Leather bag full-process self-adaptive production system and method based on intelligent workshop data real-time monitoring
Through equipment IoT collaboration and digital twin optimization technology, intelligent management of the leather bag production process has been achieved, solving the problems of low efficiency and difficult quality control in traditional production, and improving production efficiency and resource utilization.
Patent Information
- Application Number
- CN202511030973.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-25
- Publication Date
- 2025-09-23
AI Technical Summary
In the traditional leather bag production process, the production links are scattered and highly dependent on manual operations, resulting in low production efficiency, difficult to control quality, lagging information flow, and production scheduling that cannot respond to changes in real time, which cannot meet the requirements of modern production for efficiency, quality and flexibility.
Through technologies such as equipment IoT collaboration, intelligent process flow scheduling, and digital twin optimization, intelligent and refined management of the production process can be achieved, including equipment interconnection, real-time data collection, automatic execution of modular process units, quality monitoring and feedback, and digital twin model optimization scheduling.
It improves production efficiency and resource utilization, ensures product quality, reduces production time and energy consumption, and realizes efficient, flexible scheduling and intelligent upgrading of the production process.
Smart Images
Figure CN120686766A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of leather product production, and in particular to a full-process self-adaptive production system and method for leather bags based on real-time monitoring of intelligent workshop data. Background Art
[0002] In the traditional leather bag production process, multiple process steps, such as design, cutting, sewing, and packaging, operate independently, and the production process relies heavily on manual labor. Designers manually draw dimensions and graphics, and cutters arrange the leather based on their experience. Other steps, such as sewing and gluing, are also completed manually. Existing technologies often rely on single equipment and manual inspections, lacking overall coordination of the production process and real-time data monitoring. Under this traditional model, despite the introduction of some automated equipment, such as automatic glue sprayers and cutting machines, most operations still require manual intervention, resulting in low production efficiency and difficulty in achieving precise coordination between each step.
[0003] The current production model faces multiple technical deficiencies. The fragmented nature of production processes and their heavy reliance on manual labor results in unstable processes and an inability to provide real-time feedback and adjust production data, leading to process errors and production waste. Product quality is difficult to control, especially in areas such as leather arrangement, cutting precision, and sewing techniques, which are prone to quality fluctuations and lack timely quality inspection and adjustment mechanisms. Information flow lags, and production scheduling is unable to respond to changes in real time, resulting in a disconnect between production plans and actual execution, impacting production efficiency and delivery times. Consequently, existing technologies are unable to meet the efficiency, quality, and flexibility requirements of modern leather bag production. Summary of the Invention
[0004] In response to the shortcomings of the existing technology, the present invention provides a full-process self-adaptive production system and method for leather bags based on real-time monitoring of intelligent workshop data. It realizes intelligent and refined management of the production process through equipment Internet of Things collaboration, process flow, intelligent scheduling, digital twin optimization and other technologies, and improves production efficiency, quality and resource utilization.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a full-process self-adaptive production system for leather bags based on real-time monitoring of intelligent workshop data, comprising:
[0006] The equipment IoT collaboration module is used to interconnect production equipment through industrial Ethernet and collect real-time operating parameters of the production equipment;
[0007] A process flow intelligent scheduling module is used to generate a production process execution sequence based on production order information, material inventory information and the real-time operating parameters, and send it to the production equipment;
[0008] A modular process unit, configured to receive the production process execution sequence through a standardized interface and automatically execute the corresponding process;
[0009] A data monitoring and feedback module is used to monitor process parameters and customer service data in real time and provide real-time feedback to the process flow intelligent scheduling module. The data monitoring and feedback module includes a quality monitoring unit and a customer data monitoring unit;
[0010] The digital twin self-adaptive optimization module is used to build digital twin models of various equipment and process flows in the workshop and generate optimized scheduling plans.
[0011] Preferably, the production equipment includes design equipment, cutting equipment, scraping equipment, glue spraying equipment, sewing equipment and packaging equipment.
[0012] Preferably, the real-time operating parameters include the temperature, pressure, rotation speed, current, voltage, power, operating speed and fault status of the equipment.
[0013] Preferably, the modular process unit includes a cutting unit, a gluing unit, a sewing unit and a packaging unit, and the cutting unit, gluing unit, sewing unit and packaging unit are all composed of a driver, a sensor, a PLC controller and a standardized bus interface module.
[0014] Preferably, the quality monitoring unit uses a visual inspection model based on a convolutional neural network to perform online detection of suture uniformity and glue coating thickness, and the customer data monitoring unit periodically pulls customer order execution progress, quality feedback and customized configuration requirements from the mobile APP.
