Intelligent recommendation method and system for corrugated carton packaging production process

Abstract

The invention discloses an intelligent recommendation method and system for a corrugated carton packaging production process. The method comprises the steps that a user inputs the type, corrugation type parameters, the number of layers, the size, the weight, production process requirements and quality control standards of corrugated boards through a terminal; the system is based on a cloud computing platform, combines a mechanical property model and a manufacturing process database of a corrugated board, calculates and analyzes input data, and recommends a production process parameter combination; the system collects data in the production process in real time through a sensor, compares the data with recommended parameters, and automatically adjusts parameters of production equipment or gives an alarm. And the system continuously collects production data and user feedback, and updates the recommendation model by using a machine learning algorithm. According to the method and the system, the defective rate is effectively reduced, the production efficiency is improved, the recommendation result is accurate, the management is efficient, and the requirements of corrugated paper field production can be met.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent production control of corrugated paper, and particularly relates to an intelligent recommendation method and system for the production process of corrugated cardboard boxes for packaging. Background Art

[0002] As an important branch of packaging materials, corrugated cardboard boxes play an important role in logistics, warehousing, sales and other links. However, the traditional production process of corrugated cardboard boxes mainly relies on manual experience and fixed processes, lacking comprehensive analysis and intelligent optimization of the mechanical properties of corrugated cardboard, manufacturing process parameters, and real-time data during the production process.

[0003] Currently, during the production process of corrugated cardboard boxes, the selection of process parameters is mostly based on the experience of operators, making it difficult to achieve precise control and optimization. For example, during the steam heating process, workers frequently measure the temperature and moisture content of the cardboard surface using a moisture meter, thermometer or pressure gauge, and adjust the humidity and temperature of the steam according to the measurement results. However, this method has problems such as subjective errors and energy consumption, resulting in unstable forming quality of the corrugated board. In addition, there is a lack of real-time monitoring and dynamic adjustment mechanisms during the production process, making it impossible to timely detect and solve problems in production, affecting production efficiency and product quality.

[0004] In recent years, with the development of industrial informatization and intelligent technologies, it has become possible to apply advanced technologies such as cloud computing, the Internet of Things, and machine learning to the optimization of the corrugated cardboard box production process. For example, the all-Ethernet intelligent machine solution provided by Rockwell Automation has achieved efficient, flexible and flexible production of corrugated cardboard printers through integrated programming and touch screen operation, and the operation efficiency has doubled compared to the past manual operation. However, existing research and technology applications mostly focus on the improvement of single links or simple models, lacking systematic integration and in-depth mining of the mechanical properties of corrugated cardboard, manufacturing processes, and production process data. Summary of the Invention

[0005] The present invention provides an intelligent recommendation method and system for the production process of corrugated cardboard boxes for packaging to solve the technical problem that the existing prediction model has an unsatisfactory prediction effect on parameters such as the molten steel carbon content and temperature at the end of the converter process because it does not consider the process parameters of the time series type in the converter process.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] On the one hand, the present invention provides an intelligent recommendation method for the production process of corrugated cardboard boxes for packaging, which is characterized by including:

[0008] The user inputs the type of corrugated cardboard, corrugation parameters, number of layers, size, weight, as well as production process requirements and quality control standards through a terminal;

[0009] Based on the cloud computing platform, the system combines the mechanical property model of corrugated board and the manufacturing process database to calculate and analyze the input data, and recommends the combination of production process parameters;

[0010] The system collects data during the production process in real time through sensors, compares with the recommended parameters, and automatically adjusts the parameters of production equipment or issues an alarm;

[0011] The system continuously collects production data and user feedback, and uses machine learning algorithms to update the recommendation model.

[0012] Furthermore, the mechanical property model includes an in-plane impact response model and an edge crush strength simulation model:

[0013] The in-plane impact response model is constructed based on the explicit dynamic finite element method. The specific steps are as follows:

[0014] According to the type and corrugation parameters of the corrugated board, determine the geometric dimensions and mesh division scheme of the finite element model, and use tetrahedral or hexahedral elements for mesh division;

[0015] Set the material properties, including parameters such as the elastic modulus, Poisson's ratio, and yield strength of the paper. Considering the anisotropy of the paper, use the MAT274 paper constitutive model to describe the mechanical properties of the paper in different directions;

[0016] Apply boundary conditions and loads, constrain the bottom of the model, apply the impact velocity or impact force, and simulate the actual impact condition;

[0017] Run the explicit dynamic finite element analysis, calculate the stress and strain distributions of the corrugated board during the impact process, and obtain the numerical results of the dynamic densification strain and the plateau stress;

[0018] According to the calculation results, generate an in-plane impact response curve to show the mechanical behavior characteristics of the corrugated board at different impact velocities;

