A dynamic tubular continuous nitration process simulation device and simulation system

Abstract

The present invention discloses a dynamic tubular continuous nitration process simulation device and simulation system, which relates to the field of process simulation technology, including: building a simulated nitration training channel; obtaining a first nitration control parameter, inputting the simulated nitration training channel, performing a simulated nitration simulation, outputting a first nitration rate, a first nitration mass, and a first nitration temperature distribution, and calculating a first nitration fitness; when the first nitration fitness does not meet training requirements, calculating the score matching degree of the nitration training score; optimizing the nitration training score to obtain the optimal nitration training score, displaying it to an operator, and continuing nitration process control training until the training requirements are met, completing the nitration process simulation training. The present invention solves the technical problem that the prior art cannot efficiently evaluate the matching between nitration process parameters and fitness, and is difficult to achieve dynamic optimization, thereby achieving the technical effect of improving control adaptability.

Description

Technical Field

[0001] The present invention relates to the technical field of process simulation, and in particular to a dynamic tubular continuous nitration process simulation device and a simulation system. Background Art

[0002] With the continuous improvement of industrial production and environmental protection requirements, dynamic tubular continuous nitration processes have been widely used in water treatment, chemical production and other fields. However, with the increasing process complexity and expansion of production scale, the control and management of nitration processes face severe challenges. Traditional nitration process control methods generally use static or experience-driven means, which suffer from low control accuracy, insufficient parameter matching, and poor dynamic response capabilities. These methods are difficult to adapt to the efficiency, accuracy, and real-time requirements of modern industrial production. Summary of the Invention

[0003] The present application provides a dynamic tubular continuous nitration process simulation device and simulation system, which are used to solve the technical problem that the existing technology cannot efficiently evaluate the matching between nitration process parameters and adaptability, and is difficult to achieve dynamic optimization.

[0004] In view of the above problems, the present application provides a dynamic tubular continuous nitration process simulation device and simulation system.

[0005] In a first aspect of the present application, a dynamic tubular continuous nitration process simulation device is provided, comprising:

[0006] A training channel construction module, wherein the training channel construction module obtains basic process parameters of the tubular continuous nitrification process and constructs a simulated nitrification training channel; a simulated nitrification simulation module, wherein the simulated nitrification simulation module obtains a first nitrification control parameter input by an operator, inputs the parameter into the simulated nitrification training channel, performs a simulated nitrification simulation, outputs a first nitrification rate, a first nitrification mass, and a first nitrification temperature distribution, and calculates a first nitrification fitness; a score matching calculation module, wherein when the first nitrification fitness does not meet the training requirements, the score matching calculation module randomly generates a nitrification training score, and calculates the score matching of the nitrification training score in combination with the first nitrification fitness; and a simulation training module, wherein the simulation training module optimizes the nitrification training score to obtain an optimal nitrification training score, displays the optimal score to the operator, and continues the nitrification process control training until the training requirements are met and the nitrification process simulation training is completed.

[0007] A second aspect of the present application provides a dynamic tubular continuous nitration process simulation system, the system comprising:

[0008] The memory is used to store executable instructions; the processor is used to implement a dynamic tubular continuous nitration process simulation device provided by the present application when executing the executable instructions stored in the memory.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The present application obtains the basic process parameters of a tubular continuous nitration process and builds a simulated nitration training channel; obtains a first nitration control parameter input by an operator, inputs the simulated nitration training channel, performs a simulated nitration simulation, outputs a first nitration rate, a first nitration quality, and a first nitration temperature distribution, and calculates a first nitration fitness; when the first nitration fitness does not meet the training requirements, randomly generates a nitration training score, and calculates the score matching of the nitration training score in combination with the first nitration fitness; optimizes the nitration training score to obtain the optimal nitration training score, displays it to the operator, and continues nitration process control training until the training requirements are met and the nitration process simulation training is completed. The present invention solves the technical problem that the prior art cannot efficiently evaluate the matching of nitration process parameters and fitness and is difficult to achieve dynamic optimization. By using a simulated nitration training channel, combined with the control parameters input by the operator, the nitration process is dynamically simulated and fitness is evaluated. For situations where the requirements are not met, a training score is randomly generated and iteratively optimized to obtain the optimal training score until the training requirements are met, thereby achieving accurate simulation and dynamic optimization of nitration process training and achieving the technical effect of improving control adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic structural diagram of a dynamic tubular continuous nitration process simulation device provided in an embodiment of the present application;

[0013] Figure 2 This is a structural diagram of an exemplary dynamic tubular continuous nitration process simulation system of this application.

