Modeling method and device for tobacco redrying production line model

Abstract

The invention provides a modeling method and device for a tobacco redrying production line model. The method comprises the steps that S1, production line data in a tobacco redrying production line are collected in real time; the production line data comprises operation data of each equipment station, process parameters of each equipment station under different processes, unit data of different production units and production line data of the whole production line; s2, preprocessing the production line data; and S3, constructing a production line model based on the preprocessed production line data. According to the scheme, intelligent optimization of the tobacco redrying process is achieved, and the product quality and the production efficiency can be improved.

Description

Technical Field

[0001] The invention belongs to the technical field of tobacco processing, and in particular relates to a modeling method and a device for a tobacco redrying production line model. Background Art

[0002] Tobacco leaf redrying is one of the essential links in the tobacco processing process. The process usually includes vacuum rehydration, leaf moistening, leaf beating and air separation, and leaf redrying. The entire redrying process plays a vital role in the quality of the final tobacco leaf product, determining the characteristics of the tobacco leaf such as taste, combustion performance and smell.

[0003] With the application of digital equipment, the degree of automation of data collection in the tobacco redrying process has been continuously improved. However, there is still the problem that the selection of equipment control parameters is too subjective. The application of intelligent technology in the field of tobacco redrying can effectively improve this problem. By introducing artificial intelligence algorithms and data analysis technology, precise control of tobacco redrying equipment parameters can be achieved, thereby improving the consistency and stability of the quality of finished tobacco products. The application of intelligent technology can not only reduce the cost of manual adjustment of parameters, but also effectively reduce the volatility in the tobacco production process, and improve production efficiency and product quality.

[0004] Therefore, the intelligent development of the tobacco redrying industry is imperative, which will provide strong support for the industry's high-quality development and product upgrading. Summary of the invention

[0005] The purpose of the embodiments of this specification is to provide a method and device for modeling a tobacco redrying production line model.

[0006] To solve the above technical problems, the embodiments of the present application are implemented in the following ways:

[0007] In a first aspect, the present application provides a modeling method for a tobacco redrying production line model, the method comprising:

[0008] S1. Real-time collection of production line data in the tobacco redrying production line; production line data includes: operation data of each equipment station, process parameters of each equipment station under different processes, unit data of different production units and production line data on the entire production line;

[0009] S2. Preprocess the production line data;

[0010] S3. Build a production line model based on the preprocessed production line data.

[0011] In one embodiment, preprocessing the production line data includes:

[0012] S21. Design a production line model according to the hierarchy of "workshop-production line-process-equipment", classify the production line data according to the process flow, and fill in the indicators used as the production line model;

[0013] S22, clean, integrate, and filter the production line data collected in real time, store it according to the indicator dimensions of the production line modeling, delete and fill in the missing production line data, and truncate the production line data that does not meet the preset conditions. This step is set as a standardized data processing process;

[0014] S23. Package and publish the data processing flow of S22, and perform standardized processing on the real-time data generated by the production line operation.

[0015] In one of the embodiments, the operating data of each equipment station is classified according to the process flow, including: vacuum conditioning, leaf laying and swinging, first moistening, second moistening, leaf stem separation, leaf re-roasting, pre-pressing and packaging, and tobacco leaf physical property testing.

[0016] In one embodiment, S3 builds a production line model based on the preprocessed production line data, adopts the "workshop-production line-process-equipment" hierarchical structure for modeling, and expands step by step according to the parent-child structure until the specific equipment, completing the data modeling of the production line, specifically including:

[0017] S31. Model the production line and refine it to specific equipment stations as intelligent production units;

[0018] S32, intelligent production unit modeling for the production unit of the production line;

[0019] S33. Model the entire production line, perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line, and complete the model establishment of the entire production line.

