as the cooling start time of the current nitrification reaction; S2-2. Calculate the first temperature characteristic of the current nitrification reaction according to the reaction start time, cooling start time and temperature change graph of the current nitrification reaction; Extract the raw material dosage of the current nitrification reaction, the initial temperature and preset flow rate of the coolant from the database. Input the raw material dosage, first temperature characteristic, cooling start time, initial temperature and preset flow rate of the coolant of the current nitrification reaction into the trained deep learning model, and output the second temperature characteristic of the current nitrification reaction as the prediction characteristic of the current nitrification reaction; By real-time monitoring the temperature change, it is possible to predict the occurrence of abnormal situations in advance, improve the forward-looking of temperature control, avoid lagged adjustment, and conduct intelligent analysis in combination with historical data to improve the prediction accuracy and make the control more precise.

[0007] According to the above technical solution, the step S3 includes: S3-1. Calculate the value obtained by multiplying the prediction characteristic of the current nitrification reaction by the first time parameter, denoted as the prediction change amount; calculate the value obtained by adding the first temperature threshold and the prediction change amount, denoted as the first regulation judgment amount; S3-2. If the first regulation judgment amount is not within the standard temperature range of the nitrification reaction, then it is necessary to perform a first regulation on the current nitrification reaction; S3-3. If it is necessary to perform a first regulation on the current nitrification reaction, extract the minimum value in the standard temperature range of the nitrification reaction, calculate the value obtained by subtracting the first temperature threshold from the minimum value in the standard temperature range of the nitrification reaction, denoted as the first regulation change amount; calculate the ratio of the first regulation change amount to the first time parameter, denoted as the first regulation characteristic; S3-4. Take the raw material dosage, first temperature characteristic, cooling start time and initial temperature of the coolant of the current nitrification reaction as inputs, take the first regulation characteristic as the output, and combine with the deep learning model to obtain the average flow rate of the coolant as the flow rate adjustment value for the first regulation; adjust the preset flow rate to the value corresponding to the flow rate adjustment value for the first regulation; adjust the prediction characteristic to the value corresponding to the first regulation characteristic; Timely adjust the preset flow rate of the coolant to prevent the temperature from being too high or too low. By intelligently calculating the adjustment range, avoid the errors that may be brought by manual adjustment, make the reaction temperature closer to the ideal state, and improve the product quality and stability.

[0008] According to the above technical solution, the step S4 includes: S4-1. Regulate the temperature of the current nitration reaction according to the cooling start time and the preset flow rate of the coolant; set a unit time interval, obtain the temperature at the corresponding time after the unit time interval from the cooling start time, calculate the value obtained by subtracting the temperature at the corresponding time after the unit time interval from the cooling start time from the temperature at the cooling start time, and calculate the ratio of this value to the unit time interval, which is denoted as the actual second temperature characteristic of the current nitration reaction; S4-2. If the absolute value of the difference between the actual second temperature characteristic of the current nitration reaction and the predicted characteristic is denoted as the secondary regulation judgment quantity; If the secondary regulation judgment quantity is greater than or equal to the preset error value, then the current nitration reaction needs to be secondarily regulated; S4-3. When the current nitration reaction needs to be secondarily regulated, if the difference between the actual second temperature characteristic of the current nitration reaction and the predicted characteristic is negative, then reduce the preset flow rate, and the ratio of the value obtained by subtracting the reduced preset flow rate from the preset flow rate before reduction to the preset flow rate before reduction is the value obtained by multiplying the preset weight by the secondary regulation judgment quantity; If the difference between the actual second temperature characteristic of the current nitration reaction and the predicted characteristic is positive, then increase the preset flow rate, and the ratio of the value obtained by subtracting the preset flow rate before increase from the increased preset flow rate to the preset flow rate before increase is the value obtained by multiplying the preset weight by the secondary regulation judgment quantity; Through secondary adjustment, improve the accuracy of temperature control, reduce the influence of errors, solve the problems of lagging flow rate adjustment and slow response in the traditional mode, improve safety, form a closed-loop regulation system, ensure temperature stability, and reduce quality fluctuations and safety hazards.