[0014] Explanation of the accompanying symbols: training channel construction module 11, simulation nitration simulation module 12, score matching calculation module 13, simulation training module 14, bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0015] The present application provides a dynamic tubular continuous nitration process simulation device and simulation system to solve the technical problem that the existing technology cannot efficiently evaluate the matching between nitration process parameters and fitness, and is difficult to achieve dynamic optimization. Through the simulation nitration training channel, combined with the control parameters input by the operator, the nitration process is dynamically simulated and the fitness is evaluated. For situations that do not meet the requirements, training scores are randomly generated and iterative optimization is performed to obtain the optimal training score until the training requirements are met, thereby realizing accurate simulation and dynamic optimization of nitration process training and achieving the technical effect of improving control adaptability.

[0016] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0017] It should be noted that any variations of the terms "include" and "have" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Example 1, as Figure 1 As shown, the present application provides a dynamic tubular continuous nitration process simulation device, the device comprising:

[0019] The training channel building module 11 obtains basic process parameters of the tubular continuous nitrification process and builds a simulated nitrification training channel.

[0020] Furthermore, in the apparatus provided in the embodiment of the application, the training channel building module 11 is further used to:

[0021] The basic process parameters of the tubular continuous nitration process are obtained; based on the basic process parameters, a set of sample nitration control parameters of the same tubular continuous nitration process in a historical period, as well as the speed, mass and temperature distribution of the nitration process under different sample nitration control parameters are retrieved, and the sets are labeled as a sample nitration speed set, a sample nitration mass set and a sample nitration temperature distribution set, wherein each sample nitration temperature distribution includes the temperatures at multiple positions of the reaction pipeline; the sample nitration control parameter set is used as simulation input data, and the sample nitration speed set, the sample nitration mass set and the sample nitration temperature distribution set are used as simulation supervision data; the simulation input data and the simulation supervision data are used to construct and train a nitration training channel using machine learning to obtain a nitration training channel.

[0022] In an embodiment of the present application, the training channel construction module first extracts the basic process parameters of the tubular continuous nitration process from the historical database, including the geometric structure of the reaction pipeline (such as length, diameter), material properties, and operating conditions (such as temperature range, pressure range), etc.

[0023] Then, based on the basic process parameters obtained, relevant sample data of the same tubular continuous nitration process in the historical time are retrieved to construct a multidimensional sample set. Specifically, it includes a sample nitration control parameter set, which records the control parameter values used in different historical operations, such as reactant concentration, reactant flow rate and input temperature; a sample nitration rate set, which reflects the nitration rate under the corresponding control parameter conditions, to reveal the kinetic characteristics of the nitration reaction; a sample nitration quality set, which is the quality data of the product under different process conditions, that is, the purity of the product; and a sample nitration temperature distribution set, which records the temperature distribution at multiple positions of the reaction pipeline to describe the thermodynamic characteristics and heat transfer characteristics of the reaction. The speed, mass and temperature distribution of the nitration process under the control of different sample nitration control parameters are marked as a sample nitration rate set, a sample nitration mass set and a sample nitration temperature distribution set.

[0024] After data preparation is complete, these sample data are used to construct the input and supervisory datasets for the simulation model. Specifically, a set of sample nitrification control parameters is used as the simulation input data, while a set of sample nitrification rates, sample nitrification masses, and sample nitrification temperature distributions are used as the simulation supervisory data. This data is then trained using machine learning techniques, such as random forests. The model learns the complex mapping relationships between nitrification control parameters and nitrification rates, masses, and temperature distributions, constructing a simulation training pipeline capable of accurately predicting reaction outcomes. Upon completion of the training, a nitrification training pipeline is generated.