[0020] In one embodiment, S31 specific equipment stations are modeled as intelligent production units, including:

[0021] S311, determining an initial information meta-model of the equipment station according to a specific equipment station, wherein the initial information meta-model of the equipment station includes static data and dynamic data of the equipment station;

[0022] S312, according to the initial information meta-model of the equipment station, the pre-processed production line data is processed with big data features by using the principal component analysis method;

[0023] S313. Process the data again according to the proposed first quality optimal model, first delivery optimal model and first cost optimal model, optimize and adjust the initial physical model of the equipment station based on the results, and complete the dynamic reconstruction of the equipment status.

[0024] In one embodiment, S32 performs intelligent production unit modeling on the production unit of the production line, including:

[0025] S321. Determine the initial information meta-model of the production unit according to the type of the production unit;

[0026] S322, performing multi-objective optimization combination and heterogeneous data coupling and association processing on the real-time data of the production unit according to the initial information meta-model of the production unit;

[0027] S323. Process the data again according to the proposed second quality optimal model, second delivery optimal model and second cost optimal model, optimize and adjust the initial information meta-model of the production unit based on the results, and complete the dynamic reconstruction of the production unit.

[0028] In one embodiment, S33 performs production line modeling on the entire production line, specifically:

[0029] S331. Combined with the production and process requirements, sort out the static and dynamic data of the production line equipment that needs to be collected in the production process, and determine the initial information meta-model of the production line;

[0030] S332. Perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line according to the initial information meta-model of the production line to complete the model establishment of the entire production line.

[0031] In a second aspect, the present application provides a modeling device for a tobacco redrying production line model, the device comprising:

[0032] The data acquisition module is used to collect the production line data of the tobacco redrying production line in real time; the production line data includes: the operation data of each equipment station, the process parameters of each equipment station under different processes, the unit data of different production units and the production line data of the entire production line;

[0033] Preprocessing module, used to preprocess production line data;

[0034] The model building module is used to build a production line model based on the preprocessed production line data.

[0035] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the modeling method of the tobacco redrying production line model of the first aspect is implemented.

[0036] In a fourth aspect, the present application provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the modeling method of the tobacco redrying production line model as in the first aspect.

[0037] It can be seen from the technical solution provided in the above embodiments of this specification that the solution: First, intelligent production unit modeling is performed on the equipment station, including initial physical modeling and data processing. Then, the equipment model is optimized and adjusted and dynamically reconstructed based on the data results. Subsequently, intelligent unit modeling is performed on the production unit, and dynamic reconstruction is completed through optimized combination and data processing. Finally, intelligent modeling and data processing are performed on the entire production line to achieve intelligent optimization of the tobacco leaf redrying process and improve product quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 A schematic diagram of a flow chart of a modeling method for a tobacco redrying production line model provided in this application;

[0040] Figure 2 A schematic diagram of the process of building a production line model provided for this application;

[0041] Figure 3 A schematic diagram of the hierarchical structure of the production line model provided for this application;

[0042] Figure 4 A schematic diagram of the structure of a modeling device for a tobacco redrying production line model provided in this application;

[0043] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0045] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0046] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments of the present application description without departing from the scope or spirit of the present application. Other embodiments derived from the present application description will be apparent to those skilled in the art. The present application description and examples are exemplary only.

[0047] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0048] With the increasing application of digital equipment in tobacco redrying, the degree of automation of the data collection process has gradually improved. The introduction of artificial intelligence algorithms and data analysis technology can achieve precise control of tobacco redrying equipment parameters, thereby improving the consistency and stability of the quality of finished tobacco products. In addition, the application of intelligent technology can not only reduce the cost of manual parameter adjustment, but also effectively reduce the volatility in the tobacco production process, thereby improving production efficiency and product quality. In order to solve the modeling problem of the tobacco industry production line, this application proposes a modeling method for a tobacco redrying production line model. First, the equipment station is modeled as an intelligent production unit, including initial physical modeling and data processing. Then, the equipment model is optimized and adjusted and dynamically reconstructed based on the data results. Subsequently, the production unit is modeled as an intelligent unit, and the dynamic reconstruction is completed through optimization combination and data processing. Finally, the entire production line is modeled and data processed to achieve intelligent optimization of the tobacco redrying process and improve product quality and production efficiency.

