Storage medium, and optimization method, device and equipment for multi-effect rectification process flow

Abstract

The invention discloses a storage medium, and an optimization method, device and equipment for a multi-effect rectification process flow. The method comprises the following steps: constructing a mechanism model comprising each rectification tower in a multi-effect rectification system; respectively constructing a first correlation function and a second correlation function; generating a data set of a preset group number of process parameters; the data set serves as input, and the reboiler thermal load of the highest-pressure rectifying tower is obtained through mechanism model calculation and serves as theoretical output; taking the data set of the process parameters and theoretical output as modeling data, and generating a prediction model capable of predicting the thermal load of the reboiler of the highest-pressure rectifying tower according to the process parameters through deep learning; and obtaining predicted parameter values of the controllable process parameters when the maximum pressure rectifying tower reboiler has the minimum energy consumption through the prediction model. According to the method, the number of process parameters participating in calculation and the solving difficulty in subsequent optimization calculation can be greatly reduced, and the calculation efficiency of obtaining the optimal solution can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of rectification separation, and particularly to a storage medium, an optimization method, device and equipment for a multi-effect rectification process flow. Background Art

[0002] Multi-effect rectification is an efficient energy-saving process. In specific applicable application scenarios, through the form of heat coupling between the condenser of the high-pressure tower and the reboiler of the low-pressure tower, the consumption of heat utility engineering required for the rectification process can be reduced, thereby significantly reducing the energy consumption required for separation. In practical applications, multi-effect rectification can be an operation process in which multiple rectification towers with gradually decreasing pressures are connected in series; among them, the overhead vapor of the previous rectification tower is used as the heating medium for the reboiler of the subsequent rectification tower. Since in the multi-effect rectification process, except for the rectification towers at both ends, the intermediate rectification devices generally do not need to introduce heating medium and cooling medium from the outside, so it can play an energy-saving role.

[0003] In the prior art, when optimizing the process flow of multi-effect rectification through process control, generally the conventional sequential module sensitivity analysis idea is adopted for optimization design.

[0004] The inventor has found through research that the optimization process of optimizing the process flow of rectification in the prior art has at least the following defects:

[0005] Due to the strong coupling of the multi-effect rectification process and the mutual influence between different process parameters, the amount of calculation in the solution process is very large and it is difficult to obtain the optimal solution, thereby resulting in a poor optimization effect on the overall energy consumption of the multi-effect rectification equipment.

[0006] The information disclosed in this background art section is only intended to increase the understanding of the overall background of the present invention, and should not be regarded as an admission or any form of implication that this information constitutes the prior art already known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to reduce the number of process parameters involved in the optimization calculation and the difficulty of solution, and improve the calculation efficiency of obtaining the optimal solution.

[0008] The present invention provides an optimization method for a multi-effect rectification process flow, including the steps:

[0009] S11. Determine the feed state of the multi-effect rectification system according to the target separation task, and construct a mechanism model including each rectification tower in the multi-effect rectification system by taking the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraint conditions, through the determined number of effects of the multi-effect rectification and the operating pressure of each rectification tower;

[0010] S12. Respectively construct the first correlation functions between the reboiler heat loads of each distillation column and the flow rate and purity of its bottom product, and respectively construct the second correlation functions between the condenser heat loads of each distillation column and the reboiler heat loads of the next distillation column;

[0011] S13. Set a preset number of data sets for the preset process parameters that are the independent variables of the mechanism model; use the reboiler heat load of the highest-pressure distillation column corresponding to the preset number of data sets calculated through the mechanism model as the theoretical output with the data sets as the input;

[0012] S14. Use the data sets of the preset process parameters and the theoretical output as modeling data, and generate a prediction model through deep learning that can predict the reboiler heat load of the highest-pressure distillation column based on the process parameters;

[0013] S15. According to the first correlation function, the second correlation function, and specific process parameters, obtain the predicted parameter values of each controllable process parameter at the minimum energy consumption of the reboiler of the highest-pressure distillation column through the prediction model; the specific process parameters include: the number of effects of multi-effect distillation, the operating pressure of the distillation column, and the bottom product composition index with set values, and the feed position of the distillation column and the light component extraction amount of the distillation column as controllable process parameters.