[0009] A manufacturing parameter regulation decision-making system for energetic materials, which includes an acquisition and training module, a reaction prediction module, a primary regulation module, and a secondary regulation module; The acquisition and training module is responsible for collecting, screening, and analyzing the historical reaction records of the nitration reaction, forming a training set, establishing and training a deep learning model, and providing data support for subsequent regulation; the reaction prediction module is used to monitor the current nitration reaction in real time, analyze the cooling start time and the first temperature characteristic of the current nitration reaction, and use the deep learning model to predict the reaction characteristic, providing a basis for regulation decision-making; the primary regulation module is used to judge whether the current nitration reaction needs to be primarily regulated according to the predicted characteristic and adjust the preset flow rate of the coolant; the secondary regulation module is used to analyze the actual second temperature characteristic of the current nitration reaction according to the actual temperature change condition of the current nitration reaction, judge whether the current nitration reaction needs to be secondarily regulated, and precisely control the current nitration reaction to ensure that the temperature of the current nitration reaction remains stable.

[0010] According to the above technical solution, the acquisition and training module includes a data acquisition unit and a model training unit; The data acquisition unit is used to collect the reaction records of the nitrification reaction, including the raw material dosage, the start time of the reaction, the start time of cooling, the initial temperature of the cooling liquid, the average flow rate of the cooling liquid, the end time of the reaction, the end time of cooling, and the temperature change diagram, and store them in the database; the model training unit is used to screen the reaction records from the database, calculate the first temperature feature and the second temperature feature corresponding to each screened reaction record, form a training set, establish a deep learning model, and complete the training of the deep learning model.

[0011] According to the above technical solution, the reaction prediction module includes a feature extraction unit and a feature prediction unit; The feature extraction unit is used to obtain the temperature change data of the current nitrification reaction through a sensing device, and analyze the start time of cooling and the first temperature feature of the current nitrification reaction; the feature prediction unit is used to obtain the prediction feature of the current nitrification reaction according to the raw material dosage, the first temperature feature, the start time of cooling of the current nitrification reaction, as well as the initial temperature and the preset flow rate of the cooling liquid, in combination with the deep learning model.

[0012] According to the above technical solution, the primary regulation module includes a regulation determination unit and a flow rate adjustment unit; The regulation determination unit is used to judge whether the current nitrification reaction needs to be primarily regulated according to the prediction feature of the current nitrification reaction; the flow rate adjustment unit is used to analyze the flow rate adjustment value of the primary regulation if the current nitrification reaction needs to be primarily regulated, and adjust the preset flow rate.

[0013] According to the above technical solution, the secondary regulation module includes an error analysis unit and a dynamic adjustment unit; The error analysis unit is used to calculate the error between the actual temperature feature and the prediction feature, and judge whether the current nitrification reaction needs to be secondarily regulated; the dynamic adjustment unit is used to dynamically adjust the preset flow rate according to the error if the current nitrification reaction needs to be secondarily regulated, optimize the flow rate parameter, and ensure that the temperature change meets the expectation.