[0049] The present invention is further described in detail below with reference to the accompanying drawings and embodiments.

[0050] Reference Figure 1 , which shows a flow chart of a modeling method applicable to the tobacco redrying production line model provided in an embodiment of the present application.

[0051] like Figure 1 As shown, the modeling method of the tobacco redrying production line model may include:

[0052] S1. Real-time collection of production line data in the tobacco redrying production line; production line data includes: operation data of each equipment station, process parameters of each equipment station under different processes, unit data of different production units and production line data on the entire production line.

[0053] Specifically, the operation data in the tobacco redrying production line is data collected in real time and stored in a database.

[0054] S2. Preprocess the production line data.

[0055] In one embodiment, preprocessing the production line data may include:

[0056] S21. Design the production line model according to the level of "workshop-production line-process-equipment", classify the production line data according to the process flow, and fill it as the indicator of the production line model. It can be understood that the process flow is classified according to the level of "workshop-production line-process-equipment".

[0057] Among them, the operation data of each equipment station is classified according to the process flow, including: vacuum moisture recovery, leaf laying and swinging, first moisturizing, second moisturizing, leaf stem separation, leaf re-roasting, pre-pressing and packaging, and tobacco leaf physical properties testing and other steps.

[0058] Exemplarily, the equipment parameters of the vacuum rehumidification process include: equipment operating status, equipment fault status, air pressure, steam pressure and more than 20 other equipment parameters; the equipment parameters of the leaf laying and swinging process include: equipment operating status, equipment fault status, swinging table flow, leaf laying belt speed, upper and lower blade gap of the cutting knife, maximum lifting height of the unwinding roller and other parameters; the equipment parameters under the one-stage process are: one-stage drive M34 setting frequency, one-stage temperature setting temperature and other ten characteristics; the equipment parameters under the two-stage process are: two-stage roller setting frequency, two-stage circulation fan setting frequency and more than 60 setting parameters; the equipment parameters under the leaf stem separation stage process are: one-beating roller 1M13 setting frequency and more than 80 setting parameters; the equipment parameters under the leaf redrying stage process are: each drying zone fan frequency, cooling zone fan frequency, rehumidification zone fan frequency, each drying zone dehumidification fan frequency, cooling zone dehumidification fan frequency setting and more than 140 parameters; the physical property detection of tobacco leaves includes the detection of parameters such as tobacco leaf moisture and temperature, flow rate, and metal content in each bundle of tobacco leaves.

[0059] Step 22: Clean, integrate, and filter the production line data collected in real time, store it according to the indicator dimensions of the production line modeling, delete and fill in the missing production line data, and truncate the production line data that does not meet the preset conditions. Set this step as a standardized data processing process.

[0060] Specifically, the production line data is collected in real time, and the collected real-time data is cleaned, integrated, screened, etc. to retain valid data. According to the modeling splitting in S21, each device is independent, and this embodiment collects and integrates data according to the device dimension.

[0061] The acquisition frequencies of different equipment parameters vary. In order to achieve data integration and alignment, some process feature data need to be downsampled.

[0062] In actual operation, data missing and abnormal situations often occur. In order to minimize the impact of these situations on model training, interpolation is used to fill missing values ​​during the data processing stage. If missing values ​​of a feature appear continuously, this section of data samples can be removed to prevent data distortion caused by interpolation filling.

[0063] For abnormal values, that is, operating data that does not meet the preset conditions, the upper and lower thresholds of each parameter can be set according to the staff's experience and knowledge for truncation processing to ensure the authenticity and reliability of the data.

[0064] S23. Package and publish the data processing flow of S22, and perform standardized processing on the real-time data generated by the production line operation.