[0015] Preferably, the digital twin self-adaptive optimization module updates the twin model parameters through the following error correction formula:
[0016] θ ′ ←θ ′ +α(θ-θ ′ )
[0017] Among them, θ is the physical device parameter vector collected in real time, θ ′ is the parameter vector corresponding to the digital twin model, α∈(0,1) is the learning rate, and the formula of the digital twin model is:
[0018]
[0019] Among them, C max is the maximum completion time of all processes, n is the total number of equipment in the production line, U i ∈[0,1] is the utilization rate of the i-th device, E iis the energy consumption per unit time of the i-th equipment, f1 is the mapping function for minimizing the completion time objective, f2 is the mapping function for maximizing the equipment utilization objective, and f3 is the mapping function for minimizing the total energy consumption objective.
[0020] Preferably, the optimization scheduling scheme includes a production process execution sequence based on multi-objective optimization, an equipment resource load distribution scheme and a key process parameter configuration.
[0021] The full-process self-adaptive production method for leather bags based on real-time monitoring of intelligent workshop data includes:
[0022] S1. Interconnect production equipment such as design, cutting, leather scraping, gluing, sewing, and packaging via industrial Ethernet, and collect equipment operating status and process parameters in real time;
[0023] S2. Dynamically generate a production process execution sequence based on production orders, material inventory, and the equipment operating parameters, and distribute it to each production equipment;
[0024] S3. Each modular unit automatically receives and executes the production process execution sequence through a standardized interface;
[0025] S4. Online monitoring of process parameters and customer-side order progress and quality feedback;
[0026] S5. Build a workshop digital twin model based on the real-time monitoring data to optimize the production scheduling plan, and iteratively update the optimization results to the process flow intelligent scheduling module.
[0027] The present invention provides a full-process, self-adaptive production system and method for leather bags based on real-time monitoring of intelligent workshop data. This system has the following beneficial effects: It interconnects production equipment via industrial Ethernet and collects the equipment's operating status and process parameters in real time, enabling precise monitoring and scheduling of the production process. The intelligent workshop data real-time monitoring system can dynamically generate production process execution sequences and automatically distribute them to each piece of production equipment, effectively improving production efficiency and resource utilization. Through the standardized interfaces and automatic execution of modular process units, the system can flexibly respond to various process adjustments during the production process, ensuring precise execution of product quality and production schedules.
[0028] The introduction of the digital twin adaptive optimization module enables continuous optimization of production scheduling based on real-time monitoring data. This module uses real-time data to correct model parameters, optimizing the production process execution sequence, equipment resource load distribution, and key process parameter configuration, effectively reducing production time and energy consumption while improving equipment utilization. This data-driven optimization strategy not only ensures efficient production but also provides strong support for the sustainability and intelligent upgrade of production systems. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION
[0030] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0031] Example 1
[0032] like Figure 1 As shown, an embodiment of the present invention provides a full-process self-adaptive production system and method for leather bags based on real-time monitoring of smart workshop data, including an equipment Internet of Things collaboration module for interconnecting production equipment through industrial Ethernet and collecting real-time operating parameters of production equipment in real time.
[0033] The process flow intelligent scheduling module generates a production process execution sequence based on production order information, material inventory information, and real-time operating parameters, and distributes it to production equipment, including design equipment, cutting equipment, peeling equipment, glue spraying equipment, sewing equipment, and packaging equipment. Real-time operating parameters include equipment temperature, pressure, speed, current, voltage, power, operating speed, and fault status.
[0034] The modular process unit is used to receive the production process execution sequence through a standardized interface and automatically execute the corresponding process. The modular process unit includes a cutting unit, a gluing unit, a sewing unit and a packaging unit. The cutting unit, gluing unit, sewing unit and packaging unit are all composed of a driver, sensor, PLC controller and a standardized bus interface module.
[0035] The data monitoring and feedback module is used to monitor process parameters and customer service data in real time and provide real-time feedback to the process flow intelligent scheduling module. The data monitoring and feedback module includes a quality monitoring unit and a customer data monitoring unit. The quality monitoring unit uses a visual inspection model based on a convolutional neural network to perform online inspection of suture uniformity and glue coating thickness. The customer data monitoring unit periodically pulls customer order execution progress, quality feedback, and customized configuration requirements from the mobile APP.
[0036] The digital twin self-adaptive optimization module is used to build digital twin models of each workshop equipment and process flow and generate optimized scheduling solutions. The digital twin self-adaptive optimization module updates the twin model parameters using the following error correction formula:
[0037] θ ′ ←θ ′ +α(θ-θ′ )
[0038] Among them, θ is the physical device parameter vector collected in real time, θ ′ is the parameter vector corresponding to the digital twin model, α∈(0,1) is the learning rate, and the formula of the digital twin model is:
[0039]
[0040] Among them, C max is the maximum completion time of all processes, n is the total number of production line equipment, U i ∈[0,1] is the utilization rate of the i-th device, E i is the energy consumption per unit time of the i-th equipment, f1 is the objective mapping function for minimizing the completion time, f2 is the objective mapping function for maximizing the equipment utilization rate, and f3 is the mapping function for minimizing the total energy consumption. The optimal scheduling scheme includes the production process execution sequence based on multi-objective optimization, the equipment resource load distribution scheme and the key process parameter configuration.