[0014] Preferably, in the present invention, it further includes:

[0015] S16. Use the parameter values of each process parameter at the minimum energy consumption of the reboiler of the highest-pressure distillation column obtained by the prediction model as the input, and calculate the corresponding reboiler heat load of the highest-pressure distillation column through the mechanism model as the reference output;

[0016] S17. When the absolute value of the difference between the predicted parameter values is greater than the preset calculation tolerance, increase the value of the preset number of data sets and return to step S13.

[0017] On the other hand of the present invention, there is also provided an optimization device for a multi-effect distillation process flow, including:

[0018] A mechanism model generation unit, configured to determine the feed state of the multi-effect distillation system according to the target separation task, and construct a mechanism model including each distillation column in the multi-effect distillation system by taking the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraint conditions and through the determined number of effects of multi-effect distillation and the operating pressure of each distillation column;

[0019] A correlation function construction unit, configured to respectively construct the first correlation models between the reboiler heat loads of each distillation column and the flow rate and purity of its bottom product, and respectively construct the second correlation functions between the condenser heat loads of each distillation column and the reboiler heat loads of the next distillation column;

[0020] A modeling data generation unit, configured to set a preset number of data sets for preset process parameters that are independent variables of the mechanism model; and use the reboiler heat load of the highest-pressure rectification column corresponding to the preset number of data sets calculated through the mechanism model with the data sets as inputs as the theoretical output.

[0021] A prediction model generation unit, configured to use the data sets of the preset process parameters and the theoretical output as modeling data, and generate a prediction model capable of predicting the reboiler heat load of the highest-pressure rectification column according to the process parameters through deep learning.

[0022] An optimization parameter calculation unit, configured to obtain the predicted parameter values of each controllable process parameter at the minimum energy consumption of the reboiler of the highest-pressure rectification column through the prediction model according to the first correlation function, the second correlation function, and specific process parameters; the specific process parameters include: the number of effects of multi-effect rectification with preset values, the operating pressure of the rectification column, and the bottom product composition index, and, as controllable process parameters, the feed position of the rectification column and the light component extraction amount of the rectification column.

[0023] Preferably, in the present invention, it further includes:

[0024] A reference data generation unit, configured to use the parameter values of each process parameter at the minimum energy consumption of the reboiler of the highest-pressure rectification column obtained by the prediction model as inputs, and calculate the corresponding reboiler heat load of the highest-pressure rectification column through the mechanism model as the reference output.

[0025] A prediction model optimization unit, when the absolute value of the difference between the predicted parameter values is greater than a preset calculation tolerance, increases the value of the preset number of sets and returns to the modeling data generation unit.

[0026] On the other hand of the embodiment of the present invention, there is also provided an optimization device for a multi-effect rectification process flow. The optimization device for the multi-effect rectification process flow includes a computer program stored on a medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer is made to execute the methods described in the above various aspects and achieve the same technical effects.

[0027] On the other hand of the embodiment of the present invention, there is also provided a storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes each step of the optimization method for the multi-effect rectification process flow as described in any one of the above.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention first constructs a mechanism model of a multi-effect distillation system; on the other hand, the present invention also constructs a first correlation function between the reboiler heat load of each distillation column and its bottom product flow rate and purity, and a second correlation function between the condenser heat load of each distillation column and the reboiler heat load of the next distillation column; the present invention uses the mechanism model to simulate and generate a preset number of modeling data as the modeling data to construct a prediction model for predicting the reboiler heat load of the highest-pressure distillation column according to process parameters.

[0030] In the present invention, through the collaborative optimization of the mechanism model and deep learning, the multi-variable optimization of the multi-effect distillation process with strong coupling and many related factors is carried out, thus solving the problems in the prior art that the single-variable sensitivity analysis by the conventional sequential modular method has a large amount of calculation and it is difficult to find the optimal solution. In addition, in the present invention, two constructed correlation functions are also used to reduce the number of process parameters required for calculating the process, and only the feed position and the top product flow rate of each individual distillation column are left as two controllable process parameters, thereby greatly reducing the difficulty of optimization and solution.

