An energy consumption optimization system for polyester fiber production process
The energy consumption optimization system for polyester fiber production balances energy reduction with spinning quality and efficiency by associating control features and performing multi-feature optimization, addressing the neglect of stability in existing technologies.
Patent Information
- Application Number
- CN202411443609.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2024-12-20
- Estimated Expiration
- 2044-10-16
AI Technical Summary
Existing energy consumption optimization strategies in polyester fiber production, particularly for highly flame-retardant microfiber yarns, focus excessively on reducing energy consumption, neglecting stability and consistency, leading to production fluctuations and reduced spinning quality.
An energy consumption optimization system that associates control features of melt spinning equipment with fiber spinning raw materials and requirements, performs multi-feature expectation coupling optimization, and uses a spinning control energy consumption optimization module to balance energy reduction with spinning quality and efficiency.
Achieves a coordinated optimization of energy consumption and spinning quality, ensuring stable and efficient polyester fiber production by minimizing energy consumption while maintaining spinning efficiency and quality.
Smart Images
Figure CN118966475B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of fiber preparation, and in particular to an energy consumption optimization system for a polyester fiber production process. Background Art
[0002] In the production process of polyester fibers, especially in the production of highly flame-retardant polyester microfiber yarns, the melt spinning node is the main source of energy consumption. In order to respond to the call for energy conservation and emission reduction, the existing technology mainly focuses on directly reducing energy consumption by adjusting process parameters or introducing energy-saving equipment. Although the existing technology has reduced energy consumption to a certain extent, this single energy consumption optimization strategy often ignores other equally important factors in the production process, resulting in large production fluctuations and increased production risks. For example, when excessive pursuit of energy consumption reduction will sacrifice the stability and consistency of spinning quality, such as the decline of fiber breaking strength, linear density and other indicators.
[0003] Among the current related technologies, the energy consumption optimization used in the polyester fiber production process has the technical problem of excessive pursuit of energy consumption reduction and neglect of stability control in the production process, resulting in poor overall production performance. Summary of the invention
[0004] The present application provides an energy consumption optimization system for the polyester fiber production process, which adopts technical means such as obtaining fiber production spinning tasks, associating control characteristics of melt spinning equipment according to fiber spinning raw materials and fiber spinning requirements, establishing a spinning control characteristic association space, making control parameter decisions for the melt spinning equipment according to the spinning control characteristic association space, obtaining a spinning control decision space, performing multi-feature expectation coupling optimization on the spinning control decision space according to fiber spinning expectations, obtaining a spinning control expectation optimization space, performing multi-dimensional energy consumption optimization on the spinning control expectation optimization space according to a spinning energy consumption fitness function, obtaining a spinning control optimization result, and performing spinning based on the spinning control optimization result, thereby achieving a balance between energy consumption reduction and spinning quality and spinning efficiency. Under the premise of ensuring spinning quality and spinning efficiency, energy consumption is effectively reduced, and the coordinated optimization of energy consumption and other key factors is achieved to ensure the technical effect of improving the overall performance of the polyester fiber production process.
[0005] The present application provides an energy consumption optimization system for a polyester fiber production process, comprising:
[0006] A spinning task acquisition module, the spinning task acquisition module is used to obtain a fiber production spinning task, wherein the fiber production spinning task includes fiber spinning raw materials, fiber spinning requirements and fiber spinning expectations; a spinning control feature association module, the spinning control feature association module is used to associate control features of a melt spinning device according to the fiber spinning raw materials and the fiber spinning requirements, and establish a spinning control feature association space; a spinning control decision module, the spinning control decision module is used to control the melt spinning device based on the fiber spinning raw materials and the fiber spinning requirements according to the spinning control feature association space The invention relates to a spinning control parameter decision-making module, wherein the spinning control expectation optimization module is used to perform multi-feature expectation coupling optimization on the spinning control decision space according to the fiber spinning expectation, and obtain the spinning control expectation optimization space; a spinning control energy consumption optimization module, wherein the spinning control energy consumption optimization module is used to perform multi-dimensional energy consumption optimization on the spinning control expectation optimization space according to the spinning energy consumption fitness function, and obtain the spinning control optimization result; a spinning module, wherein the spinning module is used to perform spinning according to the melt spinning equipment based on the spinning control optimization result and the fiber spinning raw material.
[0007] In a possible implementation, the spinning control feature association module is used to associate control features of the melt spinning equipment according to the fiber spinning raw material and the fiber spinning demand, establish a spinning control feature association space, and perform the following processing:
[0008] Collect basic information of the fiber spinning raw materials to obtain spinning raw material information; perform spinning record retrieval based on the melt spinning equipment to obtain multiple spinning control record groups; perform control feature alignment on the multiple spinning control record groups based on the spinning raw material information and the fiber spinning requirements to obtain an aligned spinning control scheme set; perform trigger feature identification for each control dimension based on the aligned spinning control scheme set to obtain multiple spinning control trigger intervals; organize the multiple spinning control trigger intervals to generate the spinning control feature association space.