[0065] Specifically, considering the differences in the dimensions used for data parameters between different devices, in order to improve the convergence speed of the algorithm and reduce the impact of outliers, different data parameters are standardized so that their range is controlled between 0 and 1.

[0066]

[0067] Among them, x is the original data, x' is the standardized data, and x min and x max are the minimum and maximum values ​​of the feature data respectively.

[0068] It can be understood that the data processing actions of S22 are encapsulated as data standardization processing services. In the future, the real-time data of all equipment on the corresponding production line will be processed in a standardized manner through this service.

[0069] S3. Build a production line model based on the preprocessed production line data. Figure 2 shown.

[0070] In one embodiment, S3 constructs a production line model based on the preprocessed running production line data, such as Figure 3 As shown in the figure, the "workshop-production line-process-equipment" hierarchical structure is used for modeling, and the parent-child structure is expanded step by step until the specific equipment is reached to complete the data modeling of the production line, including:

[0071] S31. Model the production line and refine it to specific equipment stations as intelligent production units;

[0072] S32, intelligent production unit modeling is performed on the production unit of the production line, and after processing the production unit data through multi-objective optimization combination and heterogeneous data coupling and association, the unit dynamic reconstruction is completed according to each optimal model;

[0073] S33. Model the entire production line, perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line, and complete the model establishment of the entire production line.

[0074] The intelligent production unit has intelligent processing capabilities such as autonomy, self-governance, and collaboration. The intelligent unit based on CPS technology can realize functions such as intelligent autonomous identification, autonomous operation, and software and hardware interoperability. At the same time, the intelligent production unit (processing, logistics, warehousing, testing, assembly, etc.) has dynamic perception capabilities and can adapt to the characteristics of multi-variety and variable batch production. According to the needs of production tasks, the production system can be autonomously configured and virtually reconstructed, realizing autonomous decision-making and task allocation of production units and building an intelligent production system.

[0075] The key technology of intelligent production unit can realize the modeling of the entire production line and its various production units. It can apply the optimal quality model, optimal delivery model and optimal cost model determined according to the specific needs of customers to the entire production line, and determine the optimal models of each production line, optimal model of production unit and optimal model of equipment station. According to the feedback of real-time data in each optimal model, the mapping model is optimized to continuously adjust the physical model of the entire production line and realize the autonomous configuration technology of the intelligent unit.

[0076] The intelligent production unit has the technology to realize the joint group control of different input materials in different processes under the same plan, and can integrate the output data of different processes to realize the modeling of the entire production plan.

[0077] In one embodiment, S31 specific equipment stations are modeled as intelligent production units, including:

[0078] S311. Determine an initial information meta-model of the equipment station according to a specific equipment station, wherein the initial information meta-model of the equipment station includes static data and dynamic data of the equipment station.

[0079] Specifically, the static data of the equipment station includes data such as equipment manufacturer, brand, model and specifications, and the dynamic data is sorted out according to the equipment characteristics and process characteristics, such as equipment operating status, health status, key indicators (such as speed, temperature, pressure, etc.).

[0080] The object modeling technique proposed by Rumbaugh is widely used in engineering practice. Later, the UML was proposed on this basis, which made the modeling technology move closer to the track of standardization. The object-oriented data model contains four core concepts: object, object identification, encapsulation, and class.

[0081] Object: A basic unit encapsulated by a set of data structures and a set of operations on this data structure. An object contains attributes and methods. Attributes describe the state, composition, and characteristics of the object. The attribute set constitutes the data structure, and methods describe the behavioral characteristics of the object.

[0082] Object identifier: An identifier used by objects in a data model to distinguish identity information, which is unique.

[0083] Encapsulation: Each object is an encapsulation of its state and behavior, and communicates with other objects through open interfaces.

[0084] Class: An abstraction of the common properties and methods of a class of objects. An object is an instance of a class.