[0031] In addition, different from the data-driven modeling methods commonly used in the manufacturing industry in the prior art, in the present invention, the output of the modeling data in deep learning is calculated based on the mechanism model, and the modeling data used in deep learning can be reasonably distributed within the set variable range according to the user's experience. Therefore, the optimization design method of the embodiments of the present invention has stronger extensibility, and the prediction accuracy of the generated prediction model is also higher.

[0032] The above description is only an overview of the technical solution of the present invention. In order to be able to more clearly understand the technical means of the present invention and implement it according to the content of the specification, and at the same time to make the above and other purposes, technical features and advantages of the present invention more understandable, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 is a step diagram of the optimization method of the multi-effect distillation process flow described in the present invention;

[0034] Figure 2 is a structural schematic diagram of the optimization device of the multi-effect distillation process flow described in the present invention;

[0035] Figure 3 is a structural schematic diagram of the optimization equipment of the multi-effect distillation process flow described in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0036] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific embodiments.

[0037] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or variations thereof such as "comprises" or "comprising" shall be understood to include the stated element or component and not to exclude other elements or other components.

[0038] In this document, for convenience of description, spatial relative terms such as "below", "beneath", "lower", "above", "upper", etc. may be used to describe the relationship of one element or feature to another element or feature in the drawings. It should be understood that spatial relative terms are intended to encompass different orientations of the object in use or operation in addition to the orientation depicted in the figures. For example, if the object in the figure is flipped, the element described as "below" or "beneath" other elements or features will be oriented "above" the element or feature. Thus, the exemplary term "below" can encompass both the lower and upper directions. The object can also have other orientations (rotated 90 degrees or other orientations) and the spatial relative terms used herein should be interpreted accordingly.

[0039] In this document, terms such as "first", "second", etc. are used to distinguish two different elements or parts and are not used to define a specific position or relative relationship. In other words, in some embodiments, the terms "first", "second", etc. can also be interchanged with each other.

[0040] Embodiment 1

[0041] In order to improve the optimization effect of the overall energy consumption of the multi-effect distillation equipment, as Figure 1 shown, in an embodiment of the present invention, an optimization method for a multi-effect distillation process flow is provided, including the steps:

[0042] S11. Determine the feed state of the multi-effect distillation system according to the target separation task, and construct a mechanism model including each distillation column in the multi-effect distillation system by taking the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraints and determining the number of effects of the multi-effect distillation and the operating pressure of each distillation column.

[0043] In an embodiment of the present invention, the feed state may specifically include the temperature, pressure, flow rate, and composition of the feed, etc.; the relevant physical properties may specifically include the boiling point, critical pressure, critical temperature, thermal decomposition temperature, freezing point at a specific composition, etc. of each component. This step may specifically include:

[0044] For a specific separation task (i.e., the target separation task), first, it is necessary to determine the temperature, pressure, flow rate, and composition of the feed of the multi-effect distillation system, and design the multi-effect distillation process according to the boiling points of each component in the multi-effect distillation system at different pressures.

[0045] When determining the number of effects in multi-effect distillation and preliminarily designing the process flow, it is necessary to pay attention to whether phenomena such as exceeding the critical temperature and pressure, thermal decomposition, and coking will occur in the process streams within the process temperature and pressure operating ranges, which may affect the stable operation and product quality. The above issues need to be analyzed according to specific separation tasks and used as constraints for designing the multi-effect distillation process.

[0046] In addition, the minimum heat transfer temperature difference of the multi-effect distillation system also needs to be used as a constraint for designing the multi-effect distillation process.

[0047] After fully considering the above constraints, preliminarily design the multi-effect distillation process flow, determine the number of effects and operating pressure, and then construct a mechanism model including each distillation column in the multi-effect distillation system.

[0048] In practical applications, the tools for constructing the mechanism model (commercial process simulation software) can specifically be Aspen Plus, Aspen Hysys, ProⅡ, Petro-Sim, etc., which are software that can be used for process simulation in the petrochemical industry.