[0014] Compared with the prior art, the beneficial effects achieved by the present invention are: The present invention accurately predicts the temperature characteristics of nitrification reactions through a deep learning model, and dynamically adjusts them in combination with real-time sensing data, realizing the intelligent control of manufacturing parameters, improving the stability and safety of the reaction process; at the same time, based on historical reaction data, the present invention establishes a standardized temperature characteristic analysis method, optimizes the cooling strategy of nitrification reactions, effectively reduces temperature fluctuations, and improves product consistency; secondly, the present invention adopts a phased control strategy, precisely controls the coolant flow rate through a combination of primary control and secondary control, shortens the control response time, reduces the need for human intervention, and improves production efficiency; in addition, the present invention combines an error analysis method to correct deviations in the control process in real time, ensuring that manufacturing parameters are always within the optimal range, overcoming the problems of response lag and insufficient control accuracy in the prior art, and improving the reliability and adaptability of the manufacturing process of energetic materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the accompanying drawings: Figure 1 is a schematic flow chart of a method for regulating and making decisions on manufacturing parameters for energetic materials according to the present invention; Figure 2 is a schematic structural diagram of a system for regulating and making decisions on manufacturing parameters for energetic materials according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Please refer to Figure 1 , the present invention provides the following technical solutions: A method for regulating and making decisions on manufacturing parameters for energetic materials, the method comprising the following steps: S1. Collect the reaction records of nitrification reactions and store them in a database; screen the reaction records in the database, analyze the first temperature characteristic and the second temperature characteristic of the reaction records, and form a training set; establish a deep learning model, and complete the training of the deep learning model through the training set; According to the above technical solution, the step S1 includes: S1-1. Each nitration reaction generates a reaction record and stores it in the database. The reaction record includes raw material dosage, reaction start time, cooling start time, initial coolant temperature, average coolant flow rate, reaction end time, cooling end time, and temperature change graph. S1-2. Extract the standard temperature range of the nitration reaction from the database, extract the maximum and minimum temperatures from the temperature change graphs in each reaction record, and screen out the reaction records in which the maximum and minimum temperatures are within the standard temperature range of the nitration reaction to form a first record set. S1-3. According to the first record set, obtain the temperature difference between the cooling start time and the reaction start time from the temperature change graph of a certain reaction record in the first record set, and obtain the time interval from the reaction start time to the cooling start time of this reaction record. Take the ratio between the temperature difference between the cooling start time and the reaction start time and the time interval from the reaction start time to the cooling start time of this reaction record as the first temperature feature of this reaction record. S1-4. According to the first record set, extract the temperature at the cooling start time of each reaction record in the first record set, and take the average value of the temperatures at the cooling start time of all reaction records in the first record set as the first temperature threshold. Obtain the time interval from the cooling start time to the cooling end time of each reaction record in the first record set, and take the average value of the time intervals from the cooling start time to the cooling end time of all reaction records in the first record set as the first time parameter. Calculate the ratio between the temperature difference between the cooling end time and the cooling start time and the time interval from the cooling start time to the cooling end time in a certain reaction record as the second temperature feature of this reaction record. Take the raw material dosage, initial coolant temperature, average coolant flow rate, and first temperature feature of each reaction record in the first record set as the input of the training set; take the second temperature feature of each reaction record in the first record set as the output of the training set to form a training set. S1-5. Establish a deep learning model and complete the training of the deep learning model through the training set. Train the model through the screened and calculated data to improve the prediction accuracy of temperature changes in nitration reactions, form an intelligent model that can be used for decision-making, improve the automation level of the manufacturing process, and make parameter regulation no longer rely on fixed experience but on intelligent judgment based on historical data.

[0018] S2. Obtain the reaction start time and temperature change graph of the current nitration reaction, and analyze the cooling start time and the first temperature characteristic of the current nitration reaction; extract the raw material dosage, the initial temperature of the coolant, and the preset flow rate in the current nitration reaction from the database, and combine with the deep learning model to analyze the prediction characteristics of the current nitration reaction; According to the above technical solution, the step S2 includes: S2-1. Obtain the reaction start time and temperature change graph of the current nitration reaction through a sensing device. When the temperature at a certain moment after the reaction start time of the current nitration reaction is greater than or equal to the first temperature threshold, take this moment as the cooling start time of the current nitration reaction; S2-2. Calculate the first temperature characteristic of the current nitration reaction according to the reaction start time, cooling start time, and temperature change graph of the current nitration reaction; Extract the raw material dosage of the current nitration reaction, the initial temperature of the coolant, and the preset flow rate from the database. Input the raw material dosage, the first temperature characteristic, the cooling start time, the initial temperature of the coolant, and the preset flow rate of the current nitration reaction into the trained deep learning model, and output the second temperature characteristic of the current nitration reaction as the prediction characteristic of the current nitration reaction; By real-time monitoring the temperature change, it is possible to predict the occurrence of abnormal situations in advance, improve the forward-looking of temperature control, avoid lag adjustment, and conduct intelligent analysis in combination with historical data to improve the prediction accuracy and make the control more precise.