[0019] The edge crush strength simulation model is constructed based on the paper constitutive model. The specific steps are as follows:

[0020] According to the structural parameters of the corrugated board, establish a three-dimensional model of the corrugated board, including geometric information such as the corrugation type, number of layers, and paper thickness;

[0021] Apply the MAT274 model to set the mechanical property parameters of the paper, including the elastic modulus, Poisson's ratio, yield strength, etc., considering the mechanical differences of the paper in different directions;

[0022] Apply boundary conditions and loads, simulate the loading method in the edge crush experiment, and apply pressure to the edge of the corrugated board;

[0023] Perform finite element analysis to calculate the stress and strain distribution of corrugated board during edge compression, and obtain the numerical results of edge compression strength;

[0024] According to the calculation results, generate an edge compression strength curve to show the deformation and load-bearing capacity of corrugated board under different pressures.

[0025] Furthermore, the manufacturing process database includes process parameters and quality control data for raw material selection, pretreatment, corrugating, bonding, and cutting. The specific steps are as follows:

[0026] Raw material selection: According to the type and quality requirements of corrugated board, select the appropriate paper type, consider performance indicators such as fiber length, thickness, and strength of the paper, and record the supplier information, batch number, and inspection report of the paper;

[0027] Pretreatment: Pretreat the raw material paper, including operations such as cutting and humidity adjustment, to ensure the stable performance of the paper during production, and record the process parameters of pretreatment, such as cutting size and humidity control range;

[0028] Corrugating: Use a corrugating roll to corrugate the paper to form corrugated board with a specific corrugation type, and record the process parameters such as the specifications, pressure, and temperature of the corrugating roll, as well as the geometric parameters such as the corrugation height and pitch of the corrugated board;

[0029] Bonding: Bond the corrugated board with the face paper and the inner paper to form a multi-layer structure, and record the parameters such as the type, formula, and coating amount of the adhesive, as well as the process parameters such as temperature, pressure, and time during the bonding process;

[0030] Cutting: Cut the bonded corrugated board to obtain the required size and shape, and record the process parameters such as the model of the cutting equipment, tool parameters, and cutting speed;

[0031] Quality control: Conduct quality inspections in each production link, record the inspection results, including quality indicators such as the thickness, flatness, and strength of the cardboard, and mark and process unqualified products;

[0032] Data management: Store the process parameters and quality control data of the above-mentioned links in the database, establish data association relationships for convenient query and analysis, and regularly back up and maintain the database to ensure the security and integrity of the data;

[0033] Data analysis: Use statistical analysis methods to mine the data in the database, identify the correlation between key process parameters and product quality, establish a quality prediction model, and provide data support for process optimization.

[0034] On the other hand, the present invention also provides an intelligent recommendation system for the production process of corrugated carton packaging, which is characterized by including:

[0035] Data input module: It supports users to input information related to corrugated board and production process, has a user interface and data verification function, guides users to input data accurately, and supports batch data import and historical data backfill;

[0036] Intelligent recommendation module: A computing engine deployed in the cloud, integrating a mechanical model and a process database, using a recommendation algorithm, comprehensively considering production conditions, quality requirements, and equipment status, to realize the intelligent recommendation of production process parameters;

[0037] Cloud computing module: Utilizes distributed computing resources to quickly process and analyze large-scale data, has high scalability and fault tolerance, can handle production data and user concurrent requests of different scales, and ensures the stable operation and efficient service of the system;

[0038] Real-time monitoring and feedback module: Integrates high-precision sensor data acquisition and intelligent device control functions, realizes dynamic monitoring and parameter adjustment of the production process, supports multiple communication protocols and data transmission standards, ensures the real-time and reliability of data transmission, and has equipment status monitoring and fault diagnosis functions;

[0039] Optimization and update module: Based on production data and user feedback, continuously optimizes the recommendation model, improves system performance, uses machine learning algorithms to automatically mine potential laws and correlations in data, optimizes the internal structure and parameters of the model, and supports manual intervention and adjustment.

[0040] The beneficial effects brought by the technical solution provided by the present invention at least include:

[0041] By combining the mechanical property model of corrugated board (such as in-plane impact response model and edge crush strength simulation model) and the manufacturing process database, the system of the present invention can accurately simulate and analyze the mechanical behavior of corrugated board under different working conditions based on methods such as explicit dynamic finite element method and one-dimensional shock wave theory. Thus, it provides a solid technical basis for the recommendation of production process parameters, ensuring that the recommendation results not only conform to physical reality but also meet the quality control standards in production.