[0049] S12. Respectively construct the first correlation function between the reboiler heat load of each distillation column and its bottom product flow rate and purity, and respectively construct the second correlation function between the condenser heat load of each distillation column and the reboiler heat load of the next distillation column;

[0050] The first correlation function is used to correlate the reboiler heat load of each effect distillation column with its bottom product flow rate and purity. The first correlation function can be specifically as follows:

[0051]

[0052]

[0053] In Equations 1 and 2, where Q is the heat load, F is the feed flow rate, D is the top product flow rate; W is, X is the bottom product purity, S is the feed position of the distillation column; N is the total number of distillation columns, i is the serial number of the distillation column; f is the set of equations of the mechanism model of the distillation column; R is the reboiler; among them, f varies according to different actual application systems and is calculated by the mechanism model based on physical properties such as relative volatility.

[0054] The second correlation function is used to correlate the condenser heat load of each effect distillation column with the reboiler heat load of the next effect distillation column. The second correlation function can be specifically as follows:

[0055]

[0056]

[0057] In Equation 4, H is the heat balance set of equations of the distillation column; C is the condenser;

[0058] Through the first correlation function and the second correlation function, after a part of the process parameters in the embodiments of the present invention are mutually correlated, multiple other process parameters in the correlation function can be characterized by a small number of process parameters, thereby reducing the amount of calculation and the difficulty of solution in the subsequent calculation process.

[0059] The embodiments of the present invention reasonably simplify the coupling process of mass and heat in multi-effect distillation, greatly reduce the number of process parameters required for subsequent optimization calculation and the difficulty of solution, and the reboiler heat load of the highest-pressure distillation column as the optimization target can be solved by using a small number of process parameters.

[0060] S13. Set a preset number of data sets for the preset process parameters that are the independent variables of the mechanism model; use the reboiler heat load of the highest-pressure distillation column corresponding to the preset number obtained by calculating through the mechanism model with the data set as the input as the theoretical output.

[0061] Generate a data set of preset process parameters with a preset number; use the reboiler heat load of the highest-pressure distillation column corresponding to the preset number obtained by calculating through the mechanism model with the data set as the input as the theoretical output.

[0062] The mechanism model in the embodiments of the present invention can simulate the process of the multi-effect distillation system; by setting a data set of process parameters with a preset number to simulate the working conditions of the multi-effect distillation system, and then through the data set of process parameters with a preset number, the simulation values of the reboiler heat load of the highest-pressure distillation column corresponding to the corresponding number can be obtained through the mechanism model as the theoretical output of the multi-effect distillation system.

[0063] S14. Use the data set of the preset process parameters and the theoretical output as modeling data, and generate a prediction model capable of predicting the reboiler heat load of the highest-pressure distillation column according to the process parameters through deep learning.

[0064] Through step S13, a data set of preset process parameters with a preset number and a theoretical output can be obtained to simulate the process parameter data and the reboiler heat load data of the highest-pressure distillation column at multiple moments when the multi-effect distillation system actually works.

[0065] In this way, using the data set of the preset process parameters and the theoretical output as modeling data, a prediction model capable of predicting the reboiler heat load of the highest-pressure distillation column according to the process parameters can be generated through deep learning, and this prediction model corresponds to the multi-effect distillation system in the embodiments of the present invention.

[0066] In practical applications, the deep learning in the embodiments of the present invention can be implemented based on artificial neural networks such as BP neural networks and RBF neural networks.

[0067] S15. According to the first correlation function, the second correlation function, and specific process parameters, through the prediction model, obtain the predicted parameter values of each controllable process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved; the specific process parameters include: the number of effects of multi-effect distillation with a preset value, the operating pressure of the distillation column, and the bottom product composition index, and, taking the feed position of the distillation column and the light component extraction amount of the distillation column as controllable process parameters.

[0068] In the embodiment of the present invention, since the set correlation functions (including the first correlation function and the second correlation function) include multiple variables in the multi-effect distillation process, a large number of process parameters as dependent variables can be omitted during the calculation of the process; specifically, in the embodiment of the present invention, by using the first correlation function, the second correlation function, and the correlation equations of the related mechanism model, the heat loads of the condensers and reboilers of the upstream and downstream distillation columns can be correlated, thereby realizing the correlation between a small number of parameters and the energy consumption calculation results, and further greatly reducing the difficulty of subsequent optimization work.

[0069] For each individual distillation column, only two process parameters, namely the feed position and the top product flow rate, need to be regulated as controllable process parameters to solve the predicted parameter values when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved. Therefore, the solution difficulty is greatly reduced, the amount of calculation for solution is reduced, and the probability of not obtaining the optimal solution is effectively reduced.

