A coal chemical whole-process optimization method, device, equipment and storage medium

Abstract

This invention provides a method, apparatus, equipment, and storage medium for optimizing the entire coal chemical process. It involves constructing a chemical production planning model based on the acquired production plan. This model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model. A nonlinear solver is used to solve each model in the chemical production planning model to obtain the overall process optimization results. Compared to current methods that use spreadsheets to create simplified models, the optimized production plan results are difficult to implement in practice at the process control level. This invention addresses the issue from the perspective of optimizing the benefits of the entire plant's production plan, considering the impact of different raw material compositions and properties on the overall process. This makes the optimized production plan results easily achievable in practice at the process control level, which is beneficial for enterprises to reduce costs and increase efficiency.

Description

Technical Field

[0001] This invention relates to the field of coal chemical technology, and in particular to a method, apparatus, equipment, and storage medium for optimizing the entire coal chemical process. Background Technology

[0002] Coal chemical industry is an important method of energy conversion and chemical production, and effective production planning is of great significance to the production and operation of enterprises. Coal chemical production planning can not only optimize the procurement of raw coal, inventory scheduling, and plant production, but also achieve the optimal allocation of upstream and downstream logistics within the enterprise, thereby maximizing the enterprise's production potential and significantly improving production economic efficiency.

[0003] However, due to the broad scope and long time span of enterprise production plans, it is difficult to achieve detailed modeling of the composition and properties of raw materials and the production process of equipment. Currently, the planning modeling method basically uses spreadsheets to create simplified models, which makes it difficult to implement the optimized production plan results in practice at the process control level. That is, the inconsistency between the optimized production plan and the actual production situation makes it impossible to coordinate production from top to bottom, which is not conducive to the enterprise's cost reduction and efficiency improvement. Summary of the Invention

[0004] This invention provides a method for optimizing the entire coal chemical process, which addresses the shortcomings of existing technologies where there is a significant discrepancy between production plan optimization and actual production conditions, thereby maximizing enterprise production potential and significantly improving production economic efficiency.

[0005] This invention provides a method for optimizing the entire coal chemical process, comprising the following steps: A chemical production planning model is built based on the obtained production plan; the chemical production planning model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model. The nonlinear solver is invoked to solve each model in the chemical production planning model, and the overall process optimization results are obtained.

[0006] Preferably, the coal chemical process optimization method provided by the present invention further includes: Establish a data-driven predictive model for gasification devices; Based on the composition ratio of different raw coals and process operating conditions, the product yield and utility consumption coefficient corresponding to each type of raw coal are calculated using a gasification unit prediction model.

[0007] Preferably, according to the coal chemical industry whole-process optimization method provided by the present invention, a chemical production planning model is built based on the obtained production plan, including: Establish multiple processing devices and determine at least one processing scheme for each processing device; A chemical production planning model is built based on raw coal information, raw material logistics information, processing plan information, and the obtained production plan. Among them, raw coal information includes the type of raw coal and its physical properties; processing plan information includes the product yield and utility consumption coefficient of the raw coal corresponding to the processing unit under the processing plan.

[0008] Preferably, according to the coal chemical industry whole-process optimization method provided by the present invention, a chemical production planning model is built based on the obtained production plan, including: Construct an objective function based on the cost of raw coal, the sales value of products, and the cost of equipment. Build a product demand constraint model based on the upper and lower limits of the product's market demand. A material balance constraint model is constructed based on the input of raw coal and the output of products. Build an inventory constraint model based on the upper and lower limits of material inventory; A constraint model for the processing device is built based on the reference values ​​of the processing device under a specified operating scheme.

[0009] Preferably, in the coal chemical process optimization method provided by the present invention, the processing unit constraint model includes: a unit yield model, a unit scheme constraint model, and a processing capacity constraint model. The processing unit constraint model is constructed based on reference values ​​of the processing unit under a specified operating scheme, including: A yield model for the processing unit is built based on the feed rate, material output, and yield of side-line products under a specified operating scheme. A constraint model for the device scheme is built based on the Boolean values ​​of the processing device's operation. A processing capacity constraint model is established based on the upper and lower limits of the processing capacity of the processing device under a specified operating scheme. This invention also provides a coal chemical process optimization device, comprising the following modules: The model building module is used to build a chemical production planning model based on the obtained production plan; the chemical production planning model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model. The solver module is used to call the nonlinear solver to solve each model in the chemical production planning model and obtain the overall process optimization results.