[0085] Combined with the object-oriented modeling method of the metamodel, equipment and workstation modeling should define three levels of content: define objects (equipment / workstation) and the data contained in the objects; organize objects and the data contained in the objects; and define data formats.

[0086] The equipment structure is complex and generally consists of components, subcomponents, and parts. In addition to mechanical devices, it also includes control systems, electrical systems, auxiliary systems and their subsystems. In the metamodel, components and systems are represented by components, and subcomponents and subsystems are represented by subcomponents. Each component or subcomponent contains multiple variables. For example, the spindle component contains variables such as spindle coordinates, spindle load, spindle speed, and spindle override. Variables are represented by attributes in the metamodel. Variable information is divided into static information, dynamic information, and configuration information. Static information refers to information that does not change with equipment configuration and production process, such as equipment number, production date, etc.; dynamic information refers to information that changes dynamically during the production process, such as the number of processed parts, equipment status, etc.; configuration information refers to information that configures the equipment according to the needs of production tasks, and does not change for a long time after configuration, such as IP address, number of controlled axes, etc.; in the metamodel, the collection of similar attributes is called an attribute set, and the attribute set can be divided into a static attribute set, a dynamic attribute set, and a configuration attribute set. Each attribute has multiple characteristics such as index number, Chinese name, data type, etc., and the attribute element is used in the metamodel to represent the characteristics of the attribute. In the metamodel, operations on data are represented by methods, and relationships between data are represented by references.

[0087] Therefore, the core elements of the equipment metamodel include equipment, components, subcomponents, static attribute sets, dynamic attribute sets, configuration attribute sets, attributes, attribute elements, methods, references, etc. A hierarchical structure is used for modeling. Exemplarily, the model can include a workstation status model, a workstation capability model, and a personnel capability model. Among them, the workstation status model needs to include specific parameters such as work plan, workstation status, work-in-progress product information, and tooling; the workstation capability model needs to include information parameters such as equipment type, size range, manufacturing efficiency, and pass rate; the personnel capability model needs to include parameters such as job range, capability level, work efficiency, and quality capability.

[0088] S312. Based on the initial information meta-model of the equipment station, the pre-processed production line data is processed with big data features by principal component analysis.

[0089] Specifically, considering the large amount of real-time data and the high amount of redundant information, principal component analysis is selected for data feature processing from the perspective of dimensionality reduction. The principal component analysis method transforms the original feature space into a new feature space through linear transformation. The dimension of the new feature space is much smaller than that of the original feature space, while retaining the information of the original data as much as possible.

[0090] Exemplarily, for a given, standardized data set X, each row represents a sample, and each column represents a feature.

[0091] Compute the covariance matrix:

[0092]

[0093] Perform eigendecomposition on the covariance matrix:

[0094] Σv=λv (3)

[0095] Where v is the eigenvector, λ is the eigenvalue, and n is the number of samples in the dataset.

[0096] Select principal components: Select the eigenvectors corresponding to the largest k eigenvalues ​​to form the projection matrix:

[0097] W=(v1,v2,...,vk) (4)

[0098] Map the original data into the new feature space:

[0099] Z=XW (5)

[0100] Where Z is the data after dimensionality reduction.

[0101] S313. Process the data again according to the proposed first quality optimal model, first delivery optimal model and first cost optimal model, optimize and adjust the initial physical model of the equipment station based on the results, and complete the dynamic reconstruction of the equipment status.

[0102] Specifically, formulating the optimal quality model includes: determining key quality indicators, setting quality target values, establishing a quality assessment system, and formulating quality improvement measures.

[0103] Formulating the optimal delivery model includes: clarifying key delivery elements, setting delivery target values, establishing a delivery evaluation system, and formulating delivery improvement measures.

[0104] Formulating an optimal cost model includes: identifying cost components, setting cost target values, establishing a cost evaluation system, and formulating cost improvement measures.

[0105] After the data is processed again according to the proposed first quality optimal model, the first delivery optimal model, and the first cost optimal model, the real-time data will be extracted and calculated in combination with the business data, and bound to the business data to form view data, which will be used for reports or dashboard displays in the business system.