[0009] In a possible implementation, control feature registration is performed on the plurality of spinning control record groups based on the spinning raw material information and the fiber spinning requirements to obtain a registered spinning control scheme set, and the following processing is performed:
[0010] Traverse the multiple spinning control record groups and extract the first spinning control record group, wherein the first spinning control record group includes the first historical spinning raw material information, the first historical fiber spinning demand and the first historical spinning control scheme; based on the spinning raw material information, perform an association evaluation on the first historical spinning raw material information to obtain a first spinning raw material association coefficient; based on the fiber spinning demand, perform an association evaluation on the first historical fiber spinning demand to obtain a first spinning demand association coefficient; based on the spinning association evaluation weight, perform a weighted calculation on the first spinning raw material association coefficient and the first spinning demand association coefficient to obtain a first spinning control registration coefficient; determine whether the first spinning control registration coefficient meets the spinning control registration constraint; if the first spinning control registration coefficient meets the spinning control registration constraint, record the first historical spinning control scheme as the first registered spinning control scheme, and add the first registered spinning control scheme to the registered spinning control scheme set.
[0011] In a possible implementation, the spinning control decision module is used to make a control parameter decision for the melt spinning equipment based on the fiber spinning raw material and the fiber spinning demand according to the spinning control feature association space, obtain a spinning control decision space, and perform the following processing:
[0012] According to the spinning control feature association space, control parameters of the melt spinning equipment are set to obtain a spinning control scheme space; the spinning control scheme space is traversed to extract a first spinning control scheme; based on the fiber spinning raw material, the melt spinning equipment is simulated and controlled according to the first spinning control scheme to obtain a first simulated spinning result; it is determined whether the first simulated spinning result meets the fiber spinning requirement; if the first simulated spinning result meets the fiber spinning requirement, the first spinning control scheme is set to be a first spinning control decision, and the first spinning control decision is added to the spinning control decision space; if the first simulated spinning result does not meet the fiber spinning requirement, the first spinning control scheme is eliminated.
[0013] In a possible implementation, the spinning control expectation optimization module is used to perform multi-feature expectation coupling optimization on the spinning control decision space according to the fiber spinning expectation, obtain the spinning control expectation optimization space, and perform the following processing:
[0014] The fiber spinning expectations include an expected spinning energy consumption coefficient, an expected spinning quality coefficient and an expected spinning efficiency coefficient; based on the expected spinning energy consumption coefficient, the spinning control decision space is optimized for spinning energy consumption to obtain a first spinning control expected optimization domain; based on the expected spinning quality coefficient, the spinning control decision space is optimized for spinning quality to obtain a second spinning control expected optimization domain; based on the expected spinning efficiency coefficient, the spinning control decision space is optimized for spinning efficiency to obtain a third spinning control expected optimization domain; coupling identification is performed based on the first spinning control expected optimization domain, the second spinning control expected optimization domain and the third spinning control expected optimization domain to generate the spinning control expected optimization space.
[0015] In a possible implementation, the spinning control decision space is optimized for spinning energy consumption based on the expected spinning energy consumption coefficient to obtain a first spinning control expected optimization domain, and the following processing is performed:
[0016] According to the spinning control decision space, extract the mth spinning control decision, wherein m is a positive integer; based on the fiber spinning raw material, perform energy consumption prediction on the melt spinning equipment according to the mth spinning control decision to obtain the mth predicted spinning energy consumption coefficient; determine whether the mth predicted spinning energy consumption coefficient is less than / equal to the expected spinning energy consumption coefficient; if the mth predicted spinning energy consumption coefficient is less than / equal to the expected spinning energy consumption coefficient, add the mth spinning control decision to the first spinning control expected optimization domain.
[0017] In a possible implementation, the spinning control energy consumption optimization module is used to perform multi-dimensional energy consumption optimization on the spinning control desired optimization space according to the spinning energy consumption fitness function, obtain a spinning control optimization result, and perform the following processing:
[0018] Based on the spinning energy consumption fitness function, the fitness of the spinning control expected optimization space is calculated to obtain multiple spinning energy consumption fitnesses; based on the spinning energy consumption fitness constraint, the spinning control expected optimization space is screened for energy consumption fitness according to the multiple spinning energy consumption fitnesses to obtain a spinning control optimization strategy space; based on the spinning control optimization strategy space, spinning energy consumption minimization is optimized to generate the spinning control optimization result.