[0025] The simulated nitrification simulation module 12 obtains the first nitrification control parameter input by the operator, inputs the first nitrification training channel, performs simulated nitrification simulation, outputs the first nitrification rate, the first nitrification quality and the first nitrification temperature distribution, and calculates and obtains the first nitrification fitness.

[0026] Furthermore, in the device provided in the embodiment of the application, the simulated nitration simulation module 12 is further used to:

[0027] A first nitrification control parameter input by an operator performing operation training is obtained; the first nitrification control parameter is input into a simulated nitrification training channel, a simulated nitrification simulation is performed, and a first nitrification rate, a first nitrification quality, and a first nitrification temperature distribution are output; and a first nitrification fitness is calculated based on the first nitrification rate, the first nitrification quality, and the first nitrification temperature distribution.

[0028] In the embodiment of the present application, the simulated nitration simulation module first obtains first nitration control parameters, including reactant flow rate, reactant concentration, and reaction temperature, input by the operator based on training objectives. The first nitration control parameters are then fed into the simulated nitration training channel to perform a simulated nitration simulation. The simulated nitration training channel calculates based on the input control parameters and outputs a first nitration rate, a first nitration mass, and a first nitration temperature distribution.

[0029] Finally, the first nitrification fitness is obtained by calculating the first nitrification rate, the first nitrification quality and the first nitrification temperature distribution based on the previously introduced formula.

[0030] Furthermore, in the device provided in the embodiment of the application, the simulated nitration simulation module 12 is further used to:

[0031] Calculate the average of the temperatures at multiple locations within the first nitrification temperature distribution to obtain a first average temperature; and calculate a first nitrification fitness based on the first nitrification rate, the first nitrification quality, and the first average temperature, as shown in the following formula:

[0032] ;

[0033] Among them, XHF is the nitrification fitness, 、 and is the weight, is the nitrification rate, is the preset nitrification rate, Q is the nitrification quality, is the average temperature, is the preset temperature.

[0034] In the embodiment of the present application, firstly, a statistical analysis is performed on the temperatures at multiple locations within the first nitration temperature distribution, and the mean thereof is calculated to obtain a first average temperature.

[0035] Next, the first nitrification rate, first nitrification quality and first average temperature are substituted into the formula to calculate and determine the first nitrification fitness. The formula is ; Among them, XHF is the nitrification fitness, 、 and The weight is pre-set by technical experts according to the importance. is the nitrification rate, is the preset nitrification rate, Q is the nitrification quality, is the average temperature, is the preset temperature. and Also set by technical experts.

[0036] The score matching degree calculation module 13 randomly generates a nitrification training score when the first nitrification fitness does not meet the training requirements, and calculates the score matching degree of the nitrification training score in combination with the first nitrification fitness.

[0037] In this embodiment of the present application, the score matching calculation module first compares the first nitrification fitness with a preset nitrification fitness threshold to determine whether the first nitrification fitness is greater than the preset nitrification fitness threshold. If it is less than the preset nitrification fitness threshold, the first nitrification fitness is deemed to fail the training requirement. At this point, a nitrification training score is randomly generated, where the nitrification training score ranges from 1 to 100.

[0038] Then, the ratio of the nitration training score to the maximum training score in the training score interval is calculated, that is, the ratio of the nitration training score to 100 is calculated to obtain the score distribution coefficient.

[0039] Then, the nitrification control data in the historical period of the historical database is obtained and processed to obtain the nitrification fitness range. Then, the ratio of the first nitrification fitness to the maximum nitrification fitness in the nitrification fitness range is calculated to obtain the fitness distribution coefficient.

[0040] Finally, the difference between the score distribution coefficient and the fitness distribution coefficient is calculated to obtain the deviation percentage, and the deviation percentage is subtracted from 1 to obtain the score matching degree. For example, the difference between the score distribution coefficient and the fitness distribution coefficient can also be calculated, and then the fitness distribution coefficient is subtracted to obtain the deviation percentage, and the deviation percentage is subtracted from 1 to obtain the score matching degree.