[0010] Preferably, the coal chemical process optimization device provided by the present invention further includes: The gasification unit prediction model building module is used to build a data-driven prediction model for gasification units. The prediction module is used to calculate, based on the composition ratio of different raw coals and process operating conditions, using a gasification unit prediction model to obtain the product yield and utility consumption coefficient for each type of raw coal. This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the coal chemical process optimization method described above.

[0011] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the coal chemical process optimization method as described above.

[0012] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements any of the aforementioned coal chemical process optimization methods. This invention provides a coal chemical process optimization method, apparatus, equipment, and storage medium that constructs a chemical production planning model based on an acquired production plan. This model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing equipment constraint model. A nonlinear solver is called to solve each model in the chemical production planning model to obtain the overall process optimization results. Compared to the current method of using spreadsheets to create simplified models, the optimization results of the production plan are difficult to implement in practice at the process control level. This invention addresses the issue from the perspective of optimizing the overall plant production plan, considering the impact of different raw material compositions and properties on the overall process. This makes the optimization results of the production plan easy to implement in practice at the process control level, which is beneficial for enterprises to reduce costs and increase efficiency. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0014] Figure 1 This is one of the flowcharts of the coal chemical industry whole-process optimization method provided by the present invention.

[0015] Figure 2 This is a schematic diagram of the structure of the coal chemical industry whole process optimization device provided by the present invention.

[0016] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0018] The following is combined Figures 1-3 This invention is described.

[0019] Figure 1 This is one of the flowcharts illustrating the coal chemical industry whole-process optimization method provided by the present invention, such as... Figure 1 As shown, the method includes the following: Step 102: Build a chemical production planning model based on the obtained production plan; the chemical production planning model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model.

[0020] In step 102 above, the chemical production planning model of this embodiment of the invention is optimized with the goal of maximizing the benefits of the entire plant; it sets quantity constraints on the quantities of raw materials, products, utilities, and inventory; it sets price constraints on the raw material procurement costs, product sales prices, and utilities consumption costs; it sets material balance constraints on the materials of the entire plant; it sets processing capacity constraints on the processing units; and it sets threshold constraints on the feeding of the units, so that the feeding of the units meets the design values ​​and index requirements of the unit design.

[0021] In addition to the basic constraints mentioned above, custom constraints can also be set according to actual production needs. By setting these constraints in the large model, the overall logistics structure can be analyzed, and the material balance of the entire plant can be verified. After the large model is validated, the chemical production planning model is obtained.

[0022] Refinery processing units can be broadly categorized into primary processing units and secondary processing units. The atmospheric (or vacuum) distillation unit in an oil refinery is a primary processing unit, while the units in a coal chemical plant are primarily secondary processing units. For ease of description, in this embodiment of the invention, "processing unit" refers to all units in a coal chemical plant. The processing units include gasification, purification, methanol synthesis, sulfur recovery, olefin catalytic cracking (OCC), methanol-to-olefins (MTO), MTBE, No. 1 polypropylene, No. 1 polyethylene, and No. 2 polyethylene units.

[0023] Optionally, step 102 above includes steps (1) to (5): Step (1): Construct an objective function based on the cost of raw coal, the sales value of the product, and the cost of the equipment.

[0024] Step (2): Build a product demand constraint model based on the upper and lower limits of the market demand for the product.

[0025] Step (3): Build a material balance constraint model based on the input of raw coal and the output of products.

[0026] Step (4): Build an inventory constraint model based on the upper and lower limits of material inventory.

[0027] Step (5): Build a constraint model of the processing device based on the reference values ​​of the processing device under the specified operation scheme.

[0028] In step (1) above, the objective function is constructed to maximize the overall plant benefits. The objective function is achieved through formula (1):

[0029] In the above formula (1), This represents the sales volume of material c. Represents the collection of all products. This represents the selling price of product c. This indicates the quantity of material c purchased. This represents the collection of all raw materials. This represents the purchase price of raw material c. The processing volume of device u under production scheme m, where C is the unit processing cost of the device. This represents the set of operating schemes for a certain device. G represents the fixed cost.