[0019] In a possible implementation, the following processing is performed:
[0020] The spinning energy consumption fitness function includes:
[0021] ;
[0022] Among them, SEF represents the fitness of spinning energy consumption, exp represents the exponential function with the natural constant e as the base, EAW, EBW and ECW represent the predetermined fitness calculation weights, SEA represents the predicted spinning quality coefficient, EAO represents the expected spinning quality coefficient, SEB represents the predicted spinning efficiency coefficient, EBO represents the expected spinning efficiency coefficient, SEC represents the predicted spinning energy consumption coefficient, and ECO represents the expected spinning energy consumption coefficient.
[0023] An energy consumption optimization system for a polyester fiber production process proposed in the present application is proposed. A fiber production spinning task is obtained through a spinning task acquisition module, wherein the fiber production spinning task includes fiber spinning raw materials, fiber spinning requirements and fiber spinning expectations. A spinning control feature association module is used to associate control features of a melt spinning device according to the fiber spinning raw materials and the fiber spinning requirements, and a spinning control feature association space is established. A spinning control decision module is used to make a control parameter decision on the melt spinning device according to the spinning control feature association space based on the fiber spinning raw materials and the fiber spinning requirements, and a spinning control decision is obtained. The spinning control decision space is optimized through the spinning control expectation optimization module according to the fiber spinning expectations, and the spinning control expectation optimization space is obtained. The spinning control energy consumption optimization module performs multi-dimensional energy consumption optimization on the spinning control expectation optimization space according to the spinning energy consumption fitness function to obtain the spinning control optimization result. The spinning module is based on the spinning control optimization result and the fiber spinning raw materials. Spinning is carried out according to the melt spinning equipment, thereby achieving the coordinated optimization of energy consumption and other key factors to ensure the technical effect of improving the overall performance of the polyester fiber production process. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.
[0025] Figure 1 A schematic diagram of the structure of an energy consumption optimization system for a polyester fiber production process provided in an embodiment of the present application.
[0026] Figure 2 A schematic diagram of a flow chart for establishing a spinning control feature association space in an energy consumption optimization system for a polyester fiber production process provided in an embodiment of the present application.
[0027] Explanation of the reference numerals: spinning task acquisition module 10 , spinning control feature association module 20 , spinning control decision module 30 , spinning control expectation optimization module 40 , spinning control energy consumption optimization module 50 , spinning module 60 . DETAILED DESCRIPTION
[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.
[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.
[0030] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.
[0031] The present application embodiment provides an energy consumption optimization system for a polyester fiber production process, such as Figure 1 As shown, the system comprises:
[0032] The spinning task acquisition module 10 is used to obtain the fiber production spinning task, wherein the fiber production spinning task includes fiber spinning raw materials, fiber spinning requirements and fiber spinning expectations. Specifically, the spinning task acquisition module 10 receives the fiber production spinning task from the production plan or user interface, including fiber spinning raw materials, fiber spinning requirements and fiber spinning expectations. Among them, fiber spinning raw materials refer to raw materials used for spinning, such as polyester chips, etc.; fiber spinning requirements refer to specific requirements for spinning products, such as fiber diameter, strength, elongation, etc.; fiber spinning expectations refer to expected goals for the spinning process and results, such as energy consumption, quality and efficiency, etc.
[0033] The spinning control feature association module 20 is used to associate the control features of the melt spinning equipment according to the fiber spinning raw materials and the fiber spinning requirements, and establish a spinning control feature association space. Specifically, the spinning control feature association module 20 obtains the basic information of the raw materials used in the current spinning task, and retrieves the spinning control records (control parameters and results recorded in the historical spinning process) similar to the current raw materials and requirements from the historical database. According to the raw material information and requirements, the retrieved records are aligned to screen out similar control schemes. Identify the trigger features of each control dimension, that is, the key factors that need to be considered when adjusting the control parameters, such as temperature, pressure, etc., determine the adjustment range of the control parameters, and form a spinning control feature association space.
[0034] like Figure 2 As shown, in a possible implementation, the control features of the melt spinning equipment are associated according to the fiber spinning raw materials and the fiber spinning requirements to establish a spinning control feature association space, including: collecting basic information of the fiber spinning raw materials to obtain spinning raw material information; retrieving spinning records based on the melt spinning equipment to obtain multiple spinning control record groups; performing control feature alignment on the multiple spinning control record groups based on the spinning raw material information and the fiber spinning requirements to obtain an aligned spinning control scheme set; identifying trigger features of each control dimension based on the aligned spinning control scheme set to obtain multiple spinning control trigger intervals; and sorting the multiple spinning control trigger intervals to generate the spinning control feature association space.