[0070] In practical applications, the optimization algorithm in the embodiment of the present invention is a solution algorithm for solving multi-variable non-linear constraint optimization problems, and specifically may include one or more of algorithms such as sequential quadratic programming algorithm, simulated annealing algorithm, genetic algorithm, and particle swarm algorithm.

[0071] In summary, in the embodiment of the present invention, through the collaborative optimization of the mechanism model and deep learning, multi-variable optimization is performed on the multi-effect distillation process with strong coupling and many related factors, thus solving the problems in the prior art that the single-variable sensitivity analysis of the conventional sequential modular method has a large amount of calculation and it is difficult to find the optimal solution. In addition, in the embodiment of the present invention, two constructed correlation functions are also used to reduce the number of process parameters required for calculating the process, and only two controllable process parameters, namely the feed position and the top product flow rate, are left for each individual distillation column, thereby greatly reducing the difficulty of optimization and solution.

[0072] In addition, different from the data-driven modeling methods commonly used in the manufacturing industry in the prior art, in the embodiments of the present invention, the output of the modeling data in deep learning is calculated based on a mechanism model, and the modeling data used in deep learning can be reasonably distributed within a set variable range according to the experience of the user. Therefore, the optimization design method in the embodiments of the present invention has stronger extensibility, and the prediction accuracy of the prediction model generated therefrom is also higher.

[0073] Embodiment 2

[0074] Further, on the basis of Embodiment 1, in the embodiments of the present invention, the following steps may further be included:

[0075] S16: Taking the parameter values of each process parameter when the prediction model obtains the minimum energy consumption of the reboiler of the highest-pressure distillation column as input, calculating the reboiler heat load of the corresponding highest-pressure distillation column through the mechanism model as the reference output;

[0076] In order to verify whether the prediction accuracy of the prediction model meets the standard, in the embodiments of the present invention, the calculation result of the mechanism model may also be used as a reference to judge the prediction accuracy of the prediction model; for this purpose, referring to the independent variable input of the prediction model as the input of the mechanism model to generate a simulated value of the reboiler heat load of the highest-pressure distillation column as the reference output.

[0077] S17: When the absolute value of the difference between the prediction parameter value and the prediction parameter value is greater than a preset calculation tolerance, increasing the value of the preset number of groups and returning to step S13.

[0078] If the deviation between the prediction parameter value of the prediction model and the reference output is too large (greater than the preset calculation tolerance), it indicates that the accuracy of the prediction model is not enough. At this time, in order to appropriately increase the modeling data to improve the accuracy of the prediction model, the value of the preset number of groups can be increased and then returned to step S13 to generate more modeling data, so as to train a prediction model with higher prediction accuracy.

[0079] Embodiment 3

[0080] On the other hand of the embodiments of the present invention, an optimization device for a multi-effect distillation process flow is further provided. Figure 2 Showing a structural schematic diagram of the optimization device for the multi-effect distillation process flow provided by the embodiments of the present invention, the optimization device for the multi-effect distillation process flow is Figure 1 The device corresponding to the optimization method for the multi-effect distillation process flow in the corresponding embodiment, that is, realized in the form of a virtual device Figure 1The optimization method of the multi-effect distillation process flow in the corresponding embodiment, and each virtual module constituting the optimization device of the multi-effect distillation process flow can be executed by an electronic device, such as a network device, a terminal device, or a server. Specifically, the optimization device of the multi-effect distillation process flow in the embodiment of the present invention includes:

[0081] A mechanism model generation unit 01, configured to determine the feed state of the multi-effect distillation system according to the target separation task, and construct a mechanism model including each distillation column in the multi-effect distillation system by determining the number of effects of the multi-effect distillation and the operating pressure of each distillation column, with the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraints;

[0082] An association function construction unit 02, configured to respectively construct a first association function between the reboiler heat load of each distillation column and the bottom product flow rate and purity thereof, and a second association function between the condenser heat load of each distillation column and the reboiler heat load of the next distillation column;