[0030] In step (2) above, the product demand constraint model is implemented through formula (2):

[0031] In the above formula (2), This indicates the upper limit of market demand for product C. This indicates the lower limit of market demand for product C; This represents the sales volume of product C. This represents the collection of all products.

[0032] In step (3) above, the material balance constraint model is implemented through formula (3):

[0033] In the above formula (3), This indicates the amount of material c input to device u under operating scheme m. This indicates the input and output of material c in device u under operating scheme m; This represents the collection of materials fed into device u under operating scheme m; UBL represents the set of materials produced by device u under operating scheme m, and UBL represents the set of all devices. This represents the set of operation schemes for a certain device.

[0034] In step (4) above, the inventory constraint model is implemented through formula (4):

[0035] In the above formula (4), This represents the inventory value of material c; This indicates the maximum inventory level for material C. This indicates the lower limit of the inventory level for material C; This represents the collection of all inventory materials.

[0036] In step (5) above, specifying an operation plan refers to a processing plan of the processing device. For a processing device, there may be at least one processing plan. Different processing plans correspond to different working conditions and operating conditions, and also have different product yield data.

[0037] The reference values ​​for the processing equipment under the specified operating scheme include: relevant material values, product yield data of the processing equipment under the specified operating scheme, and processing capacity of the processing equipment.

[0038] Optionally, the processing device constraint model includes: device yield model, device scheme constraint model, and processing capacity constraint model, and the above step (5) includes steps (51) to (53): Step (51): Build a device yield model based on the feed rate, material output and yield of side-line products of the processing device under the specified operating scheme.

[0039] Step (52): Build a device scheme constraint model based on the operation Boolean value of the processing device.

[0040] Step (53): Build a processing capacity constraint model based on the upper and lower limits of the processing capacity of the processing device under the specified operation scheme.

[0041] In step (51) above, the yield model of the apparatus is realized by formula (5):

[0042] In the above formula (5), c represents the material of the device, m represents the processing scheme of the processing device, and u represents the type of processing device; This represents the output of material c of processing device u under operating scheme m. This indicates the yield of the side-line product c of the processing unit u under operating scheme m. This represents the total feed amount of the processing device u under the operating scheme.

[0043] In step (52) above, the yield model of the apparatus is realized by formula (6):

[0044] In the above formula (6), MAT represents the set of operation schemes; It is a Boolean variable indicating whether the processing device u adopts the operation scheme m. It is 1 if it is in operation and 0 if it is not in operation.

[0045] In step (53) above, the feed rate of the device needs to meet the processing capacity limit. The processing capacity constraint model is achieved through formula (7):

[0046] In the above formula (7), This indicates the lower limit of the processing capacity of processing device u under operating scheme m. This indicates the upper limit of the processing capacity of the processing device u under the operation scheme m.

[0047] Optionally, the coal chemical process optimization method also includes steps 100 to 101: Step 100: Establish a data-driven prediction model for the gasification device.

[0048] Step 101: Based on the composition ratio of different raw coals and process operating conditions, calculate the product yield and utility consumption coefficient corresponding to each type of raw coal using the gasification unit prediction model.

[0049] In step 100 above, this embodiment of the invention establishes a gasification device prediction model based on a long short-term memory network using actual operating data of the processing device. The input variables of the gasification device prediction model are the data of the feed entering the processing device, including the physical properties of the raw coal, the quantity of raw coal, the gasifier temperature, and the operating pressure. The output variables of the gasification device prediction model refer to the data of the products produced after processing by the processing device, including oxygen yield, moisture yield, coal gasification syngas yield, ammonia yield, ash and slag yield, waste coal slurry yield, and utility consumption coefficient. A gasification device prediction model is established using commercial software to simulate the production process, obtaining a large amount of output data. The output data is used as the validation set of the dataset, on which the gasification device prediction model is corrected and optimized. During the production process, the feed and discharge materials are balanced. That is, the feed and discharge material inputs and outputs are both 1. The gasification device prediction model describes the product yield corresponding to 1 unit of feed.