[0019] S3. According to the prediction characteristics of the current nitration reaction, judge whether it is necessary to perform a first adjustment on the current nitration reaction; if it is necessary to perform a first adjustment on the current nitration reaction, analyze the flow rate adjustment value of the first adjustment, and adjust the preset flow rate; According to the above technical solution, the step S3 includes: S3-1. Calculate the value obtained by multiplying the prediction characteristic of the current nitration reaction by the first time parameter, denoted as the prediction change amount; calculate the value obtained by adding the first temperature threshold and the prediction change amount, denoted as the first adjustment judgment amount; S3-2. If the first adjustment judgment amount is not within the standard temperature range of the nitration reaction, it is necessary to perform a first adjustment on the current nitration reaction; S3-3. If it is necessary to perform a first adjustment on the current nitration reaction, extract the minimum value in the standard temperature range of the nitration reaction, calculate the value obtained by subtracting the first temperature threshold from the minimum value in the standard temperature range of the nitration reaction, denoted as the first adjustment change amount; calculate the ratio of the first adjustment change amount to the first time parameter, denoted as the first adjustment characteristic; S3-4. Take the raw material dosage, the first temperature characteristic, the cooling start time, and the initial temperature of the coolant of the current nitration reaction as inputs, take the primary regulation characteristic as the output, and combine with a deep learning model to obtain the average flow rate of the coolant as the flow rate adjustment value for the primary regulation; adjust the preset flow rate to the value corresponding to the flow rate adjustment value for the primary regulation; adjust the prediction characteristic to the value corresponding to the primary regulation characteristic; Timely adjust the preset flow rate of the coolant to prevent the temperature from being too high or too low. By intelligently calculating the adjustment range, the error that may be brought by manual adjustment is avoided, making the reaction temperature closer to the ideal state and improving the product quality and stability.

[0020] S4. According to the temperature change graph of the current nitration reaction, analyze the actual second temperature characteristic of the current nitration reaction, determine whether secondary regulation of the current nitration reaction is required, and perform secondary regulation; According to the above technical solution, the step S4 includes: S4-1. Regulate the temperature of the current nitration reaction according to the cooling start time and the preset flow rate of the coolant; set a unit time interval, obtain the temperature at the corresponding time after the unit time interval from the cooling start time, calculate the value obtained by subtracting the temperature at the corresponding time after the unit time interval from the cooling start time from the temperature at the cooling start time, and calculate the ratio of this value to the unit time interval, which is denoted as the actual second temperature characteristic of the current nitration reaction; S4-2. If the absolute value of the difference between the actual second temperature characteristic of the current nitration reaction and the prediction characteristic is denoted as the secondary regulation judgment quantity; If the secondary regulation judgment quantity is greater than or equal to the preset error value, then secondary regulation of the current nitration reaction is required; S4-3. When secondary regulation of the current nitration reaction is required, if the difference between the actual second temperature characteristic of the current nitration reaction and the prediction characteristic is negative, then reduce the preset flow rate, and the ratio of the value obtained by subtracting the reduced preset flow rate from the preset flow rate before reduction to the preset flow rate before reduction is the value obtained by multiplying the preset weight by the secondary regulation judgment quantity; If the difference between the actual second temperature characteristic of the current nitration reaction and the prediction characteristic is positive, then increase the preset flow rate, and the ratio of the value obtained by subtracting the preset flow rate before increase from the increased preset flow rate to the preset flow rate before increase is the value obtained by multiplying the preset weight by the secondary regulation judgment quantity; For example: The cooling start time of the current nitration reaction is t0 = 300, the temperature at the cooling start time is 85, and the preset flow rate of the coolant is 10; set the unit time interval to 60, and obtain the temperature at t1 = t0 + 60 = 360 as 80; calculate the actual second temperature characteristic of the current nitration reaction as (80 - 85) / 60 = -0.833; The predicted feature is -0.1; the calculated secondary regulation judgment quantity is ∣(−0.0833)−(−0.1)∣ = 0.0167; The preset error value is 0.015. Since 0.0167 ≥ 0.015, secondary regulation is required; The difference between the actual second temperature feature and the predicted feature of the current nitrification reaction is (−0.0833)−(−0.1)=0.0167, which is positive, so the preset flow rate is increased; The preset weight is 10; The value obtained by multiplying the preset weight by the secondary regulation judgment quantity is 10×0.0167 = 0.167; The ratio of the value obtained by subtracting the preset flow rate before increase from the preset flow rate after increase to the preset flow rate before increase is 0.167, so the preset flow rate after increase is 10.167; Through secondary adjustment, the accuracy of temperature control is improved, the error influence is reduced, the problems of lagging flow rate adjustment and slow response in the traditional mode are solved, the safety is improved, a closed-loop regulation system is formed, the temperature is ensured to be stable, and the quality fluctuation and safety hazards are reduced.