[0042] The real-time monitoring and feedback module of the present invention uses industrial Internet of Things technology to be able to collect key data in the production process in real time and conduct comparative analysis with the recommended parameters. Once it is found that the deviation exceeds the preset range, the system will automatically trigger an alarm and adjust the parameters of the production equipment, thereby effectively reducing the defective rate, improving production efficiency, and reducing production costs.

[0043] The optimization and update module of the present invention adopts machine learning algorithms to continuously collect production data and user feedback, automatically mine potential patterns and correlations in the data, and optimize the internal structure and parameters of the recommendation model. This not only improves the accuracy of the recommendation results but also enables the system to adapt to changes in different production environments and requirements, with good scalability and robustness.

[0044] The visualization interface provided by the system of the present invention displays recommendation results, production process data, and quality analysis reports in the form of intuitive charts, graphs, and reports. Users can perform multi-dimensional data screening and drilling as needed to deeply understand the production situation and use the intelligent alarm and prompt functions to handle abnormal situations in a timely manner, thereby achieving scientific and efficient production management.

[0045] In the present invention, the cloud computing module utilizes distributed computing resources and containerization technologies to achieve elastic scheduling and efficient utilization of resources. At the same time, through the fault tolerance mechanism and performance monitoring, it ensures the stable operation of the system under high load conditions, providing reliable support for the rapid processing and analysis of large-scale production data. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0047] Figure 1 It is a flowchart of an intelligent recommendation method for the corrugated cardboard box packaging production process provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will further describe the embodiments of the present invention in detail with reference to the drawings.

[0049] This embodiment provides an intelligent recommendation method and system for the corrugated cardboard box packaging production process. According to

[0050] The user inputs the type of corrugated board, corrugation parameters, number of layers, size, weight, as well as production process requirements and quality control standards through the terminal;

[0051] Based on the cloud computing platform, the system combines the mechanical property model of corrugated board and the manufacturing process database to calculate and analyze the input data and recommend a combination of production process parameters;

[0052] The system collects data during the production process in real time through sensors, compares it with the recommended parameters, and automatically adjusts the production equipment parameters or issues an alarm;

[0053] The system continuously collects production data and user feedback, and uses machine learning algorithms to update the recommendation model.

[0054] Please refer to Figure 1 the flowchart of the intelligent recommendation method for the corrugated cardboard packaging production process shown.

[0055] It should be noted that the mechanical property model includes an in-plane impact response model and an edge crush strength simulation model:

[0056] The in-plane impact response model is constructed based on the explicit dynamic finite element method. The specific steps are as follows:

[0057] According to the type and corrugation parameters of the corrugated board, determine the geometric dimensions and mesh division scheme of the finite element model, and use tetrahedral or hexahedral elements for mesh division;

[0058] Set the material properties, including parameters such as the elastic modulus, Poisson's ratio, and yield strength of the paper. Considering the anisotropy of the paper, use the MAT274 paper constitutive model to describe the mechanical properties of the paper in different directions;

[0059] Apply boundary conditions and loads, constrain the bottom of the model, apply the impact velocity or impact force, and simulate the actual impact conditions;

[0060] Run the explicit dynamic finite element analysis, calculate the stress and strain distributions of the corrugated board during the impact process, and obtain the numerical results of the dynamic densification strain and the plateau stress;

[0061] According to the calculation results, generate an in-plane impact response curve to show the mechanical behavior characteristics of the corrugated board at different impact velocities;

[0062] The edge crush strength simulation model is constructed based on the paper constitutive model. The specific steps are as follows:

[0063] According to the structural parameters of the corrugated board, establish a three-dimensional model of the corrugated board, including geometric information such as the corrugation type, number of layers, and paper thickness;

[0064] Apply the MAT274 model to set the mechanical property parameters of the paper, including the elastic modulus, Poisson's ratio, yield strength, etc., considering the mechanical differences of the paper in different directions;

[0065] Apply boundary conditions and loads, simulate the loading method in the edge crush experiment, and apply pressure to the edge of the corrugated board;

[0066] Conduct finite element analysis, calculate the stress and strain distributions of the corrugated board during the edge crush process, and obtain the numerical results of the edge crush strength;

[0067] Based on the calculation results, generate an edge crush strength curve to show the deformation and load-bearing capacity of corrugated cardboard under different pressures.

[0068] It should be noted that the manufacturing process database contains process parameters and quality control data for raw material selection, pretreatment, corrugating, bonding, and cutting. The specific steps are as follows:

[0069] Raw material selection: According to the type and quality requirements of corrugated cardboard, select appropriate paper types, consider performance indicators such as fiber length, thickness, and strength of the paper, and record the supplier information, batch number, and inspection report of the paper.

[0070] Pretreatment: Pretreat the raw material paper, including operations such as cutting and humidity adjustment, to ensure the stable performance of the paper during production, and record the process parameters of pretreatment, such as cutting size, humidity control range, etc.