[0050] For example, consider the processing scheme of a reforming unit. The input to the reforming unit is the reforming feed, which is 1. The output of the reforming unit is reformed hydrogen, reformed gas, reformed liquefied petroleum gas (LPG), reformed gasoline, and losses. Reformed hydrogen yield + reformed gas yield + reformed LPG yield + reformed gasoline yield + loss yield = 1. The trained prediction model for the gasification unit can quickly predict the corresponding product yields and utility consumption data for different raw coal feedstocks, providing a guarantee for subsequent process control and overall optimization.

[0051] The physical properties data of the raw coal include: volatile matter, ash content, total sulfur content, fixed carbon, and lower calorific value. These data are transferred to subsequent processing units along the material flow path and are used in calculations affecting the final properties of the product.

[0052] As the fundamental source of the process, raw coal directly influences the operating rates of various processing units and the selection of processing routes. Data-driven gasification unit forecasting models can dynamically respond to market changes. By meticulously classifying raw coal and establishing its processing schemes, the construction of chemical production planning models can be further improved, enabling the rational optimization of raw coal procurement, inventory scheduling, and processing unit production scheduling. Simultaneously, it can achieve optimal allocation of upstream and downstream logistics within the enterprise, thereby maximizing the enterprise's production potential and significantly improving economic efficiency.

[0053] Optionally, based on steps 100 to 101 above, step 102 includes steps A to B: Step A: Establish multiple processing devices and determine at least one processing scheme for each processing device.

[0054] Step B: Construct a chemical production planning model based on raw coal information, raw material logistics information, processing plan information, and the obtained production plan; among which, raw coal information includes the type of raw coal and its physical properties; processing plan information includes the product yield and utility consumption coefficient of the raw coal corresponding to the processing unit under the processing plan.

[0055] In step A above, the processing scheme describes the side-line yield of each product during the corresponding feed production. During the model optimization calculation process, one or more schemes will be selected to start simultaneously.

[0056] The raw coal information also includes the types of raw materials procured besides raw coal. The raw material logistics information includes the usage and destination of the raw materials.

[0057] The types of raw coal include: lignite, bituminous coal, and anthracite.

[0058] The chemical production planning model also includes a utility model. The utility model calculates the amount of auxiliary materials, water, electricity, and ventilation resources consumed by each processing scheme in the processing unit in order to account for the utility costs of each processing scheme.

[0059] Step 104: Call the nonlinear solver to solve each model in the chemical production planning model to obtain the overall process optimization results. In step 104 above, a suitable nonlinear solver is selected based on the complexity of the problem and programming habits. In this embodiment of the invention, the CPLEX solver is selected to solve each model in the chemical production planning model. The solution process includes steps (1) to (4): Step (1): Define the problem to be solved. The problem to be solved can be represented by a system of nonlinear equations.

[0060] Step (2): Configure the solution parameters. The solution parameters include: tolerance and maximum number of iterations.

[0061] Step (3): Run the solver and analyze the results. Run the solver and check if it converges. If it converges, analyze the results to obtain the required process parameters.

[0062] Step (4): Verification and optimization. Verify whether the solution results conform to physical and chemical principles. If the results are unreasonable, it may be necessary to adjust the model, initial guesses, or solution parameters.

[0063] For the sake of completeness, this embodiment of the invention provides a basic introduction to the CPLEX solver. The CPLEX solver is a commercial optimization engine developed by IBM, specifically designed for solving large-scale linear programming, integer programming, mixed integer programming, and quadratic programming problems.

[0064] The CPLEX solver can solve a variety of complex mathematical programming problems, such as linear programming (LP), integer programming (IP), and mixed integer programming (MIP).

[0065] The CPLEX solver is known for its fast solution speed and powerful superlinear acceleration capabilities, making it particularly suitable for efficient handling of large-scale problems.

[0066] After installation, the CPLEX solver may require its path to be added to the system environment variables for use in MATLAB or other programming environments.

[0067] The programming languages ​​supported by the CPLEX solver include: Java Integration: For Java developers, CPLEX provides a rich API interface, allowing model building and solving via code. This includes steps such as defining variables, setting objective functions, adding constraints, and solving the model.