[0041] The full-process self-adaptive production method for leather bags based on real-time monitoring of intelligent workshop data includes:
[0042] S1. Interconnect production equipment such as design, cutting, leather scraping, gluing, sewing and packaging through industrial Ethernet, and collect equipment operating status and process parameters in real time.
[0043] S2. Dynamically generate the production process execution sequence based on production orders, material inventory and equipment operating parameters, and send it to each production equipment.
[0044] S3. Each modular unit automatically receives and executes the production process execution sequence through a standardized interface.
[0045] S4. Online monitoring of process parameters and customer-side order progress and quality feedback.
[0046] S5. Build a digital twin model of the workshop based on real-time monitoring data to optimize the production scheduling plan, and iteratively update the optimization results to the process flow intelligent scheduling module.
[0047] Example 2
[0048] This example uses actual production data to illustrate how to optimize production scheduling through real-time monitoring and data feedback.
[0049] Implementation steps:
[0050] Device interconnection and data collection:
[0051] The production equipment of this system includes design equipment, cutting equipment, scraping equipment, glue spraying equipment, sewing equipment and packaging equipment. The equipment is interconnected through industrial Ethernet to collect the operating status data of the equipment in real time. The real-time operating parameters of the equipment include temperature, pressure, speed, current, voltage, power, operating speed and fault status. For example, the temperature of the design equipment is 35℃, the speed is 1500 rpm, the operating speed is 200mm / s, the current is 2A, the voltage is 380V, and the power is 750W. The real-time operating data of the cutting equipment is as follows: Figure 1 shown.
[0052] Production process execution sequence generation:
[0053] Based on real-time production order information, material inventory information, and real-time equipment operating parameters, the process flow intelligent scheduling module generates a production process execution sequence in real time and sends it to the production equipment. For example, when processing a production order for a batch of 500 leather bags, the system generates the following execution sequence based on order requirements and material inventory:
[0054] Design equipment: Sequence 1.
[0055] Cutting device: Sequence 2.
[0056] Glue spraying equipment: sequence 3.
[0057] Sewing equipment: Sequence 4.
[0058] This sequence is adjusted based on real-time feedback, ensuring production stays on schedule.
[0059] Modular process units automatically perform:
[0060] The modular process units automatically receive and execute the above process sequences. Each unit receives production tasks through a standardized interface and automatically executes them according to the preset control strategy. For example, the cutting unit automatically performs precise operations based on cutting parameters to ensure that the cutting size meets the design requirements. The operating data of the cutting unit is shown in Table 1:
[0061] Equipment temperature: 36°C, current: 1.8A, operating speed: 250mm / s.
[0062] Tool pressure: 10MPa, production speed: 300 leather bags / hour.
[0063] Data monitoring and feedback adjustment:
[0064] The data monitoring and feedback module monitors various process parameters in real time, such as stitch uniformity in the sewing unit and glue coating thickness in the gluing unit. The quality monitoring unit uses a convolutional neural network to perform online testing of stitch uniformity to ensure production quality. For example, monitoring data shows that stitch uniformity reaches 98% and the glue coating thickness error is less than 0.5mm, meeting quality requirements. The customer data monitoring unit regularly pulls customer order execution progress, quality feedback, and customized configuration requests from the mobile app.
[0065] Digital twin adaptive optimization:
[0066] Based on real-time data, the digital twin adaptive optimization module builds digital twin models of each workshop equipment and process flow and generates an optimized scheduling plan. The twin model parameters are updated using the following error correction formula:
[0067] New parameters = original parameters + learning rate × (real-time acquisition parameters - model prediction value)
[0068] Assuming the maximum completion time for equipment 1 is 1 hour and the specific energy consumption of equipment 2 is 2 kWh, the equipment utilization and energy consumption are adjusted through an optimization algorithm, ultimately resulting in an optimized production process execution sequence and equipment resource load distribution plan. The system's goals are to minimize production time, maximize equipment utilization, and minimize energy consumption.
[0069] Optimization results and implementation:
[0070] The optimized production process execution sequence, equipment resource load distribution plan, and key process parameter configuration are generated and fed back to the process flow intelligent scheduling module. For example, the optimized scheduling plan shows that an order originally scheduled to take 200 minutes can now be completed in 100 minutes, reducing production energy consumption by 15%. Equipment utilization has increased by 15%, significantly improving production efficiency and resource utilization.