[0035] Specifically, the detailed basic information of the fiber spinning raw materials (such as polyester chips) used in the current spinning task, such as composition, melting point, viscosity, etc., is collected through sensors, manual input or database query. Using the database management system, similar spinning process records are retrieved in the historical spinning records according to the spinning raw material information and spinning requirements (such as fiber diameter, strength, etc.). These records contain the control parameters (such as temperature, pressure, speed, etc.) and results (such as fiber quality, energy consumption, etc.) used in the previous spinning process. The retrieved multiple spinning control record groups are matched with the raw material information and requirements of the current spinning task, and the similarity between each spinning control record group and the current task is evaluated by the similarity algorithm. The most relevant spinning control record group is selected to form a registered spinning control scheme set. The registered spinning control scheme set is a collection of successfully matched control parameter combinations. Each control parameter in the registered spinning control scheme set is deeply analyzed to identify the sensitive range or trigger point of each control parameter under different spinning stages or conditions, that is, which parameter changes will significantly affect the spinning results. The trigger feature refers to the feature point or interval that triggers a significant change in the spinning result when the control parameter reaches a certain value during the spinning process, and the spinning control trigger interval is a collection of these feature points or intervals. Multiple spinning control trigger intervals are sorted to form a multi-dimensional control feature association space, namely the spinning control feature association space. This space associates the trigger features of each control parameter according to the spinning raw material information and spinning requirements, and describes how each control parameter should be adjusted under different spinning conditions to achieve the best spinning effect. This implementation method avoids the process of exploring control parameters from scratch by quickly retrieving and matching historical records, and provides accurate control parameter recommendations for the current spinning task.
[0036] In a possible implementation, the control features of the multiple spinning control record groups are aligned based on the spinning raw material information and the fiber spinning demand to obtain an aligned spinning control scheme set, including: traversing the multiple spinning control record groups to extract a first spinning control record group, wherein the first spinning control record group includes first historical spinning raw material information, first historical fiber spinning demand and first historical spinning control scheme; based on the spinning raw material information, performing correlation evaluation on the first historical spinning raw material information to obtain a first spinning raw material correlation coefficient; based on the fiber spinning demand, Perform correlation evaluation on the first historical fiber spinning demand to obtain a first spinning demand correlation coefficient; based on the spinning correlation evaluation weight, perform weighted calculation on the first spinning raw material correlation coefficient and the first spinning demand correlation coefficient to obtain a first spinning control alignment coefficient; determine whether the first spinning control alignment coefficient meets the spinning control alignment constraint; if the first spinning control alignment coefficient meets the spinning control alignment constraint, record the first historical spinning control scheme as a first aligned spinning control scheme, and add the first aligned spinning control scheme to the aligned spinning control scheme set.
[0037] Specifically, a database storing historical spinning records is accessed, and all spinning control record groups are extracted and traversed. Each set of records contains raw material information, fiber spinning requirements and corresponding spinning control schemes in the historical spinning process. From the traversed spinning control record groups, one group is selected as the current processing object, namely the first spinning control record group. The spinning raw material information in the current spinning task is compared with the first historical spinning raw material information, and the similarity or difference between the two is calculated to obtain the first spinning raw material association coefficient, which represents the similarity or association between the current spinning raw material information and the historical spinning raw material information. Similarly, the fiber spinning requirements in the current spinning task are compared with the first historical fiber spinning requirements, and the first spinning requirement association coefficient is calculated. According to the preset spinning association evaluation weight, the first spinning raw material association coefficient and the first spinning requirement association coefficient are weighted and summed to obtain the first spinning control registration coefficient. Among them, the spinning association evaluation weight is a pre-set coefficient used to reflect the relative importance of spinning raw material information and spinning requirements in the registration process. The spinning control registration coefficient is a quantitative assessment of the degree of matching between the current historical spinning control scheme and the current spinning task after comprehensively considering the spinning raw material information and the spinning requirements. The calculated first spinning control registration coefficient is compared with the preset spinning control registration constraint to determine whether it meets the constraint condition. The spinning control registration constraint is a preset threshold or condition used to determine whether the historical spinning control scheme is close enough to the current spinning task for reference or direct use. If the first spinning control registration coefficient meets the spinning control registration constraint, the first historical spinning control scheme is marked as the first registered spinning control scheme and added to the registered spinning control scheme set. Continue to traverse the remaining spinning control record groups and repeat the above steps until all record groups are processed. The registered spinning control scheme set contains all historical spinning control schemes that have a high degree of matching with the current spinning task. This implementation method effectively selects the control scheme that is closest to the current spinning task by correlating and evaluating the historical spinning records, thereby improving the accuracy and reliability of the registered spinning control scheme set, thereby reducing subsequent spinning quality problems caused by improper control parameter settings.
[0038] The spinning control decision module 30 is used to make a control parameter decision for the melt spinning device based on the fiber spinning raw material and the fiber spinning demand according to the spinning control feature association space to obtain a spinning control decision space. Specifically, based on the fiber spinning raw material, the fiber spinning demand and the spinning control feature association space, the initial control parameters are set for the melt spinning device. Using simulation software or experimental equipment, a spinning simulation is performed according to the initial control parameters to evaluate whether the simulation results meet the spinning requirements. If the requirements are met, a spinning control decision is generated; otherwise, the parameters are adjusted and re-simulated.