[0071] Corrugating: Use a corrugating roll to corrugate the paper to form corrugated cardboard with a specific corrugation type, and record the process parameters such as the specifications, pressure, and temperature of the corrugating roll, as well as the geometric parameters such as the corrugation height and pitch of the corrugated cardboard.

[0072] Bonding: Bond the corrugated cardboard with the face paper and the inner paper to form a multi-layer structure, and record the parameters such as the type, formula, and coating amount of the adhesive, as well as the process parameters such as temperature, pressure, and time during the bonding process.

[0073] Cutting: Cut the bonded corrugated cardboard to obtain the required size and shape, and record the process parameters such as the model of the cutting equipment, tool parameters, and cutting speed.

[0074] Quality control: Conduct quality inspections in each production link, record the inspection results, including quality indicators such as the thickness, flatness, and strength of the cardboard, and mark and process unqualified products.

[0075] Data management: Store the process parameters and quality control data of the above-mentioned links in the database, establish data association relationships for convenient query and analysis, and regularly back up and maintain the database to ensure the security and integrity of the data.

[0076] Data analysis: Use statistical analysis methods to mine the data in the database, identify the correlation between key process parameters and product quality, establish a quality prediction model, and provide data support for process optimization.

[0077] It should be noted that an intelligent recommendation system for the production process of corrugated carton packaging includes:

[0078] Data Input Module: It supports users to input information related to corrugated board and production process, has a user interface and data verification function, guides users to input data accurately, and supports batch data import and historical data backfilling;

[0079] The development team designed an intuitive and user-friendly interface that supports web and mobile device access. The interface adopts a responsive design to ensure normal display and operation on different devices.

[0080] In the user interface, detailed form input items are set, including basic information such as the type of corrugated board (such as A flute, B flute, etc.), flute parameters (flute height, flute pitch, etc.), number of layers, size, weight, etc., as well as production process requirements (such as temperature, humidity, pressure, etc.) and quality control standards (such as edge crush strength, puncture strength, etc.).

[0081] To improve the accuracy of data input, a data verification function is also integrated into the interface. When users input data, the system checks in real time whether the format and range of the data meet the requirements, and promptly prompts users to correct the data that does not meet the requirements.

[0082] To facilitate users to input data in batches, the system supports batch data import functions in formats such as Excel and CSV. Users can import the pre-prepared corrugated board parameters and production process requirements into the system in tabular form, greatly improving the data input efficiency.

[0083] At the same time, the system also provides a historical data backfilling function. Users can upload historical production data files from the local area, and the system automatically parses and stores them in the corresponding database tables, facilitating users for data management and analysis.

[0084] Intelligent Recommendation Module: A computing engine deployed in the cloud, which integrates a mechanical model and a process database, uses recommendation algorithms, and comprehensively considers production conditions, quality requirements, and equipment status to realize intelligent recommendation of production process parameters;

[0085] Cloud Computing Module: Utilizes distributed computing resources to quickly process and analyze large-scale data, has high scalability and fault tolerance, can handle production data of different scales and user concurrent requests, and ensures the stable operation and efficient service of the system;

[0086] Real-time Monitoring and Feedback Module: Integrates high-precision sensor data acquisition and intelligent device control functions, realizes dynamic monitoring and parameter adjustment of the production process, supports multiple communication protocols and data transmission standards, ensures the real-time and reliability of data transmission, and has equipment status monitoring and fault diagnosis functions;

[0087] Optimization and Update Module: Based on production data and user feedback, continuously optimize the recommendation model, improve system performance, use machine learning algorithms to automatically mine potential laws and associations in the data, optimize the internal structure and parameters of the model, and support manual intervention and adjustment.

[0088] It should be noted that the intelligent recommendation module is constructed based on the explicit dynamic finite element method and the one-dimensional shock wave theory. The specific steps are as follows:

[0089] Receive the corrugated board parameters and production process requirements input by the user, including information such as corrugation type, number of layers, size, weight, impact speed, etc.;

[0090] According to the input parameters, retrieve similar process cases from the manufacturing process database to obtain the initial process parameter combination;

[0091] Import the initial process parameter combination into the mechanical property model, run explicit dynamic finite element analysis and edge crush strength simulation, and calculate mechanical property indexes such as the corresponding dynamic densification strain, plateau stress, and edge crush strength;

[0092] In-plane Impact Response Model: Based on the explicit dynamic finite element method, the R & D team constructed an in-plane impact response model. In actual applications, according to the corrugated board type and corrugation type parameters input by the user, the system automatically determines the geometric dimensions and mesh division scheme of the finite element model, and uses tetrahedral or hexahedral elements for mesh division. Set material properties such as the elastic modulus, Poisson's ratio, and yield strength of the paper, consider the anisotropy of the paper, and use the MAT274 paper constitutive model to describe the mechanical properties of the paper in different directions. Apply boundary conditions and loads, constrain the bottom of the model, apply the impact speed or impact force, and simulate the actual impact conditions. Run explicit dynamic finite element analysis, calculate the stress and strain distributions of the corrugated board during the impact process, obtain the numerical results of the dynamic densification strain and plateau stress, and generate the in-plane impact response curve.