[0071] During implementation, the system's intelligent scheduling and optimization model effectively improved production efficiency and reduced energy consumption and equipment load. Through continuous data monitoring and real-time feedback, the system can quickly respond to any changes in production, ensuring that the production process is always in optimal condition. Key system operation data is shown in Table 1:
[0072] Production order completion time: 100 minutes (before optimization: 200 minutes).
[0073] Total energy consumption: 20kWh (before optimization: 23kWh).
[0074] Equipment utilization rate: 95% (before optimization: 80%).
[0075] Table 1: Production cost table:
[0076]
[0077] In the past few years, production costs have been effectively reduced by improving production efficiency and reducing resource waste.
[0078] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.
Claims
1. A full-process self-adaptive production system for leather bags based on real-time monitoring of intelligent workshop data, characterized by: include: The equipment IoT collaboration module is used to interconnect production equipment through industrial Ethernet and collect real-time operating parameters of the production equipment; A process flow intelligent scheduling module is used to generate a production process execution sequence based on production order information, material inventory information and the real-time operating parameters, and send it to the production equipment; A modular process unit, configured to receive the production process execution sequence through a standardized interface and automatically execute the corresponding process; A data monitoring and feedback module is used to monitor process parameters and customer service data in real time and provide real-time feedback to the process flow intelligent scheduling module. The data monitoring and feedback module includes a quality monitoring unit and a customer data monitoring unit; The digital twin self-adaptive optimization module is used to build digital twin models of various equipment and process flows in the workshop and generate optimized scheduling plans.
2. The full-process self-adaptive production system for leather bags based on real-time monitoring of intelligent workshop data according to claim 1 is characterized by: The production equipment includes design equipment, cutting equipment, peeling equipment, glue spraying equipment, sewing equipment and packaging equipment.
3. The full-process self-adaptive production system for leather bags based on real-time monitoring of intelligent workshop data according to claim 1 is characterized by: The real-time operating parameters include the temperature, pressure, rotation speed, current, voltage, power, operating speed and fault status of the equipment.
4. The leather bag full-process self-adaptive production system based on real-time monitoring of intelligent workshop data according to claim 1 is characterized by: The modular process unit includes a cutting unit, a gluing unit, a sewing unit and a packaging unit, and the cutting unit, gluing unit, sewing unit and packaging unit are all composed of a driver, a sensor, a PLC controller and a standardized bus interface module.
5. The leather bag full-process self-adaptive production system based on real-time monitoring of intelligent workshop data according to claim 1 is characterized by: The quality monitoring unit uses a visual inspection model based on convolutional neural networks to perform online inspection of suture uniformity and glue coating thickness, and the customer data monitoring unit periodically pulls customer order execution progress, quality feedback and customized configuration requirements from the mobile APP.
6. The leather bag full-process self-adaptive production system based on real-time monitoring of intelligent workshop data according to claim 1 is characterized by: The digital twin self-adaptive optimization module updates the twin model parameters through the following error correction formula: i ′ ←θ ′ +α(θ-θ ′ ) Among them, θ is the physical device parameter vector collected in real time, θ ′ is the parameter vector corresponding to the digital twin model, α∈(0,1) is the learning rate, and the formula of the digital twin model is: Among them, C max is the maximum completion time of all processes, n is the total number of equipment in the production line, U i ∈[0,1] is the utilization rate of the i-th device, E i is the energy consumption per unit time of the i-th equipment, f1 is the mapping function for minimizing the completion time objective, f2 is the mapping function for maximizing the equipment utilization objective, and f3 is the mapping function for minimizing the total energy consumption objective.
7. The leather bag full-process self-adaptive production system based on real-time monitoring of intelligent workshop data according to claim 1 is characterized by: The optimization scheduling plan includes a production process execution sequence based on multi-objective optimization, an equipment resource load distribution plan, and a key process parameter configuration.
8. A full-process self-adaptive production method for leather bags based on real-time monitoring of intelligent workshop data, characterized in that: include: S1. Interconnect production equipment such as design, cutting, leather scraping, gluing, sewing, and packaging via industrial Ethernet, and collect equipment operating status and process parameters in real time; S2. Dynamically generate a production process execution sequence based on production orders, material inventory, and the equipment operating parameters, and distribute it to each production equipment; S3. Each modular unit automatically receives and executes the production process execution sequence through a standardized interface; S4. Online monitoring of process parameters and customer-side order progress and quality feedback; S5. Build a workshop digital twin model based on the real-time monitoring data to optimize the production scheduling plan, and iteratively update the optimization results to the process flow intelligent scheduling module.