[0039] In a possible implementation, based on the fiber spinning raw material and the fiber spinning demand, a control parameter decision is made on the melt spinning equipment according to the spinning control feature association space to obtain a spinning control decision space, including: setting control parameters of the melt spinning equipment according to the spinning control feature association space to obtain a spinning control scheme space; traversing the spinning control scheme space to extract a first spinning control scheme; based on the fiber spinning raw material, the melt spinning equipment is simulated controlled according to the first spinning control scheme to obtain a first simulated spinning result; judging whether the first simulated spinning result meets the fiber spinning demand; if the first simulated spinning result meets the fiber spinning demand, setting the first spinning control scheme as a first spinning control decision, and adding the first spinning control decision to the spinning control decision space; if the first simulated spinning result does not meet the fiber spinning demand, eliminating the first spinning control scheme.
[0040] Specifically, according to the spinning control feature association space (i.e., the association relationship of how various known control features affect the spinning results), the melt spinning equipment is preliminarily set with control parameters, including temperature, pressure, speed, extrusion amount, etc., and their different combinations constitute the spinning control scheme space, that is, the spinning control scheme space is a set of all possible control parameter combinations, and each combination represents a possible spinning control scheme. Traverse the spinning control scheme space, extract any spinning control scheme from it for simulation control, that is, through computer simulation software in a virtual environment based on fiber spinning raw materials (such as polyester chips), according to the first spinning control scheme, simulate the actual spinning process, and obtain the first simulated spinning result after simulation control. Evaluate whether this simulation result meets the fiber spinning requirements (such as whether the fiber diameter, strength, elongation, etc. meet the standards). If the first simulated spinning result meets the fiber spinning requirements, then the first spinning control scheme is regarded as a valid control decision and is added to the spinning control decision space. The spinning control decision space is a collection of all control decision schemes that meet the spinning requirements. If the first simulated spinning result does not meet the requirements, the control scheme is eliminated, and the spinning control scheme space is traversed to extract the next control scheme for simulation and evaluation until all schemes are traversed. This implementation method uses simulated control to quickly evaluate the feasibility of different control schemes without wasting raw materials and energy, reducing the cost of trial and error and achieving optimal decision-making on the control parameters of the melt spinning equipment.
[0041] The spinning control expectation optimization module 40 is used to perform multi-feature expectation coupling optimization on the spinning control decision space according to the fiber spinning expectation to obtain the spinning control expectation optimization space. Specifically, according to the fiber spinning expectation (energy consumption, quality, efficiency, etc.), the spinning control decision space is optimized with multiple objectives. Optimize energy consumption, quality, efficiency, etc. respectively to obtain their respective optimization domains. Couple the optimization domains to construct the spinning control expectation optimization space to find a spinning control solution that meets multiple expectations at the same time.
[0042] In a possible implementation, according to the fiber spinning expectation, the spinning control decision space is optimized by multi-feature expectation coupling to obtain the spinning control expectation optimization space, including: the fiber spinning expectation includes an expected spinning energy consumption coefficient, an expected spinning quality coefficient and an expected spinning efficiency coefficient; based on the expected spinning energy consumption coefficient, the spinning control decision space is optimized for spinning energy consumption to obtain a first spinning control expectation optimization domain; based on the expected spinning quality coefficient, the spinning control decision space is optimized for spinning quality to obtain a second spinning control expectation optimization domain; based on the expected spinning efficiency coefficient, the spinning control decision space is optimized for spinning efficiency to obtain a third spinning control expectation optimization domain; coupling identification is performed based on the first spinning control expectation optimization domain, the second spinning control expectation optimization domain and the third spinning control expectation optimization domain to generate the spinning control expectation optimization space.
[0043] Specifically, the three key expected goals in the fiber spinning process are the expected spinning energy consumption coefficient, the expected spinning quality coefficient and the expected spinning efficiency coefficient. These three expected coefficients represent different optimization directions in the production process, that is, the lowest energy consumption, the highest quality and the highest efficiency that are expected to be achieved in the production process. Based on the expected spinning energy consumption coefficient, the spinning control decision space is traversed to find the control parameter combination that can make the energy consumption closest to or lower than the expected value (less than / equal to the expected spinning energy consumption coefficient). These combinations constitute the first spinning control expected optimization domain. Similarly, based on the expected spinning quality coefficient, the spinning control decision space is optimized to find the control parameter combination that can produce high-quality fibers (greater than / equal to the expected spinning quality coefficient). These combinations constitute the second spinning control expected optimization domain. Finally, based on the expected spinning efficiency coefficient, the spinning control decision space is optimized to find the control parameter combination that can improve production efficiency (greater than / equal to the expected spinning efficiency coefficient). These combinations constitute the third spinning control expected optimization domain. After obtaining three separate optimization domains, coupling identification is performed, that is, by finding the intersection of these three optimization domains, a combination of control parameters that simultaneously meet the energy consumption, quality, and efficiency expectations is found. This intersection is the expected optimization space for spinning control, which represents the optimal control parameter range that can simultaneously meet multiple optimization goals under current production conditions. This implementation method adopts a multi-feature expectation coupling optimization method, which comprehensively considers multiple key indicators in the production process and avoids other problems caused by the optimization of a single indicator. For example, simply pursuing low energy consumption may lead to a decrease in fiber quality or a decrease in production efficiency; while simply pursuing high quality or high efficiency may lead to a significant increase in energy consumption. Through multi-feature coupling optimization, a balance point is found between different indicators, and the overall production process is optimized.