[0106] After combining with the business, relevant indicators of the equipment can be calculated, such as OEE, MTTR, MTBF, etc., and the equipment can be adjusted and optimized based on the indicators.

[0107] In one embodiment, S32 performs intelligent production unit modeling on the production unit of the production line, including:

[0108] S321. Determine the initial information meta-model of the production unit according to the production unit type;

[0109] S322, performing multi-objective optimization combination and heterogeneous data coupling and association processing on the real-time data of the production unit according to the initial information meta-model of the production unit;

[0110] In terms of multi-objective optimization combination processing, an adaptive fast non-dominated sorting genetic algorithm (ANSGA) is used to realize data processing. This algorithm is based on the adaptive genetic algorithm (AGA) and NSGA-II algorithm, and introduces multiple crossover mutations and adaptive crossover mutation bit methods, combining the advantages of the two, with both excellent convergence rate and the advantages of non-dominated solution set sorting. It can well solve the multi-objective optimization problems in tobacco redrying plants.

[0111] At the same time, multi-source data integration is used to carry out heterogeneous data coupling and association processing, integrate heterogeneous data from different data sources, and perform association analysis through feature extraction, alignment and fusion methods to provide a more comprehensive and consistent perspective.

[0112] Since the model can only be visualized after being associated with the business, so that users can better understand the business, step S322 is to associate the real-time collected data stored according to the model with the business data.

[0113] S323. Process the data again according to the proposed second quality optimal model, second delivery optimal model and second cost optimal model, optimize and adjust the initial information meta-model of the production unit based on the results, and complete the dynamic reconstruction of the production unit.

[0114] It should be noted that the principle of step S323 is similar to that of step S313 and will not be repeated here.

[0115] In one embodiment, S33 performs production line modeling on the entire production line, specifically:

[0116] S331. Combined with the production and process requirements, sort out the static and dynamic data of the production line equipment that needs to be collected in the production process, and determine the initial information meta-model of the production line;

[0117] S332. Perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line according to the initial information meta-model of the production line to complete the model establishment of the entire production line.

[0118] This means that not only is the data on the production line analyzed in depth, but the production process is continuously monitored and adjusted in real time through the framework of the information meta-model. This ensures that the operating efficiency of the production line is maximized, while responding and optimizing in real time to any problems or bottlenecks that may arise, ensuring a smooth and efficient production process. In addition, dynamic reconstruction optimization processing also means that we can flexibly adjust the configuration and operation process of the production line according to changes in market demand and production conditions to adapt to changing production needs, thereby improving overall production flexibility and market response speed.

[0119] The principle of large-cycle optimization is to decompose a large problem into multiple sub-problems, then solve these sub-problems separately, combine the solutions of the sub-problems, and adjust and improve the original problem based on the combined results. This process may require multiple iterations until the entire problem converges. Specifically, the production tasks after the production line optimization are decomposed into unit task indicators and distributed to each production unit, and then the unit task indicators are decomposed into each equipment task indicator and distributed to each equipment station. Then, the static and dynamic data of the model are extracted according to business needs, and the real-time data collected by the model is used to bind it to the production tasks.

[0120] The dynamic reconstruction optimization processing specifically processes the data again according to the proposed third quality optimal model, the third delivery optimal model and the third cost optimal model, and then optimizes and adjusts the initial information meta-model of the production line to complete the multi-objective production optimization of the production line.

[0121] Reference Figure 4 , which shows a structural schematic diagram of a modeling device for a tobacco redrying production line model described according to an embodiment of the present application.

[0122] like Figure 4 As shown, the modeling device 400 of the tobacco redrying production line model may include:

[0123] The data acquisition module 410 is used to collect the production line data in the tobacco redrying production line in real time; the production line data includes: the operation data of each equipment station, the process parameters of each equipment station under different processes, the unit data of different production units and the production line data of the entire production line;

[0124] A preprocessing module 420, used for preprocessing production line data;

[0125] The model building module 430 is used to build a production line model based on the preprocessed production line data.