[0093] Edge Crush Strength Simulation Model: Based on the paper constitutive model, the R & D team constructed an edge crush strength simulation model. According to the structural parameters of the corrugated board, the system establishes a three-dimensional model of the corrugated board, including geometric information such as corrugation type, number of layers, and paper thickness. Apply the MAT274 model to set the mechanical property parameters of the paper, apply boundary conditions and loads, simulate the loading method in the edge crush experiment, and apply pressure to the edge of the corrugated board. Conduct finite element analysis, calculate the stress and strain distributions of the corrugated board during the edge crush process, obtain the numerical results of the edge crush strength, and generate the edge crush strength curve.

[0094] Evaluate the calculation results to determine whether they meet the quality control standards specified by the user. If not, adjust the process parameters and repeat the simulation calculation until a process parameter combination that meets the quality requirements is found;

[0095] Recommend process parameter combinations that meet quality requirements to users, and at the same time provide corresponding mechanical property analysis reports and production suggestions;

[0096] Support the flexible combination and switching of multiple mechanical property models to adapt to different production scenarios and quality requirements. The module adopts a microservices architecture and supports independent deployment and expansion.

[0097] It should be noted that the real-time monitoring and feedback module is constructed through industrial Internet of Things technology. The specific steps are as follows:

[0098] Connect production equipment and sensors to collect real-time data during the production process, including cardboard thickness, flatness, moisture content, workshop environmental temperature and humidity, equipment operation status parameters, etc.;

[0099] Preprocess the collected data to remove noise and outliers to ensure the accuracy and reliability of the data;

[0100] Store the preprocessed data in a temporary buffer, and transfer the data to the cloud computing module for further processing and analysis at a set time interval or data volume threshold;

[0101] In the cloud computing module, compare and analyze the real-time data with the recommended production process parameters. When it is found that the deviation exceeds the preset tolerance range, automatically trigger an alarm mechanism to notify production personnel to intervene;

[0102] In order to achieve elastic resource scheduling, a resource scheduling algorithm is integrated in the cloud computing module. According to the user request volume and data processing volume, the system automatically adjusts the allocation of computing resources to ensure that the system can still run stably under high load.

[0103] Adjust the operation parameters of production equipment according to real-time data and feedback from production personnel to achieve dynamic optimization and quality control of the production process;

[0104] Adopt a combination of edge computing and cloud computing to preprocess and analyze real-time data, reducing data transmission latency and storage pressure.

[0105] It should be noted that the optimization and update module is constructed using machine learning algorithms. The specific steps are as follows:

[0106] Continuously collect production data and user feedback, including information such as production process parameters, quality inspection results, and user evaluations;

[0107] Perform preprocessing operations such as data cleaning and normalization on the collected data to remove outliers and noisy data to ensure the quality and consistency of the data;

[0108] Extract key features from the preprocessed data, such as production process parameters, quality inspection results, etc., and construct feature vectors;

[0109] Use the extracted feature vectors and corresponding label data to train the recommendation model, evaluate the model performance using a loss function, and adjust the model parameters through an optimization algorithm to minimize the loss function value;

[0110] Validate the trained model on an independent validation set, evaluate the generalization ability and prediction accuracy of the model, and further optimize and update the model according to the validation results to ensure that the model can adapt to new production data and user requirements.

[0111] It should be noted that the data input module supports web and mobile terminal access and has cross-platform compatibility. The specific steps are as follows:

[0112] Design a user-friendly interface, including various input methods such as form input, drop-down menu, file upload, etc., to guide users to accurately input basic information such as the type of corrugated board, corrugation parameters, number of layers, size, weight, etc., as well as production process requirements and quality control standards;

[0113] When users input data, perform real-time data verification to check whether the format and range of the data meet the requirements. For data that does not meet the requirements, prompt users to correct it in a timely manner;

[0114] Support the batch data import function, allowing users to batch import the parameters and production process requirements of corrugated boards in formats such as Excel and CSV to improve data input efficiency;

[0115] Support the historical data backfill function. Users can upload historical production data files from the local area, and the system automatically parses and stores them in the corresponding database tables to facilitate users' data management and analysis;

[0116] Adopt a responsive design to ensure that the module can be normally displayed and operated on desktop computers, tablets, and smartphones, providing a consistent user experience.