[0041] Furthermore, in the apparatus provided in the embodiment of the application, the score matching calculation module 13 is further configured to:

[0042] Determine whether the first nitrification fitness is greater than or equal to a preset nitrification fitness threshold; if so, the training requirement is met; otherwise, the training requirement is not met; when the training requirement is not met, randomly generate a nitrification training score within a training score range; and calculate a score matching degree of the nitrification training score in combination with the first nitrification fitness.

[0043] In the present embodiment, the first nitrification fitness is first compared with a preset nitrification fitness threshold. If the first nitrification fitness is greater than or equal to the preset nitrification fitness threshold, it is determined that the current training requirements have been met and the nitrification process has reached the preset standard, and no further adjustment is required. If the first nitrification fitness is less than the threshold, it is determined that the current fitness does not meet the training requirements.

[0044] When the fitness does not meet the training requirements, a nitration training score is randomly generated within the training score range (usually 1 to 100).

[0045] Then, the score matching degree is calculated by combining the first nitrification temperature distribution and the first nitrification fitness. When calculating the score matching degree, the score distribution coefficient is first obtained by calculating the ratio of the randomly generated nitrification training score to the maximum value (100) in the training score interval. The score distribution coefficient represents the relative level of the current training score within the entire training range and is used to quantify the intensity of the training target. Then, the nitrification fitness interval (i.e., the historical fitness range) is calculated based on the historical nitrification process data, and the first nitrification fitness is calculated by calculating the ratio of the first nitrification fitness to the maximum value of the fitness interval to obtain the fitness distribution coefficient, which is used to evaluate the historical performance of the current fitness.

[0046] Finally, by calculating the difference between the score distribution coefficient and the fitness distribution coefficient, we get the deviation percentage, which represents the degree of difference between the current score and the fitness. The final score match is calculated by "1 minus the deviation percentage".

[0047] Furthermore, in the apparatus provided in the embodiment of the application, the score matching calculation module 13 is further configured to:

[0048] The ratio of the nitrification training score to the maximum training score within the training score interval is calculated to obtain a score distribution coefficient; the nitrification fitness interval is obtained by calculation and processing based on the nitrification control data within the historical time; the ratio of the first nitrification fitness to the maximum nitrification fitness within the nitrification fitness interval is calculated to obtain a fitness distribution coefficient; the deviation percentage between the score distribution coefficient and the fitness distribution coefficient is calculated, and the deviation percentage is subtracted from 1 to obtain a score matching degree.

[0049] In the present embodiment, the score distribution coefficient is first calculated, which is the ratio of the randomly generated nitration training score to the maximum training score within the training score interval. The maximum training score interval is usually 100. The score distribution coefficient is obtained by dividing the maximum training score within the training score interval by the nitration training score.

[0050] Next, the nitrification fitness of each set of data is calculated based on the historical nitrification control data. Specifically, the nitrification fitness range is obtained by performing the calculation in the same manner as the above-mentioned calculation to obtain the first nitrification fitness.

[0051] The first nitrification fitness is then compared to the maximum fitness within the nitrification fitness range to obtain a fitness distribution coefficient. Specifically, the maximum fitness within the nitrification fitness range is divided by the first nitrification fitness to obtain the fitness distribution coefficient.

[0052] Then, the fitness distribution coefficient is subtracted from the score distribution coefficient to get the deviation percentage. Finally, the deviation percentage is subtracted from 1 to get the score matching degree.

[0053] The simulation training module 14 optimizes the nitrification training score, obtains the optimal nitrification training score, displays it to the operator, and continues the nitrification process control training until the training requirements are met and the nitrification process simulation training is completed.

[0054] In this embodiment, the simulation training module first randomly generates nitration training scores and calculates the matching degree of each generated score. Subsequently, iterative optimization is performed based on the score matching degree, adjusting the training scores and gradually approaching the optimal state until the score matching degree converges. Ultimately, the training score with the highest score matching degree is output as the optimal nitration training score and displayed to the operator.

[0055] After the operator views the optimal nitrification training score, the operator continues to receive new nitrification control parameters and repeats the training process based on the simulation results until the parameters input by the operator meet the training requirements, completing the nitrification process simulation training.