[0083] A modeling data generation unit 03, configured to set a preset number of data sets for preset process parameters that are independent variables of the mechanism model; and use the reboiler heat load of the highest-pressure distillation column corresponding to the preset number of data sets calculated through the mechanism model as the theoretical output;

[0084] A prediction model generation unit 04, configured to use the data set of the preset process parameters and the theoretical output as modeling data, and generate a prediction model capable of predicting the reboiler heat load of the highest-pressure distillation column according to the process parameters through deep learning;

[0085] An optimization parameter calculation unit 05, configured to obtain the predicted parameter values of each controllable process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved according to the first association function, the second association function, and specific process parameters, through the prediction model; the specific process parameters include: the number of effects of the multi-effect distillation, the operating pressure of the distillation column, and the bottom product composition index whose values have been set, and the feed position of the distillation column and the light component extraction amount of the distillation column as controllable process parameters.

[0086] Preferably, in the present invention, it further includes:

[0087] A reference data generation unit (not shown in the figure), configured to use the parameter values of each process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved obtained by the prediction model as input, and calculate the corresponding reboiler heat load of the highest-pressure distillation column through the mechanism model as the reference output;

[0088] A prediction model optimization unit (not shown in the figure), when the absolute value of the difference between the predicted parameter value and the predicted parameter value is greater than a preset calculation tolerance, increases the value of the preset number of groups and returns to the modeling data generation unit.

[0089] Since the working principle and beneficial effects of the multi-effect distillation process optimization device in the embodiments of the present invention have been described and explained in Figure 1 the corresponding multi-effect distillation process optimization method, they can be referred to each other and will not be elaborated here.

[0090] Embodiment 4

[0091] Corresponding to the method embodiment, in the embodiments of the present invention, an optimization device for a multi-effect distillation process is also provided, such as a terminal, a server, etc. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto.

[0092] An example diagram of the hardware structure block diagram of the optimization device for the multi-effect distillation process provided in the embodiments of the present invention, as Figure 3 shown, may include:

[0093] Processor 1, communication interface 2, memory 3, and communication bus 4;

[0094] Among them, processor 1, communication interface 2, and memory 3 complete mutual communication through communication bus 4;

[0095] Optionally, communication interface 2 can be an interface of a communication module, such as an interface of a GSM module;

[0096] Processor 1 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0097] Memory 3 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

[0098] Among them, processor 1 is specifically configured to execute the computer program stored in memory 3 to perform the following steps:

[0099] S11. Determine the feed state of the multi-effect distillation system according to the target separation task. With the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraints, construct a mechanism model including each distillation column in the multi-effect distillation system by determining the number of effects of the multi-effect distillation and the operating pressure of each distillation column.

[0100] S12. Respectively construct a first correlation function between the reboiler heat load of each distillation column and its bottom product flow rate and purity, and respectively construct a second correlation function between the condenser heat load of each distillation column and the reboiler heat load of the next distillation column.

[0101] S13. Set a preset number of data sets for the preset process parameters that are the independent variables of the mechanism model; use the reboiler heat load of the highest-pressure distillation column corresponding to the preset number, which is calculated through the mechanism model with the data set as the input, as the theoretical output.

[0102] S14. Use the data set of the preset process parameters and the theoretical output as modeling data, and generate a prediction model through deep learning that can predict the reboiler heat load of the highest-pressure distillation column according to the process parameters.

[0103] S15. According to the first correlation function, the second correlation function and specific process parameters, obtain the predicted parameter values of each controllable process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved through the prediction model; the specific process parameters include: the number of effects of the multi-effect distillation, the operating pressure of the distillation column and the bottom product composition index whose values have been set, and the feed position of the distillation column and the light component extraction amount of the distillation column as the controllable process parameters. Preferably, in the present invention, it further includes:

[0104] S16. Use the parameter values of each process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved obtained through the prediction model as the input, and calculate the corresponding reboiler heat load of the highest-pressure distillation column through the mechanism model as the reference output.

[0105] S17. When the absolute value of the difference between the predicted parameter value and the predicted parameter value is greater than the preset calculation tolerance, increase the value of the preset number and return to step S13.

[0106] The above product can execute the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For the technical details not described in detail in this embodiment, reference can be made to the optimization method of the multi-effect distillation process flow provided by the embodiment of the present invention.