[0021] Please refer to Figure 2 , a manufacturing parameter regulation decision-making system for energetic materials, the system includes an acquisition training module, a reaction prediction module, a primary regulation module and a secondary regulation module; The acquisition training module is responsible for collecting, screening and analyzing the historical reaction records of the nitrification reaction, forming a training set, establishing and training a deep learning model, and providing data support for subsequent regulation; the reaction prediction module is used to monitor the current nitrification reaction in real time, analyze the cooling start time and the first temperature feature of the current nitrification reaction, and use the deep learning model to predict the reaction feature, providing a basis for regulation decision-making; the primary regulation module is used to judge whether primary regulation is required for the current nitrification reaction according to the predicted feature, and adjust the preset flow rate of the coolant; the secondary regulation module is used to analyze the actual second temperature feature of the current nitrification reaction according to the actual temperature change condition of the current nitrification reaction, and judge whether secondary regulation is required for the current nitrification reaction, and precisely control the current nitrification reaction to ensure that the temperature of the current nitrification reaction remains stable.

[0022] According to the above technical solution, the acquisition training module includes a data acquisition unit and a model training unit; The data acquisition unit is used to collect the reaction records of the nitrification reaction, including the raw material dosage, the start time of the reaction, the start time of cooling, the initial temperature of the cooling liquid, the average flow rate of the cooling liquid, the end time of the reaction, the end time of cooling, and the temperature change diagram, and store them in the database; the model training unit is used to screen the reaction records from the database, calculate the first temperature feature and the second temperature feature corresponding to each screened reaction record, form a training set, establish a deep learning model, and complete the training of the deep learning model.

[0023] According to the above technical solution, the reaction prediction module includes a feature extraction unit and a feature prediction unit; The feature extraction unit is used to obtain the temperature change data of the current nitrification reaction through a sensing device, and analyze the start time of cooling and the first temperature feature of the current nitrification reaction; the feature prediction unit is used to obtain the prediction feature of the current nitrification reaction according to the raw material dosage, the first temperature feature, the start time of cooling of the current nitrification reaction, the initial temperature of the cooling liquid, and the preset flow rate, in combination with the deep learning model.

[0024] According to the above technical solution, the primary regulation module includes a regulation determination unit and a flow rate adjustment unit; The regulation determination unit is used to judge whether the current nitrification reaction needs to be primarily regulated according to the prediction feature of the current nitrification reaction; the flow rate adjustment unit is used to analyze the flow rate adjustment value of the primary regulation if the current nitrification reaction needs to be primarily regulated, and adjust the preset flow rate.

[0025] According to the above technical solution, the secondary regulation module includes an error analysis unit and a dynamic adjustment unit; The error analysis unit is used to calculate the error between the actual temperature feature and the prediction feature, and judge whether the current nitrification reaction needs to be secondarily regulated; the dynamic adjustment unit is used to dynamically adjust the preset flow rate according to the error if the current nitrification reaction needs to be secondarily regulated, optimize the flow rate parameter, and ensure that the temperature change meets the expectation.

[0026] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0027] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A decision-making method for regulating manufacturing parameters of energetic materials, characterized in that: The method includes the following steps: S1. Collect the reaction records of the nitrification reaction and store them in a database; screen the reaction records in the database, analyze the first temperature feature and the second temperature feature of the reaction records, and form a training set; establish a deep learning model, and complete the training of the deep learning model through the training set; S2. Obtain the reaction start time and the temperature change graph of the current nitrification reaction, and analyze the cooling start time and the first temperature feature of the current nitrification reaction; extract the raw material dosage in the current nitrification reaction, as well as the initial temperature and the preset flow rate of the coolant from the database, and combine the deep learning model to analyze the prediction features of the current nitrification reaction; S3. According to the prediction features of the current nitrification reaction, determine whether it is necessary to perform a first regulation on the current nitrification reaction; if it is necessary to perform a first regulation on the current nitrification reaction, then analyze the flow rate adjustment value of the first regulation and adjust the preset flow rate; S4. According to the temperature change graph of the current nitrification reaction, analyze the actual second temperature feature of the current nitrification reaction, determine whether it is necessary to perform a second regulation on the current nitrification reaction, and perform the second regulation.