[0044] In a possible implementation, the spinning energy consumption is optimized in the spinning control decision space based on the expected spinning energy consumption coefficient to obtain a first spinning control expected optimization domain, including: extracting the mth spinning control decision according to the spinning control decision space, wherein m is a positive integer; based on the fiber spinning raw material, energy consumption is predicted for the melt spinning equipment according to the mth spinning control decision to obtain the mth predicted spinning energy consumption coefficient; determining whether the mth predicted spinning energy consumption coefficient is less than / equal to the expected spinning energy consumption coefficient; if the mth predicted spinning energy consumption coefficient is less than / equal to the expected spinning energy consumption coefficient, adding the mth spinning control decision to the first spinning control expected optimization domain.
[0045] Specifically, the spinning control decision space contains all possible combinations or value ranges of spinning control parameters, including spinning speed, temperature, pressure, stretch ratio, etc., which jointly determine the performance and energy consumption of the spinning process. The mth spinning control decision is randomly selected from the spinning control decision space. This decision is a specific parameter combination and represents a possible configuration of the spinning process. Based on the selected mth spinning control decision, the characteristics of the fiber spinning raw material and the performance parameters of the melt spinning equipment are used to predict energy consumption through a machine learning model, and the energy consumption required to complete the spinning process under given spinning control conditions is estimated, and the mth predicted spinning energy consumption coefficient is calculated. The predicted mth spinning energy consumption coefficient is compared with the pre-set expected spinning energy consumption coefficient. This expected value represents the energy consumption target or upper limit of the enterprise or production process. If the mth predicted spinning energy consumption coefficient is less than or equal to the expected spinning energy consumption coefficient, it means that the currently selected spinning control decision meets or exceeds the goal of energy consumption optimization. Therefore, this decision is considered valid and is added to the first spinning control expected optimization domain, which brings together all spinning control decisions that meet the energy consumption optimization conditions. Repeat the above steps, continuously extract new control decisions from the spinning control decision space, and perform energy consumption prediction and comparison until the preset number of iterations is reached. Finally, the first spinning control expected optimization domain contains a series of optimal or near-optimal spinning control decisions. This implementation method quickly screens out control decisions that meet the expected energy consumption by performing energy consumption prediction, thereby improving the optimization efficiency.
[0046] The spinning control energy consumption optimization module 50 is used to perform multi-dimensional energy consumption optimization on the spinning control desired optimization space according to the spinning energy consumption fitness function to obtain a spinning control optimization result. Specifically, the spinning energy consumption fitness function is used to evaluate the fitness of the schemes in the spinning control desired optimization space, and the spinning control scheme with the lowest energy consumption is screened out according to the fitness result.
[0047] In a possible implementation, the spinning control desired optimization space is subjected to multi-dimensional energy consumption optimization according to the spinning energy consumption fitness function to obtain a spinning control optimization result, including: based on the spinning energy consumption fitness function, the fitness of the spinning control desired optimization space is calculated to obtain a plurality of spinning energy consumption fitnesses; based on the spinning energy consumption fitness constraint, the spinning control desired optimization space is subjected to energy consumption fitness optimization screening according to the plurality of spinning energy consumption fitnesses to obtain a spinning control optimization strategy space; based on the spinning control optimization strategy space, spinning energy consumption minimization optimization is performed to generate the spinning control optimization result.
[0048] Specifically, according to the spinning energy consumption fitness function, the fitness of each spinning control decision in the spinning control expected optimization space is calculated to obtain the corresponding spinning energy consumption fitness value. Based on the spinning energy consumption fitness constraint (preset threshold), the multiple spinning energy consumption fitnesses calculated are screened, and only the control decisions that meet the constraint conditions (that is, the control decisions whose energy consumption fitness reaches a certain level) will be retained to form a spinning control optimization strategy space. The control decisions in this space are all potential candidates for energy consumption optimization. In the spinning control optimization strategy space, the spinning energy consumption minimization optimization is further performed, and the goal is to find a control decision that can minimize the spinning energy consumption (or as small as possible). This control decision is regarded as the final spinning control optimization result. This implementation method quickly eliminates control decisions that obviously do not meet the energy consumption optimization goal through energy consumption fitness constraints and screening, reduces unnecessary calculation and experimental costs, and improves optimization efficiency.