[0117] It should be noted that the cloud computing module has high scalability and fault tolerance. The specific steps are as follows:

[0118] Utilize distributed computing resources and adopt the Hadoop distributed computing framework to quickly process and analyze large-scale production data, improving computing efficiency and response speed;

[0119] Implement elastic resource scheduling, automatically adjust the allocation of computing resources according to the user request volume and data processing volume, and ensure that the system can still operate stably under high load;

[0120] Adopt containerization technology for service deployment and management, encapsulate each component of the system into independent containers, and improve resource utilization and system scalability;

[0121] Implement a fault tolerance mechanism. When a certain computing node fails, automatically reassign tasks to other healthy nodes to ensure the continuity of computing tasks and the integrity of data;

[0122] Regularly monitor and optimize the system performance, collect system operation status data, analyze performance bottlenecks, and make timely optimization adjustments to ensure the efficient operation of the system.

[0123] It should be noted that the system also provides a visualization interface to display recommendation results, production process data, and quality analysis reports. The specific steps are as follows:

[0124] Design intuitive charts, graphs, and reports to display key data and analysis results, including the mechanical property curve of corrugated board, the distribution map of production process parameters, the statistical table of quality inspection results, etc.;

[0125] Support multi-dimensional data filtering and drilling functions. Users can select different filtering conditions (time range, production line, product type) according to their needs to view data, or gradually drill down from the overall data to detailed data to deeply understand the production situation;

[0126] Provide intelligent alarm and prompt functions. When abnormal situations (quality index exceeding the standard, equipment failure) occur during the production process, the system automatically issues an alarm and highlights the abnormal information on the visualization interface to remind users to pay attention and handle it in a timely manner;

[0127] Generate detailed production reports and quality analysis reports, including production process parameters, quality inspection results, production efficiency statistics, etc. Support the export and printing functions of reports to facilitate users to summarize and report production;

[0128] Support users to customize views and report templates. Users can customize personalized visualization interfaces and report formats according to their own management needs and analysis habits to improve the scientificity and effectiveness of production management.

[0129] In addition, it should be noted that the present invention can be provided as a method, a device, or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0130] Embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing terminal device generate a device for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or a device for implementing the functions specified in multiple blocks.

[0131] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or a device for implementing the functions specified in multiple blocks. These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or a device for implementing the functions specified in multiple blocks.

[0132] It should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article, or terminal device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or terminal device including the said element.

[0133] Finally, it should be noted that the above description is the preferred embodiment of the present invention. It should be pointed out that although the preferred embodiments of the present invention have been described, for those skilled in the art of this technology, once they know the basic creative concept of the present invention, without departing from the principle described in the present invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. An intelligent recommendation method for corrugated carton packaging production process, characterized in that: include: The user inputs the type, flute parameters, number of layers, size, weight, production process requirements and quality control standards of the corrugated board through the terminal; Based on the cloud computing platform, the system combines the mechanical properties model of corrugated board and the manufacturing process database to calculate and analyze the input data and recommend production process parameter combinations; The system collects data from the production process in real time through sensors, compares it with recommended parameters, and automatically adjusts production equipment parameters or issues alarms; The system continuously collects production data and user feedback, and uses machine learning algorithms to update the recommendation model.

2. The intelligent recommendation method for corrugated paperboard packaging production process according to claim 1, characterized in that: The mechanical properties model includes an in-plane impact response model and an edge pressure strength simulation model: The in-plane impact response model is constructed based on the explicit dynamic finite element method, and the specific steps are as follows: According to the type and flute parameters of the corrugated board, the geometric dimensions and meshing scheme of the finite element model are determined, and the meshing is performed using tetrahedron or hexahedron elements; Set material properties, including paper elastic modulus, Poisson's ratio, yield strength and other parameters. Consider the anisotropy of paper and use the MAT274 paper constitutive model to describe the mechanical properties of paper in different directions. Apply boundary conditions and loads, constrain the bottom of the model, and apply impact velocity or impact force to simulate actual impact conditions; Run explicit dynamic finite element analysis to calculate the stress and strain distribution of corrugated cardboard during the impact process, and obtain the numerical results of dynamic densification strain and platform stress; Based on the calculation results, the in-plane impact response curve is generated to show the mechanical behavior characteristics of corrugated cardboard under different impact velocities; The edge pressure strength simulation model is constructed based on the paper constitutive model, and the specific steps are as follows: According to the structural parameters of corrugated cardboard, a three-dimensional model of the corrugated cardboard is established, including geometric information such as flute type, number of layers, and paper thickness; The MAT274 model is used to set the mechanical properties of paper, including elastic modulus, Poisson's ratio, yield strength, etc., taking into account the mechanical differences of paper in different directions; Apply boundary conditions and loads to simulate the loading method in the edge pressure test and apply pressure to the edge of the corrugated cardboard; Finite element analysis was performed to calculate the stress and strain distribution of corrugated cardboard during edge compression, and the numerical results of edge compression strength were obtained; Based on the calculation results, an edge compression strength curve is generated to show the deformation and bearing capacity of corrugated cardboard under different pressures.