[0126] Optionally, the preprocessing module 420 is further used for:

[0127] S21. Design a production line model according to the hierarchy of "workshop-production line-process-equipment", classify the production line data according to the process flow, and fill in the indicators used as the production line model;

[0128] S22, clean, integrate, and filter the production line data collected in real time, store it according to the indicator dimensions of the production line modeling, delete and fill in the missing production line data, and truncate the production line data that does not meet the preset conditions. This step is set as a standardized data processing process;

[0129] S23. Package and publish the data processing flow of S22, and perform standardized processing on the real-time data generated by the production line operation.

[0130] Optionally, the operating data of each equipment station can be classified according to the process flow, including: vacuum conditioning, leaf laying and swinging, first moistening, second moistening, leaf stem separation, leaf redrying, pre-pressing and packaging, and tobacco leaf physical property testing.

[0131] Optionally, the model building module 430 is further configured to:

[0132] S31. Model the production line and refine it to specific equipment stations as intelligent production units;

[0133] S32, intelligent production unit modeling for the production unit of the production line;

[0134] S33. Model the entire production line, perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line, and complete the model establishment of the entire production line.

[0135] Optionally, the model building module 430 is further configured to:

[0136] S311, determining an initial information meta-model of the equipment station according to a specific equipment station, wherein the initial information meta-model of the equipment station includes static data and dynamic data of the equipment station;

[0137] S312, according to the initial information meta-model of the equipment station, the pre-processed production line data is processed with big data features by using the principal component analysis method;

[0138] S313. Process the data again according to the proposed first quality optimal model, first delivery optimal model and first cost optimal model, optimize and adjust the initial physical model of the equipment station based on the results, and complete the dynamic reconstruction of the equipment status.

[0139] Optionally, the model building module 430 is further configured to:

[0140] S321. Determine the initial information meta-model of the production unit according to the type of the production unit;

[0141] S322, performing multi-objective optimization combination and heterogeneous data coupling and association processing on the real-time data of the production unit according to the initial information meta-model of the production unit;

[0142] S323. Process the data again according to the proposed second quality optimal model, second delivery optimal model and second cost optimal model, optimize and adjust the initial information meta-model of the production unit based on the results, and complete the dynamic reconstruction of the production unit.

[0143] Optionally, the model building module 430 is further configured to:

[0144] S331. Combined with the production and process requirements, sort out the static and dynamic data of the production line equipment that needs to be collected in the production process, and determine the initial information meta-model of the production line;

[0145] S332. Perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line according to the initial information meta-model of the production line to complete the model establishment of the entire production line.

[0146] The modeling device of a tobacco redrying production line model provided in this embodiment can execute the embodiment of the above method. Its implementation principle and technical effect are similar and will not be repeated here.

[0147] Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 5 As shown, a structural schematic diagram of an electronic device 500 suitable for implementing an embodiment of the present application is shown.

[0148] like Figure 5 As shown, the electronic device 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0149] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0150] In particular, according to the embodiments of the present disclosure, the above reference Figure 1 The described process can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program code for executing the modeling method of the above-mentioned tobacco redrying production line model. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511.

[0151] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of the code, and the aforementioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0152] The units or modules involved in the embodiments described in the present application may be implemented by software or hardware. The units or modules described may also be arranged in a processor. The names of these units or modules do not constitute limitations on the units or modules themselves in certain circumstances.

[0153] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop, a mobile phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0154] As another aspect, the present application further provides a storage medium, which may be a storage medium included in the aforementioned device in the above embodiment; or a storage medium that exists independently and is not assembled into the device. The storage medium stores one or more programs, and the aforementioned programs are used by one or more processors to execute the modeling method of the tobacco redrying production line model described in the present application.