[0049] In a possible implementation, the spinning energy consumption fitness function includes:
[0050] ;
[0051] Among them, SEF represents the fitness of spinning energy consumption, exp represents the exponential function with the natural constant e as the base, EAW, EBW and ECW represent the predetermined fitness calculation weights, SEA represents the predicted spinning quality coefficient, EAO represents the expected spinning quality coefficient, SEB represents the predicted spinning efficiency coefficient, EBO represents the expected spinning efficiency coefficient, SEC represents the predicted spinning energy consumption coefficient, and ECO represents the expected spinning energy consumption coefficient.
[0052] The spinning module 60 is used to perform spinning according to the melt spinning device based on the spinning control optimization result and the fiber spinning raw material. Specifically, the spinning module 60 receives the spinning control optimization result and the fiber spinning raw material, adjusts the control parameters of the melt spinning device according to the spinning control optimization result, performs actual spinning production, and produces polyester fiber products that meet the requirements. The embodiment of the present application adopts technical means such as obtaining a fiber production spinning task, associating control features of a melt spinning device according to fiber spinning raw materials and fiber spinning requirements, establishing a spinning control feature association space, making control parameter decisions for the melt spinning device according to the spinning control feature association space, obtaining a spinning control decision space, performing multi-feature expectation coupling optimization on the spinning control decision space according to fiber spinning expectations, obtaining a spinning control expectation optimization space, performing multi-dimensional energy consumption optimization on the spinning control expectation optimization space according to a spinning energy consumption fitness function, obtaining a spinning control optimization result, and performing spinning based on the spinning control optimization result, thereby achieving a balance between energy consumption reduction and spinning quality and spinning efficiency. While ensuring spinning quality and spinning efficiency, energy consumption is effectively reduced, and the coordinated optimization of energy consumption and other key factors is achieved, thereby ensuring the technical effect of improving the overall performance of the polyester fiber production process.
[0053] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0054] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Claims
1. An energy consumption optimization system for polyester fiber production process, It is characterized in that The system comprises: A spinning task acquisition module, wherein the spinning task acquisition module is used to obtain a fiber production spinning task, wherein the fiber production spinning task includes fiber spinning raw materials, fiber spinning requirements and fiber spinning expectations; A spinning control feature association module, the spinning control feature association module is used to associate control features of the melt spinning equipment according to the fiber spinning raw materials and the fiber spinning requirements, and establish a spinning control feature association space; A spinning control decision module, wherein the spinning control decision module is used to make a control parameter decision on the melt spinning equipment based on the fiber spinning raw material and the fiber spinning demand according to the spinning control feature association space to obtain a spinning control decision space; A spinning control expectation optimization module, wherein the spinning control expectation optimization module is used to perform multi-feature expectation coupling optimization on the spinning control decision space according to the fiber spinning expectation to obtain a spinning control expectation optimization space; A spinning control energy consumption optimization module, wherein the spinning control energy consumption optimization module is used to perform multi-dimensional energy consumption optimization on the spinning control desired optimization space according to the spinning energy consumption fitness function to obtain a spinning control optimization result; A spinning module, the spinning module is used to perform spinning according to the melt spinning equipment based on the spinning control optimization result and the fiber spinning raw material; Wherein, the spinning energy consumption fitness function includes: ； Among them, SEF represents the fitness of spinning energy consumption, exp represents the exponential function with the natural constant e as the base, EAW, EBW and ECW represent the predetermined fitness calculation weights, SEA represents the predicted spinning quality coefficient, EAO represents the expected spinning quality coefficient, SEB represents the predicted spinning efficiency coefficient, EBO represents the expected spinning efficiency coefficient, SEC represents the predicted spinning energy consumption coefficient, and ECO represents the expected spinning energy consumption coefficient.
2. An energy consumption optimization system for a polyester fiber production process as claimed in claim 1, It is characterized in that The spinning control feature association module is used to associate the control features of the melt spinning equipment according to the fiber spinning raw material and the fiber spinning demand, and establish a spinning control feature association space, including: Collecting basic information of the fiber spinning raw material to obtain spinning raw material information; Perform spinning record retrieval based on the melt spinning equipment to obtain multiple spinning control record groups; Based on the spinning raw material information and the fiber spinning requirements, control feature registration is performed on the multiple spinning control record groups to obtain a registered spinning control solution set; Based on the registered spinning control scheme set, trigger feature recognition of each control dimension is performed to obtain multiple spinning control trigger intervals; The plurality of spinning control trigger intervals are sorted to generate the spinning control feature association space.