3. The intelligent recommendation method for corrugated paperboard packaging production process according to claim 1, characterized in that: The manufacturing process database contains process parameters and quality control data for raw material selection, pretreatment, corrugating, bonding, and cutting. The specific steps are as follows: Raw material selection: select the appropriate paper type according to the type and quality requirements of the corrugated board, consider the paper's fiber length, thickness, strength and other performance indicators, and record the paper's supplier information, batch number and inspection report; Pretreatment: Pretreatment of raw material paper, including cutting, adjusting humidity and other operations, to ensure the stability of paper performance during the production process, and record pretreatment process parameters, such as cutting size, humidity control range, etc.; Corrugating: Use corrugating rollers to corrugate paper to form corrugated board with a specific flute type. Record the corrugating roller specifications, pressure, temperature and other process parameters, as well as the corrugated board's corrugation height, corrugation spacing and other geometric parameters; Bonding: Bond the corrugated cardboard with the face paper and the back paper to form a multi-layer structure, and record the type, formula, coating amount and other parameters of the adhesive, as well as the temperature, pressure, time and other process parameters during the bonding process; Cutting: Cut the bonded corrugated cardboard to obtain the required size and shape, and record the model of the cutting equipment, tool parameters, cutting speed and other process parameters; Quality control: Conduct quality inspections at each production stage and record the inspection results, including the thickness, flatness, strength and other quality indicators of the cardboard, and mark and handle unqualified products; Data management: Store the process parameters and quality control data of the above links in the database, establish data association relationships, facilitate query and analysis, and regularly back up and maintain the database to ensure data security and integrity; Data analysis: Use statistical analysis methods to mine data in the database, identify the correlation between key process parameters and product quality, establish quality prediction models, and provide data support for process optimization.

4. An intelligent recommendation system for corrugated carton packaging production process, characterized in that: include: Data input module: supports users to input information related to corrugated cardboard and production process, has user interface and data verification functions, guides users to input data accurately, supports batch data import and historical data backfill; Intelligent recommendation module: A computing engine deployed in the cloud that integrates mechanical models and process databases, uses recommendation algorithms, and comprehensively considers production conditions, quality requirements, and equipment conditions to achieve intelligent recommendations for production process parameters. Cloud computing module: It uses distributed computing resources to quickly process and analyze large-scale data. It has high scalability and fault tolerance, and can handle production data of different scales and concurrent user requests to ensure stable system operation and efficient service. Real-time monitoring and feedback module: Integrates high-precision sensor data acquisition and intelligent equipment control functions to achieve dynamic monitoring and parameter adjustment of the production process, supports multiple communication protocols and data transmission standards, ensures the real-time and reliability of data transmission, and has equipment status monitoring and fault diagnosis functions; Optimization and update module: Based on production data and user feedback, continuously optimize the recommendation model, improve system performance, use machine learning algorithms to automatically mine potential patterns and associations in the data, optimize the internal structure and parameters of the model, and support manual intervention and adjustment.

5. The intelligent recommendation system for corrugated paperboard packaging production process according to claim 4, characterized in that: The intelligent recommendation module is constructed based on the explicit dynamic finite element method and one-dimensional shock wave theory, and the specific steps are as follows: Receive the corrugated cardboard parameters and production process requirements input by the user, including flute type, number of layers, size, weight, impact speed and other information; According to the input parameters, similar process cases are retrieved from the manufacturing process database to obtain the initial process parameter combination; Import the initial process parameter combination into the mechanical properties model, run explicit dynamic finite element analysis and edge compression strength simulation, and calculate the corresponding mechanical properties such as dynamic densification strain, platform stress and edge compression strength; Evaluate the calculation results to determine whether they meet the quality control standards specified by the user. If not, adjust the process parameters and repeat the simulation calculation until a combination of process parameters that meets the quality requirements is found; Recommend the process parameter combination that meets the quality requirements to the user, and provide the corresponding mechanical properties analysis report and production suggestions; It supports flexible combination and switching of multiple mechanical property models to adapt to different production scenarios and quality requirements. The module adopts a microservice architecture and supports independent deployment and expansion.