[0068] Python Integration: CPLEX also supports the Python language. Users can install the docplex library to build and solve optimization models using Python. This allows Python developers to easily leverage the powerful features of CPLEX.

[0069] For ease of understanding, the following examples are provided in the embodiments of the present invention.

[0070] Assuming that lignite, bituminous coal, and anthracite are currently available on the market, and that appropriate gasification processes and gasifying agents are used in a gasifier to produce combustible gases with different component contents, the corresponding feed and yield relationships are shown in the table below:

[0071] Taking lignite processing as an example, the unit yield model is as follows:

[0072]

[0073]

[0074]

[0075]

[0076] The material balance constraint model is as follows: = + + + = + + +

[0077] Set the feed, target values, upper and lower bound quantity constraints, purchase price, sales price, and utility consumption of the processing scheme for the entire plant. Combine different processing schemes in the overall plant production planning model, and then call the nonlinear solver to solve the coal chemical plant model to obtain the best efficiency in the plant, as well as the raw material selection results and the optimal start-up route.

[0078] This invention provides a method for optimizing the entire coal chemical process. It involves constructing a chemical production planning model based on the obtained production plan. This model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model. A nonlinear solver is used to solve each model in the chemical production planning model to obtain the overall process optimization results. Compared to the current method of using spreadsheets to create simplified models, the optimized production plan results are difficult to implement in practice at the process control level. This invention addresses the issue from the perspective of optimizing the overall plant production plan's benefits, considering the impact of different raw material compositions and properties on the overall process, providing comprehensive guidance for the optimal selection of raw coal. The optimized production plan is largely consistent with actual production conditions, making the optimized results easily implementable at the process control level, which is beneficial for cost reduction and efficiency improvement for enterprises.

[0079] The coal chemical process optimization device provided by the present invention is described below. The coal chemical process optimization device described below and the coal chemical process optimization method described above can be referred to in correspondence.

[0080] Figure 2 This is a schematic diagram of the structure of the coal chemical industry whole-process optimization device provided by the present invention, as shown below. Figure 2 As shown, the device includes the following: The model building module 200 is used to build a chemical production planning model based on the obtained production plan; wherein, the chemical production planning model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing equipment constraint model.

[0081] The solver module 202 is used to call the nonlinear solver to solve each model in the chemical production planning model and obtain the overall process optimization results.

[0082] Optionally, the coal chemical process optimization unit also includes: The gasification unit prediction model building module is used to build a data-driven prediction model for gasification units.

[0083] The prediction module is used to calculate, based on the composition ratio of different raw coals and process operating conditions, the product yield and utility consumption coefficient corresponding to each type of raw coal through the prediction model of the gasification device.

[0084] Optionally, the model building module 200 includes: The processing scheme determination submodule is used to establish multiple processing devices and determine at least one processing scheme for each processing device. The chemical production planning model building submodule is used to build a chemical production planning model based on raw coal information, raw material logistics information, processing scheme information, and the obtained production plan. Among them, raw coal information includes the type of raw coal and its physical properties; processing scheme information includes the product yield and utility consumption coefficient of the raw coal corresponding to the processing unit under the processing scheme.

[0085] Optionally, the model building module 200 includes: The objective function construction submodule is used to construct the objective function based on the cost of raw coal, the sales value of the product, and the cost of the equipment. The demand constraint model building submodule is used to build a product demand constraint model based on the upper and lower limits of the product's market demand. The Material Balance Constraint Model submodule is used to build a material balance constraint model based on the input of raw coal and the output of products. The inventory constraint model submodule is used to build an inventory constraint model based on the upper and lower limits of material inventory. The machining device constraint model submodule is used to build a machining device constraint model based on the reference values ​​of the machining device under a specified operating scheme.

[0086] Optionally, the processing equipment constraint model includes: an equipment yield model, an equipment scheme constraint model, and a processing capacity constraint model. The processing equipment constraint model sub-module includes: The unit yield model building submodule is used to build a unit yield model based on the feed rate, material output, and yield of side-line products of the processing unit under a specified operating scheme. The device scheme constraint model building submodule is used to build the device scheme constraint model based on the Boolean values ​​of the processing device's operation. The processing capacity constraint model building submodule is used to build a processing capacity constraint model based on the upper and lower limits of the processing capacity of the processing device under a specified operating scheme.