3. An energy consumption optimization system for a polyester fiber production process as claimed in claim 2, It is characterized in that Based on the spinning raw material information and the fiber spinning requirements, the control feature registration of the plurality of spinning control record groups is performed to obtain a registered spinning control scheme set, including: Traversing the plurality of spinning control record groups, extracting a first spinning control record group, wherein the first spinning control record group includes first historical spinning raw material information, first historical fiber spinning requirements, and a first historical spinning control scheme; Based on the spinning raw material information, performing a correlation evaluation on the first historical spinning raw material information to obtain a first spinning raw material correlation coefficient; Based on the fiber spinning demand, performing a correlation evaluation on the first historical fiber spinning demand to obtain a first spinning demand correlation coefficient; Based on the spinning association evaluation weight, weighted calculation is performed on the first spinning raw material association coefficient and the first spinning demand association coefficient to obtain a first spinning control registration coefficient; determining whether the first spinning control registration coefficient satisfies the spinning control registration constraint; If the first spinning control registration coefficient satisfies the spinning control registration constraint, the first historical spinning control scheme is recorded as a first registered spinning control scheme, and the first registered spinning control scheme is added to the registered spinning control scheme set.
4. An energy consumption optimization system for a polyester fiber production process as claimed in claim 1, It is characterized in that The spinning control decision module is used to make a control parameter decision for the melt spinning equipment based on the fiber spinning raw material and the fiber spinning demand according to the spinning control feature association space to obtain a spinning control decision space, including: Setting control parameters of the melt spinning equipment according to the spinning control feature association space to obtain a spinning control solution space; Traversing the spinning control scheme space and extracting a first spinning control scheme; Based on the fiber spinning raw material, the melt spinning device is simulated controlled according to the first spinning control scheme to obtain a first simulated spinning result; Determining whether the first simulated spinning result meets the fiber spinning requirement; If the first simulated spinning result meets the fiber spinning requirement, setting the first spinning control scheme as a first spinning control decision, and adding the first spinning control decision to the spinning control decision space; If the first simulated spinning result does not meet the fiber spinning requirement, the first spinning control scheme is eliminated.
5. An energy consumption optimization system for a polyester fiber production process as claimed in claim 1, It is characterized in that The spinning control expectation optimization module is used to perform multi-feature expectation coupling optimization on the spinning control decision space according to the fiber spinning expectation to obtain the spinning control expectation optimization space, including: The fiber spinning expectations include expected spinning energy consumption coefficient, expected spinning quality coefficient and expected spinning efficiency coefficient; Optimizing the spinning energy consumption in the spinning control decision space based on the expected spinning energy consumption coefficient to obtain a first spinning control expected optimization domain; Optimizing the spinning quality of the spinning control decision space based on the expected spinning quality coefficient to obtain a second spinning control expected optimization domain; Optimizing the spinning efficiency in the spinning control decision space based on the expected spinning efficiency coefficient to obtain a third spinning control expected optimization domain; The spinning control expected optimization space is generated by performing coupling identification based on the first spinning control expected optimization domain, the second spinning control expected optimization domain and the third spinning control expected optimization domain.
6. An energy consumption optimization system for polyester fiber production process as claimed in claim 5, It is characterized in that Optimizing the spinning energy consumption in the spinning control decision space based on the expected spinning energy consumption coefficient to obtain a first spinning control expected optimization domain includes: Extracting the mth spinning control decision according to the spinning control decision space, wherein m is a positive integer; Based on the fiber spinning raw material, predicting the energy consumption of the melt spinning equipment according to the mth spinning control decision, to obtain the mth predicted spinning energy consumption coefficient; Determining whether the m-th predicted spinning energy consumption coefficient is less than / equal to the expected spinning energy consumption coefficient; If the m-th predicted spinning energy consumption coefficient is less than / equal to the expected spinning energy consumption coefficient, the m-th spinning control decision is added to the first spinning control expected optimization domain.
7. An energy consumption optimization system for polyester fiber production process as claimed in claim 1, It is characterized in that The spinning control energy consumption optimization module is used to perform multi-dimensional energy consumption optimization on the spinning control expected optimization space according to the spinning energy consumption fitness function to obtain a spinning control optimization result, including: Based on the spinning energy consumption fitness function, performing fitness calculation on the spinning control expected optimization space to obtain a plurality of spinning energy consumption fitnesses; Based on the spinning energy consumption fitness constraint, the spinning control desired optimization space is subjected to energy consumption fitness optimization screening according to the multiple spinning energy consumption fitnesses to obtain a spinning control optimization strategy space; The spinning energy consumption minimization optimization is performed based on the spinning control optimization strategy space to generate the spinning control optimization result.