[0155] Storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0156] It should be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0157] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A modeling method for a tobacco redrying production line model, characterized in that: The method comprises: S1. Real-time collection of production line data in the tobacco redrying production line; the production line data includes: operation data of each equipment station, process parameters of each equipment station under different processes, unit data of different production units and production line data on the entire production line; S2. Preprocessing the production line data; S3. Build a production line model based on the preprocessed production line data.

2. The method according to claim 1, characterized in that The preprocessing of the production line data includes: S21. Divide the production line data into different levels according to the "workshop-production line-process-equipment" level by level, design a production line model, classify the production line data according to the process flow, and fill in the indicators used as the production line model; S22, cleaning, integrating, and screening the production line data collected in real time, storing it according to the indicator dimensions of the production line modeling, deleting and filling the missing production line data, and truncating the production line data that does not meet the preset conditions, and setting this step as a standardized data processing process; S23. Package and publish the data processing flow of S22, and perform standardized processing on the real-time data generated by the production line operation.

3. The method according to claim 2, characterized in that The operation data of each equipment station are classified according to the process flow, including: vacuum moisture recovery, leaf laying and swinging, first moistening, second moistening, leaf stem separation, leaf re-roasting, pre-pressing and packaging, and tobacco leaf physical property testing.

4. The method according to claim 1, characterized in that: S3 constructs a production line model based on the preprocessed production line data, adopts the "workshop-production line-process-equipment" hierarchical structure for modeling, and expands step by step according to the parent-child structure until the specific equipment, completing the data modeling of the production line, specifically including: S31. Model the production line and refine it to specific equipment stations as intelligent production units; S32, intelligent production unit modeling for the production unit of the production line; S33. Model the entire production line, perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line, and complete the model establishment of the entire production line.

5. The method according to claim 4, characterized in that The S31 specific equipment station is modeled as an intelligent production unit, including: S311, determining an initial information meta-model of the equipment station according to a specific equipment station, wherein the initial information meta-model of the equipment station includes static data and dynamic data of the equipment station; S312, performing big data feature processing on the preprocessed production line data by principal component analysis according to the initial information meta-model of the equipment station; S313. Process the data again according to the proposed first quality optimal model, first delivery optimal model and first cost optimal model, optimize and adjust the initial physical model of the equipment station based on the results, and complete the dynamic reconstruction of the equipment status.

6. The method according to claim 1, characterized in that The S32 performs intelligent production unit modeling on the production unit of the production line, including: S321. Determine the initial information meta-model of the production unit according to the type of the production unit; S322, performing multi-objective optimization combination and heterogeneous data coupling and association processing on the real-time data of the production unit according to the initial information meta-model of the production unit; S323. Process the data again according to the proposed second quality optimal model, second delivery optimal model and second cost optimal model, optimize and adjust the initial information meta-model of the production unit based on the results, and complete the dynamic reconstruction of the production unit.

7. The method according to claim 1, characterized in that The S33 performs production line modeling on the entire production line, specifically: S331. Combined with the production and process requirements, sort out the static and dynamic data of the production line equipment that needs to be collected in the production process, and determine the initial information meta-model of the production line; S332. Perform large-loop optimization and dynamic reconstruction optimization processing on the real-time data of the production line according to the initial information meta-model of the production line to complete the model establishment of the entire production line.

8. A modeling device for a tobacco redrying production line model, characterized in that: The device comprises: The data acquisition module is used to collect the production line data in the tobacco redrying production line in real time; the production line data includes: the operation data of each equipment station, the process parameters of each equipment station under different processes, the unit data of different production units and the production line data of the entire production line; A preprocessing module, used for preprocessing the production line data; The model building module is used to build a production line model based on the preprocessed production line data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the modeling method of the tobacco redrying production line model as described in any one of claims 1-7 is implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the modeling method of the tobacco redrying production line model as described in any one of claims 1 to 7 is implemented.

Images