[0056] Furthermore, in the apparatus provided in the embodiment of the application, the simulation training module 14 is further configured to:

[0057] Continue to randomly generate nitrification training scores, calculate the score matching degree, perform iterative optimization of the nitrification training scores until convergence, output the nitrification training score with the maximum score matching degree, and obtain the optimal nitrification training score; display the optimal nitrification training score to the operator; continue to receive nitrification control parameters input by the operator until the training requirements are met and the nitrification process simulation training is completed.

[0058] In the embodiment of the present application, firstly, a nitration training score (ranging from 1 to 100) is randomly generated, and the score matching degree is obtained by calculation using the same method as described above.

[0059] Afterwards, new nitration training scores are randomly generated, and the score matching is calculated one by one. The training scores and matching results of each round are recorded for optimization and screening. In each iteration, the direction and range of generated training scores are adjusted based on the changing trend of matching, gradually approaching the optimal result.

[0060] The key to the optimization process is convergence. When the change in score matching over multiple iterations (e.g., five rounds) falls below a set threshold (e.g., 0.001), the optimization process is considered to have reached convergence, and new training scores are no longer randomly generated. The training score with the highest matching score is selected from all recorded training scores and becomes the optimal nitration training score for the current process conditions.

[0061] The optimal nitrification training score is then visually displayed to the operator. The system then receives new nitrification control parameters entered by the operator. The corresponding nitrification training score is recalculated based on the new nitrification control parameters and compared with the preset nitrification training score. If the calculated nitrification training score is greater than or equal to the preset nitrification training score, the training requirements are considered met and the nitrification process simulation training is complete. Otherwise, the above process is repeated, with continued optimization and training, until the preset requirements are met.

[0062] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0063] The present application obtains the basic process parameters of a tubular continuous nitration process and builds a simulated nitration training channel; obtains a first nitration control parameter input by an operator, inputs the simulated nitration training channel, performs a simulated nitration simulation, outputs a first nitration rate, a first nitration quality, and a first nitration temperature distribution, and calculates a first nitration fitness; when the first nitration fitness does not meet the training requirements, randomly generates a nitration training score, and calculates the score matching of the nitration training score in combination with the first nitration fitness; optimizes the nitration training score to obtain the optimal nitration training score, displays it to the operator, and continues nitration process control training until the training requirements are met and the nitration process simulation training is completed. The present invention solves the technical problem that the prior art cannot efficiently evaluate the matching of nitration process parameters and fitness and is difficult to achieve dynamic optimization. By using a simulated nitration training channel, combined with the control parameters input by the operator, the nitration process is dynamically simulated and fitness is evaluated. For situations where the requirements are not met, a training score is randomly generated and iteratively optimized to obtain the optimal training score until the training requirements are met, thereby achieving accurate simulation and dynamic optimization of nitration process training and achieving the technical effect of improving control adaptability.

[0064] In the second embodiment, based on the same inventive concept as the dynamic tubular continuous nitration process simulation device in the aforementioned embodiment, the present application also provides a dynamic tubular continuous nitration process simulation system, comprising: at least one processor; a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the steps of any one of the devices described in the aforementioned embodiment one.

[0065] Figure 2 This is a schematic diagram of the structure of a dynamic tubular continuous nitration process simulation system for this application. Figure 2 In the figure, the bus architecture is represented by bus 300, which can include any number of interconnected buses and bridges. Bus 300 connects various circuits including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 can be used to store data used by processor 302 when performing operations.