[0107] Example Five

[0108] In an embodiment of the present invention, a storage medium is further provided. The storage medium can store a program suitable for execution by a processor, and the program is used for:

[0109] S11. Determine the feed state of the multi-effect distillation system according to the target separation task. Taking the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraints, construct a mechanism model including each distillation column in the multi-effect distillation system by determining the number of effects of the multi-effect distillation and the operating pressure of each distillation column;

[0110] S12. Respectively construct a first correlation function between the reboiler heat load of each distillation column and its bottom product flow rate and purity, and respectively construct a second correlation function between the condenser heat load of each distillation column and the reboiler heat load of the next distillation column;

[0111] S13. Set a preset number of data sets for the preset process parameters that are the independent variables of the mechanism model; use the reboiler heat load of the highest-pressure distillation column corresponding to the preset number of data sets calculated through the mechanism model with the data sets as inputs as the theoretical output;

[0112] S14. Use the data sets of the preset process parameters and the theoretical output as modeling data, and generate a prediction model capable of predicting the reboiler heat load of the highest-pressure distillation column according to the process parameters through deep learning;

[0113] S15. According to the first correlation function, the second correlation function and specific process parameters, obtain the predicted parameter values of each controllable process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved through the prediction model; the specific process parameters include: the number of effects of the multi-effect distillation, the operating pressure of the distillation column and the bottom product composition index whose values have been set, and the feed position of the distillation column and the light component extraction amount of the distillation column as controllable process parameters.

[0114] Preferably, in the present invention, it further includes:

[0115] S16. Use the parameter values of each process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved obtained by the prediction model as inputs, and calculate the reboiler heat load of the corresponding highest-pressure distillation column through the mechanism model as the reference output;

[0116] S17. When the absolute value of the difference between the predicted parameter values is greater than the preset calculation tolerance, increase the value of the preset number of data sets and return to step S13.

[0117] Optionally, the refined functions and extended functions of the program can be referred to the above description.

[0118] The above-mentioned product can execute the method provided by the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference may be made to the methods provided in other embodiments of the present invention.

[0119] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0120] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in an electrical, mechanical, or other form.

[0121] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0122] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0123] It should be understood that in the embodiments of the present application, the dependent claims, each embodiment, and features can be combined with each other to achieve the solution of the foregoing technical problems.

[0124] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0125] The above description of the disclosed embodiments enables those skilled in the art to implement or use this application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application will not be limited to the embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. An optimization method for a multi-effect distillation process flow, characterized in that, it includes the steps: S11. Determine the feed state of the multi-effect distillation system according to the target separation task, and construct a mechanism model including each distillation column in the multi-effect distillation system by determining the number of effects of the multi-effect distillation and the operating pressure of each distillation column, with the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraints; S12. Respectively construct a first correlation function between the reboiler heat load of each distillation column and its bottom product flow rate and purity, and respectively construct a second correlation function between the condenser heat load of each distillation column and the reboiler heat load of its next distillation column; S13. Set a preset number of data sets for the preset process parameters that are the independent variables of the mechanism model; Take the reboiler heat load of the highest-pressure distillation column corresponding to the preset number of groups calculated through the mechanism model with the data set as the input as the theoretical output; S14. Use the data set of the preset process parameters and the theoretical output as modeling data, and generate a prediction model capable of predicting the reboiler heat load of the highest-pressure distillation column according to the process parameters through deep learning; S15. According to the first correlation function, the second correlation function and specific process parameters, obtain the predicted parameter values of each controllable process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved through the prediction model; The specific process parameters include: the number of effects of the multi-effect distillation, the operating pressure of the distillation column and the bottom product composition index with set values, and the feed position of the distillation column and the light component extraction amount of the distillation column as controllable process parameters.

2. The optimization method for the multi-effect distillation process flow according to claim 1, characterized in that, it further includes: S16. Take the parameter values of each process parameter when the minimum energy consumption of the reboiler of the highest-pressure distillation column is achieved obtained through the prediction model as the input, and calculate the corresponding reboiler heat load of the highest-pressure distillation column through the mechanism model as the reference output; S17. When the absolute value of the difference between the predicted parameter value and the predicted parameter value is greater than the preset calculation tolerance, increase the value of the preset number of groups and return to step S13.