2. The method for regulating and controlling decision-making of manufacturing parameters for energetic materials according to claim 1, wherein: The step S1 includes: S1-1. Each time a nitrification reaction is carried out, a reaction record is generated and stored in the database; the reaction record includes raw material dosage, reaction start time, cooling start time, initial temperature of the coolant, average flow rate of the coolant, reaction end time, cooling end time and temperature change graph; S1-2. Extract the standard temperature range of the nitrification reaction from the database, extract the maximum and minimum values of the temperature from the temperature change graphs in each reaction record, and screen out the reaction records in which the maximum and minimum values of the temperature are within the standard temperature range of the nitrification reaction to form a first record set; S1-3. According to the first record set, obtain the temperature difference between the cooling start time and the reaction start time from the temperature change graph of a certain reaction record in the first record set, and obtain the time interval from the reaction start time to the cooling start time of the reaction record. Take the ratio between the temperature difference between the cooling start time and the reaction start time and the time interval from the reaction start time to the cooling start time in the reaction record as the first temperature feature of the reaction record; S1-4. According to the first record set, extract the temperature at the cooling start time of each reaction record in the first record set, and take the average value of the temperatures at the cooling start time of all reaction records in the first record set as the first temperature threshold; Obtain the time interval from the cooling start time to the cooling end time of each reaction record in the first record set, and take the average value of the time intervals from the cooling start time to the cooling end time of all reaction records in the first record set as the first time parameter; Calculate the ratio between the temperature difference between the cooling end time and the cooling start time in a certain reaction record and the time interval from the cooling start time to the cooling end time in the reaction record as the second temperature feature of the reaction record; Use the raw material dosage, initial coolant temperature, average coolant flow rate, and first temperature feature of each reaction record in the first record set as the input of the training set; use the second temperature feature of each reaction record in the first record set as the output of the training set to form a training set. S1-5. Establish a deep learning model and complete the training of the deep learning model through the training set.

3. The manufacturing parameter regulation and control decision-making method for energetic materials according to claim 2, characterized in that: The step S2 includes: S2-1. Obtain the reaction start time and temperature change graph of the current nitration reaction through a sensing device. If the temperature at a certain moment after the reaction start time of the current nitration reaction is greater than or equal to the first temperature threshold, use this moment as the cooling start time of the current nitration reaction. S2-2. Calculate the first temperature feature of the current nitration reaction according to the reaction start time, cooling start time, and temperature change graph of the current nitration reaction. Extract the raw material dosage of the current nitration reaction, the initial temperature of the coolant, and the preset flow rate from the database. Input the raw material dosage, first temperature feature, cooling start time, initial temperature of the coolant, and preset flow rate of the current nitration reaction into the trained deep learning model, and output the second temperature feature of the current nitration reaction as the prediction feature of the current nitration reaction.

4. The method for regulating and controlling decision-making of manufacturing parameters for energetic materials according to claim 3, characterized in that: The step S3 includes: S3-1. Calculate the value obtained by multiplying the prediction feature of the current nitration reaction by the first time parameter, denoted as the predicted change; calculate the value obtained by adding the first temperature threshold and the predicted change, denoted as the first regulation judgment quantity. S3-2. If the first regulation judgment quantity is not within the standard temperature range of the nitration reaction, then the current nitration reaction needs to be regulated once. S3-3. If the current nitration reaction needs to be regulated once, extract the minimum value in the standard temperature range of the nitration reaction, calculate the value obtained by subtracting the first temperature threshold from the minimum value in the standard temperature range of the nitration reaction, denoted as the first regulation change; calculate the ratio of the first regulation change to the first time parameter, denoted as the first regulation feature. S3-4. Use the raw material dosage, first temperature feature, cooling start time, and initial temperature of the coolant of the current nitration reaction as the input, use the first regulation feature as the output, combine with the deep learning model to obtain the average coolant flow rate as the flow rate adjustment value for the first regulation; adjust the preset flow rate to the value corresponding to the flow rate adjustment value for the first regulation; adjust the prediction feature to the value corresponding to the first regulation feature.