[0066] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0068] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A dynamic tubular continuous nitration process simulation device, characterized in that: The device comprises: A training channel building module, wherein the training channel building module obtains basic process parameters of the tubular continuous nitrification process and builds a simulated nitrification training channel; a simulated nitrification simulation module, wherein the simulated nitrification simulation module obtains a first nitrification control parameter input by an operator, inputs the first nitrification control parameter into the simulated nitrification training channel, performs a simulated nitrification simulation, outputs a first nitrification rate, a first nitrification quality, and a first nitrification temperature distribution, and calculates a first nitrification fitness; a score matching degree calculation module, wherein when the first nitrification fitness does not meet the training requirements, the score matching degree calculation module randomly generates a nitrification training score, and calculates the score matching degree of the nitrification training score in combination with the first nitrification fitness, wherein the nitrification training score is 1 to 100; A simulation training module, wherein the simulation training module optimizes the nitrification training score, obtains the optimal nitrification training score, displays the optimal score to the operator, and continues the nitrification process control training until the training requirements are met and the nitrification process simulation training is completed; Simulation training modules, including: Continue to randomly generate nitrification training scores, calculate the score matching degree, perform iterative optimization of the nitrification training scores until convergence, output the nitrification training score with the largest score matching degree, and obtain the optimal nitrification training score; Displaying the optimal nitration training score to the operator; Continue to receive nitrification control parameters input by the operator until the training requirements are met and the nitrification process simulation training is completed.

2. The dynamic tubular continuous nitration process simulation device according to claim 1, characterized in that: Training channel building module, used for: Obtain the basic process parameters of the tubular continuous nitration process; Based on the basic process parameters, a set of sample nitration control parameters for the same tubular continuous nitration process over a historical period of time is retrieved, as well as the speed, mass, and temperature distributions of the nitration process under different sample nitration control parameters, which are labeled as a sample nitration speed set, a sample nitration mass set, and a sample nitration temperature distribution set, wherein each sample nitration temperature distribution includes temperatures at multiple locations in the reaction pipeline; Using the sample nitrification control parameter set as simulation input data, and using the sample nitrification rate set, sample nitrification quality set, and sample nitrification temperature distribution set as simulation supervision data; The simulation input data and the simulation supervision data are used, and machine learning is utilized to construct and train a nitrification training channel to obtain a nitrification training channel.

3. The dynamic tubular continuous nitration process simulation device according to claim 1, characterized in that: Nitrification simulation module for: obtaining a first nitrification control parameter input by an operator undergoing operation training; Inputting the first nitrification control parameter into a simulated nitrification training channel to perform a simulated nitrification simulation, and outputting a first nitrification rate, a first nitrification quality, and a first nitrification temperature distribution; A first nitrification fitness is obtained by calculation according to the first nitrification rate, the first nitrification quality and the first nitrification temperature distribution.

4. The dynamic tubular continuous nitration process simulation device according to claim 3, characterized in that: Nitrification simulation module for: Calculating an average of temperatures at multiple locations within the first nitrification temperature distribution to obtain a first average temperature; According to the first nitrification rate, the first nitrification quality and the first average temperature, the first nitrification fitness is calculated as follows: Among them, XHF is the nitrification fitness, w1, w2 and w3 are weights, V r is the nitrification rate, V y is the preset nitrification rate, Q is the nitrification quality, T r is the average temperature, T y is the preset temperature.

5. The dynamic tubular continuous nitration process simulation device according to claim 1, characterized in that: Score matching calculation module, used for: determining whether the first nitrification fitness is greater than or equal to a preset nitrification fitness threshold; if so, the training requirement is met; otherwise, the training requirement is not met; When the training requirements are not met, a nitration training score is randomly generated within the training score range; The score matching degree of the nitrification training score is calculated based on the first nitrification temperature distribution and the first nitrification fitness.

6. The dynamic tubular continuous nitration process simulation device according to claim 5, characterized in that: Score matching calculation module, used for: Calculating the ratio of the nitration training score to the maximum training score within the training score interval to obtain a score distribution coefficient; Based on the historical nitrification control data, the nitrification fitness range is calculated and processed; Calculating a ratio of the first nitrification fitness to a maximum nitrification fitness within the nitrification fitness range to obtain a fitness distribution coefficient; The deviation percentage between the score distribution coefficient and the fitness distribution coefficient is calculated, and the score matching degree is obtained by subtracting the deviation percentage from 1.

7. A dynamic tubular continuous nitration process simulation system, characterized in that: The system comprises: a memory for storing executable instructions; The processor is configured to implement a dynamic tubular continuous nitration process simulation device according to any one of claims 1 to 6 when executing the executable instructions stored in the memory.

Images