[0087] This invention provides a coal chemical process optimization device. It constructs a chemical production planning model based on the acquired production plan. This model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model. A nonlinear solver is used to solve each model in the chemical production planning model to obtain the overall process optimization results. Compared to the current simplified model built using spreadsheets, the optimized production plan results are difficult to implement in practice at the process control level. This invention addresses the issue from the perspective of optimizing the overall plant production plan's benefits, considering the impact of different raw material compositions and properties on the overall process, providing a comprehensive guidance for the optimal selection of raw coal. The optimized production plan is largely consistent with actual production conditions, making the optimized results easily implementable at the process control level, which is beneficial for cost reduction and efficiency improvement for enterprises.

[0088] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 810, a communications interface 820, a memory 830, and a communication bus 840. The processor 810, communications interface 820, and memory 830 communicate with each other via the communication bus 840. The processor 810 can call logical instructions from the memory 830 to execute a coal chemical process optimization method.

[0089] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0090] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the coal chemical industry whole-process optimization method provided by the above methods.

[0091] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the coal chemical process optimization method provided by the above methods.

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing the entire coal chemical process, characterized in that, include: A chemical production planning model is constructed based on the obtained production plan; wherein, the chemical production planning model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing unit constraint model; The nonlinear solver is invoked to solve each model in the chemical production planning model to obtain the overall process optimization results.

2. The coal chemical industry whole-process optimization method according to claim 1, characterized in that, Also includes: Establish a data-driven predictive model for gasification devices; Based on the composition ratio of different raw coals and process operating conditions, the product yield and utility consumption coefficient corresponding to each type of raw coal are calculated using the prediction model of the gasification unit.

3. The method for optimizing the entire coal chemical process according to claim 2, characterized in that, The step of building a chemical production planning model based on the obtained production plan includes: Establish multiple processing devices and determine at least one processing scheme for each processing device; A chemical production planning model is constructed based on raw coal information, raw material logistics information, processing scheme information, and the obtained production plan. The raw coal information includes the type of raw coal and its physical properties. The processing scheme information includes the product yield and utility consumption coefficient of the raw coal corresponding to the processing unit under the processing scheme.

4. The coal chemical industry whole-process optimization method according to claim 1, characterized in that, The step of building a chemical production planning model based on the obtained production plan includes: The objective function is constructed based on the cost of raw coal, the sales value of the product, and the cost of the equipment. The product demand constraint model is constructed based on the upper and lower limits of the product's market demand. The material balance constraint model is constructed based on the input of raw coal and the output of products. The inventory constraint model is constructed based on the upper and lower limits of material inventory. The constraint model of the processing device is built based on the reference values ​​of the processing device under the specified operating scheme.

5. The coal chemical industry whole-process optimization method according to claim 4, characterized in that, The processing device constraint model includes: a device yield model, a device scheme constraint model, and a processing capacity constraint model. The step of constructing the processing device constraint model based on reference values ​​of the processing device under a specified operating scheme includes: The yield model of the processing device is constructed based on the feed rate, material output, and yield of side-line products under the specified operating scheme. The constraint model of the device scheme is constructed based on the Boolean values ​​of the processing device's operation. The processing capacity constraint model is constructed based on the upper and lower limits of the processing capacity of the processing device under the specified operating scheme.

6. A coal chemical process optimization device, characterized in that, include: The model building module is used to build a chemical production planning model based on the obtained production plan; wherein, the chemical production planning model includes an objective function, a product demand constraint model, a material balance constraint model, an inventory constraint model, and a processing equipment constraint model; The solver module is used to call the nonlinear solver to solve each model in the chemical production planning model and obtain the overall process optimization results.

7. The coal chemical process optimization device according to claim 6, characterized in that, Also includes: The gasification unit prediction model building module is used to build a data-driven prediction model for gasification units. The prediction module is used to calculate, based on the composition ratio of different raw coals and process operating conditions, the product yield and utility consumption coefficient corresponding to each type of raw coal through the prediction model of the gasification device.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the coal chemical industry whole process optimization method as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the coal chemical industry whole process optimization method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the coal chemical industry whole process optimization method as described in any one of claims 1 to 6.

Images