5. The manufacturing parameter regulation and control decision-making method for energetic materials according to claim 4, wherein: The step S4 includes: S4-1. Regulate the temperature of the current nitration reaction according to the cooling start time and the preset flow rate of the coolant; set a unit time interval, obtain the temperature at the corresponding moment after the unit time interval from the cooling start time, calculate the value obtained by subtracting the temperature at the corresponding moment after the unit time interval from the cooling start time from the temperature at the cooling start time, and calculate the ratio of this value to the unit time interval, denoted as the actual second temperature feature of the current nitration reaction. S4-2. If the absolute value of the difference between the actual second temperature feature and the prediction feature of the current nitration reaction is denoted as the second regulation judgment quantity. If the second regulation judgment quantity is greater than or equal to the preset error value, then the current nitration reaction needs to be regulated twice. S4-3. When secondary regulation of the current nitrification reaction is required, if the difference between the actual second temperature characteristic and the predicted characteristic of the current nitrification reaction is negative, the preset flow rate is decreased, and the ratio of the value obtained by subtracting the decreased preset flow rate from the preset flow rate before the decrease to the preset flow rate before the decrease is the value obtained by multiplying the preset weight by the secondary regulation judgment quantity. If the difference between the actual second temperature characteristic and the predicted characteristic of the current nitrification reaction is positive, the preset flow rate is increased, and the ratio of the value obtained by subtracting the preset flow rate before the increase from the increased preset flow rate to the preset flow rate before the increase is the value obtained by multiplying the preset weight by the secondary regulation judgment quantity.

6. A manufacturing parameter regulation and decision-making system for energetic materials, which is used to implement a manufacturing parameter regulation and decision-making method for energetic materials described in any one of claims 1-5, and is characterized in that: The system includes a data collection and training module, a reaction prediction module, a primary regulation module, and a secondary regulation module. The data collection and training module is responsible for collecting, screening, and analyzing the historical reaction records of the nitrification reaction, forming a training set, establishing a deep learning model, and training it to provide data support for subsequent regulation. The reaction prediction module is used to monitor the current nitrification reaction in real time, analyze the cooling start time and the first temperature characteristic of the current nitrification reaction, and use the deep learning model to predict the reaction characteristics to provide a basis for the regulation decision. The primary regulation module is used to determine whether primary regulation of the current nitrification reaction is required based on the predicted characteristics and adjust the preset flow rate of the coolant. The secondary regulation module is used to analyze the actual second temperature characteristic of the current nitrification reaction according to the actual temperature change situation of the current nitrification reaction, determine whether secondary regulation of the current nitrification reaction is required, and precisely control the current nitrification reaction to ensure that the temperature of the current nitrification reaction remains stable.

7. The manufacturing parameter regulation and decision-making system for energetic materials according to claim 6, wherein: The data collection and training module includes a data collection unit and a model training unit. The data collection unit is used to collect the reaction records of the nitrification reaction, including the raw material dosage, reaction start time, cooling start time, initial temperature of the coolant, average flow rate of the coolant, reaction end time, cooling end time, and temperature change diagram, and store them in the database. The model training unit is used to screen the reaction records from the database, calculate the first temperature characteristic and the second temperature characteristic corresponding to each screened reaction record, form a training set, establish a deep learning model, and complete the training of the deep learning model.

8. The manufacturing parameter regulation and control decision-making system for energetic materials according to claim 6, characterized in that: The reaction prediction module includes a feature extraction unit and a feature prediction unit. The feature extraction unit is used to obtain the temperature change data of the current nitrification reaction through a sensing device and analyze the cooling start time and the first temperature characteristic of the current nitrification reaction. The feature prediction unit is used to obtain the predicted characteristics of the current nitrification reaction according to the raw material dosage, the first temperature characteristic, the cooling start time of the current nitrification reaction, and the initial temperature and preset flow rate of the coolant, in combination with the deep learning model.

9. The manufacturing parameter regulation and control decision-making system for energetic materials according to claim 6, wherein: The primary regulation module includes a regulation determination unit and a flow rate adjustment unit. The regulation determination unit is used to judge whether primary regulation of the current nitrification reaction is required based on the predicted characteristics of the current nitrification reaction. The flow rate adjustment unit is used to analyze the flow rate adjustment value for primary regulation and adjust the preset flow rate if primary regulation of the current nitrification reaction is required.

10. The manufacturing parameter regulation and control decision-making system for energetic materials according to claim 6, wherein: The secondary regulation module includes an error analysis unit and a dynamic adjustment unit. The error analysis unit is used to calculate the error between the actual temperature feature and the predicted feature, and determine whether secondary regulation of the current nitrification reaction is required; the dynamic adjustment unit is used to perform secondary regulation on the current nitrification reaction if necessary, dynamically adjust the preset flow rate according to the error, optimize the flow rate parameters, and ensure that the temperature change meets the expectation.

Images