3. The optimization method for the multi-effect distillation process flow according to claim 1 or 2, characterized in that, the first correlation function includes: where Q is the heat load, F is the feed flow rate, D is the top product flow rate; W is the bottom product flow rate, X is the bottom product purity, S is the feed position of the distillation column; N is the total number of distillation columns, i is the serial number of the distillation column; f is the system of equations of the mechanism model of the distillation column; R is the reboiler; the second correlation function includes: where H is the heat balance system of equations of the distillation column; C is the condenser.

4. The optimization method for the multi-effect distillation process flow according to claim 3, characterized in that, the feed state includes: the temperature, pressure, flow rate and composition of the feed; the relevant physical properties include: the boiling point, critical pressure, critical temperature, thermal decomposition temperature of each component, and the freezing point at a specific composition.

5. The optimization method for the multi-effect distillation process flow according to claim 4, characterized in that, The construction includes the mechanism models of the distillation columns in the multi-effect distillation system, including: The commercial process simulation software used includes one or more of Aspen Plus, Aspen Hysys, ProⅡ, and Petro-Sim.

6. The optimization method for the multi-effect distillation process flow according to claim 5, characterized in that, The deep learning is based on a BP neural network or an RBF neural network.

7. The optimization method for the multi-effect distillation process flow according to claim 5, characterized in that, The predicted parameter values of the controllable process parameters when obtaining the minimum energy consumption of the reboiler of the highest-pressure distillation column through the prediction model include: The algorithms used include one or more of the sequential quadratic programming algorithm, the simulated annealing algorithm, the genetic algorithm, and the particle swarm algorithm.

8. An optimization device for the multi-effect distillation process flow, characterized in that, including: A mechanism model generation unit, configured to determine the feed state of the multi-effect distillation system according to the target separation task, and construct a mechanism model including the distillation columns in the multi-effect distillation system by taking the relevant physical properties of each component in the separation system and the minimum heat transfer temperature difference of the system as constraints, and determining the number of effects of the multi-effect distillation and the operating pressures of each distillation column; A correlation function construction unit, configured to respectively construct a first correlation function between the reboiler heat load of each distillation column and its bottom product flow rate and purity, and a second correlation function between the condenser heat load of each distillation column and the reboiler heat load of the next distillation column; A modeling data generation unit, configured to set a preset number of data sets for the preset process parameters that are the independent variables of the mechanism model; Using the reboiler heat load of the highest-pressure distillation column corresponding to the preset number of data sets calculated through the mechanism model as the theoretical output; A prediction model generation unit, configured to use the data set of the preset process parameters and the theoretical output as modeling data, and generate a prediction model capable of predicting the reboiler heat load of the highest-pressure distillation column according to the process parameters through deep learning; An optimization parameter calculation unit, configured to obtain the predicted parameter values of the controllable process parameters when the reboiler of the highest-pressure distillation column has the minimum energy consumption through the prediction model according to the first correlation function, the second correlation function, and specific process parameters; The specific process parameters include: the number of effects of the multi-effect distillation, the operating pressure of the distillation column, and the bottom product composition index with set values, and the feed position of the distillation column and the light component extraction amount of the distillation column as the controllable process parameters.

9. The optimization device for the multi-effect distillation process flow according to claim 8, characterized in that, further including: A reference data generation unit, configured to use the parameter values of each process parameter when the reboiler of the highest-pressure distillation column has the minimum energy consumption obtained by the prediction model as input, and calculate the corresponding reboiler heat load of the highest-pressure distillation column through the mechanism model as the reference output; A prediction model optimization unit, when the absolute value of the difference between the predicted parameter value and the predicted parameter value is greater than the preset calculation tolerance, increase the value of the preset number of groups and return to the modeling data generation unit.

10. An optimization device for a multi-effect distillation process flow, characterized in that, comprising: a memory for storing a computer program; a processor for calling and executing the computer program to implement the steps of the optimization method for the multi-effect distillation process flow according to any one of claims 1-7.

11. A storage medium, characterized in that, including a software program adapted to be executed by a processor to implement the steps of the optimization method for the multi-effect distillation process flow according to any one of claims 1-7.

Images