6. The intelligent recommendation system for corrugated paperboard packaging production process according to claim 4, characterized in that: The real-time monitoring and feedback module is constructed through industrial Internet of Things technology, and the specific steps are as follows: Connect production equipment and sensors to collect real-time data during the production process, including cardboard thickness, flatness, moisture content, workshop environment temperature and humidity, equipment operating status parameters, etc. Preprocess the collected data to remove noise and outliers to ensure the accuracy and reliability of the data; The preprocessed data is stored in a temporary buffer and transmitted to the cloud computing module for further processing and analysis according to the set time interval or data volume threshold; In the cloud computing module, real-time data is compared and analyzed with the recommended production process parameters. When deviations are found to exceed the preset tolerance range, an alarm mechanism is automatically triggered to notify production personnel to intervene. Adjust the operating parameters of production equipment based on real-time data and feedback from production personnel to achieve dynamic optimization and quality control of the production process; A combination of edge computing and cloud computing is used to pre-process and analyze real-time data to reduce data transmission delays and storage pressure.

7. The intelligent recommendation system for corrugated paperboard packaging production process according to claim 4, characterized in that: The optimization and update module is constructed using a machine learning algorithm, and the specific steps are: Continuously collect production data and user feedback, including production process parameters, quality inspection results, user evaluation and other information; Perform pre-processing operations such as cleaning and normalization on the collected data to remove outliers and noise data to ensure data quality and consistency; Extract key features from preprocessed data, such as production process parameters, quality inspection results, etc., and construct feature vectors; The recommendation model is trained using the extracted feature vectors and the corresponding label data, the model performance is evaluated using the loss function, and the model parameters are adjusted through the optimization algorithm to minimize the loss function value; The trained model is validated on an independent validation set to evaluate the model's generalization ability and prediction accuracy. The model is further optimized and updated based on the validation results to ensure that the model can adapt to new production data and user needs.

8. The intelligent recommendation system for corrugated paperboard packaging production process according to claim 4, characterized in that: The data input module supports web and mobile terminal access and has cross-platform compatibility. The specific steps are as follows: Design a user-friendly interface, including form input, drop-down menu, file upload and other input methods, to guide users to accurately input basic information such as corrugated cardboard type, flute parameters, number of layers, size, weight, as well as production process requirements and quality control standards; When users input data, data verification is performed in real time to check whether the format and range of the data meet the requirements. For data that does not meet the requirements, users are promptly prompted to make corrections; Support batch data import function, allowing users to batch import corrugated cardboard parameters and production process requirements in Excel, CSV and other formats to improve data input efficiency; Support historical data backfill function. Users can upload historical production data files locally. The system will automatically parse and store them in the corresponding database table, making it easier for users to manage and analyze data. Responsive design is used to ensure that the module can be displayed and operated normally on desktop computers, tablets, and smartphones, providing a consistent user experience.

9. The intelligent recommendation system for corrugated paperboard packaging production process according to claim 4, characterized in that: The cloud computing module has high scalability and fault tolerance, and the specific steps are as follows: Utilize distributed computing resources and adopt the Hadoop distributed computing framework to quickly process and analyze large-scale production data, thereby improving computing efficiency and response speed; Implement flexible resource scheduling, automatically adjust the allocation of computing resources according to user requests and data processing volume, and ensure that the system can still run stably under high load conditions; Use containerization technology for service deployment and management, encapsulate each component of the system into an independent container, and improve resource utilization and system scalability; Implement a fault-tolerant mechanism. When a computing node fails, the task is automatically redistributed to other healthy nodes to ensure the continuity of computing tasks and the integrity of data. Regularly monitor and optimize system performance, collect system operation status data, analyze performance bottlenecks, and make timely optimization adjustments to ensure efficient operation of the system.

10. The intelligent recommendation system for corrugated paperboard packaging production process according to claim 4, characterized in that: The system also provides a visual interface to display recommendation results, production process data and quality analysis reports. The specific steps are as follows: Design intuitive charts, graphs and reports to display key data and analysis results, including mechanical property curves of corrugated board, distribution diagrams of production process parameters, statistical tables of quality inspection results, etc. Supports multi-dimensional data filtering and drilling functions. Users can select different filtering conditions (time range, production line, product type) to view data as needed, or drill from overall data to detailed data to gain an in-depth understanding of production conditions; Provide intelligent alarm and prompt functions. When abnormal situations occur during the production process (quality indicators exceed the standard, equipment failure), the system automatically issues an alarm and highlights the abnormal information on the visual interface to remind users to pay attention and handle it in time; Generate detailed production reports and quality analysis reports, including production process parameters, quality inspection results, production efficiency statistics and other information, support report export and printing functions, and facilitate users to make production summaries and reports; It supports user-defined views and report templates. Users can customize personalized visualization interfaces and report formats according to their own management needs and analysis habits to improve the scientificity and effectiveness of production management.

Images