Packaging workshop production line intelligent management system and method based on big data

Abstract

The invention discloses a packaging workshop production line intelligent management system and method based on big data, and relates to the technical field of packaging workshop production management, and the system comprises an Internet of Things data collection module, a big data analysis module, a dynamic production scheduling module, a real-time control module, and a man-machine interaction module. Multi-dimensional data of equipment states, order demands and material inventory are captured in real time through the Internet of Things data acquisition module, and deep analysis is performed through the big data analysis module, so that the dynamic production scheduling module can respond to changes of production elements in real time, and equipment failure rate prediction and order delivery cycle prediction results are fully fused; a production scheduling scheme considering efficiency, cost and delivery reliability is accurately generated, the matching relation between orders and equipment is dynamically adjusted through real-time data, idle and overload operation of the equipment are avoided, optimal configuration of materials, the equipment and human resources is achieved, and the adaptability of a production system to complex and changeable production environments is greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of packaging workshop production management, and specifically to an intelligent management system and method for a packaging workshop production line based on big data. Background Art

[0002] At a time when industrial automation and informatization are deeply integrated, packaging workshops, as a key link in product production, have a decisive impact on the company's production efficiency, cost control, and market competitiveness through their intelligent management level. Faced with a rapidly changing market environment, packaging workshops need to cope with challenges such as frequent changes in orders, increased equipment complexity, and fluctuations in material supply. Traditional production management models lack flexibility and real-time performance, making it difficult to meet the needs of efficient and flexible production. Innovative intelligent management systems and methods have become an urgent need in the industry.

[0003] However, existing technologies have significant defects. At the dynamic production scheduling level, they are mostly based on static plans and cannot respond to dynamic events such as order changes and equipment failures in real time, which can easily lead to production delays and efficiency losses. In terms of resource allocation, due to the lack of comprehensive analysis of real-time data such as equipment status and material inventory, equipment is often idle or materials are wasted. In addition, the real-time monitoring capability is weak, making it difficult to detect production anomalies in a timely manner. Quality problems occur frequently, and it is unable to provide strong support for decision-making, which seriously restricts the optimization space of the production process.

[0004] In summary, the existing packaging workshop production management system has obvious shortcomings in dynamic adaptation and efficient resource utilization. Developing an intelligent management system and method that combines the Internet of Things and real-time control technology and uses big data to achieve dynamic production scheduling and optimal resource allocation has become a core breakthrough for improving the production management level of packaging workshops. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a big data-based intelligent management system and method for packaging workshop production lines. It can obtain full-factor data such as equipment status, order requirements, and material inventory in real time through the Internet of Things data acquisition module. After deep mining by the big data analysis module, the dynamic production scheduling module integrates multi-objective optimization to generate a scientific production scheduling plan. This process can quickly adjust the production schedule according to real-time changes, greatly improving production efficiency. At the same time, based on accurate resource demand prediction and allocation, it avoids equipment idleness and excessive material consumption, thereby reducing production costs.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, an intelligent management system for a packaging workshop production line based on big data, the system comprises: an Internet of Things data acquisition module, a big data analysis module, a dynamic production scheduling module, a real-time control module, and a human-computer interaction module;

[0007] The IoT data acquisition module is used to collect real-time operating data on equipment status, production progress, material inventory, and environmental parameters in the packaging workshop, and transmit it to the big data analysis module via wireless communication;

[0008] The big data analysis module is used to clean, store, and pre-process the collected data, and predict equipment failure rates and order delivery cycles;

[0009] The dynamic production scheduling module is used to generate an initial production scheduling plan based on the real-time information of basic production data and the prediction results provided by the big data analysis module, and optimize the initial production scheduling plan to obtain the final production scheduling plan;

[0010] The real-time control module is used to send the optimized final production scheduling plan to the production equipment and the execution mechanism, synchronously monitor the execution status of the equipment, and dynamically adjust the final production scheduling plan according to actual production needs;

[0011] The human-computer interaction module is used to provide a visual operation interface, which is convenient for production management personnel to view production data, production scheduling plans, and equipment status information in real time, and to manually adjust and intervene in the production scheduling plans.

[0012] Furthermore, the IoT data acquisition module includes an equipment status acquisition unit, a production progress acquisition unit, a material inventory acquisition unit, and an environmental parameter acquisition unit;

[0013] The equipment status acquisition unit is composed of a vibration sensor, a current sensor, and a temperature sensor deployed on the production equipment, and is used to collect equipment operating vibration frequency, motor operating current, and component temperature data in real time;

[0014] The production progress collection unit includes a photoelectric counter and an industrial visual camera installed on the production line, which is used to collect order completion quantity, real-time count and packaging appearance image data;

[0015] The material inventory collection unit consists of a warehouse area RFID reader and shelf weight sensor, using RFID electronic tags to collect inventory quantity, storage location and material flow data of raw materials, semi-finished products and finished products;

[0016] The environmental parameter collection unit includes temperature and humidity sensors, dust concentration sensors and gas detectors distributed in the workshop, which are used to collect temperature and humidity, dust particle concentration and volatile organic compound content data in the production area.

[0017] Furthermore, the big data analysis module includes a data processing unit, a data storage unit, and a production scheduling forecasting unit;

[0018] The data processing unit performs cleaning, denoising, missing value filling and abnormal data elimination on the collected heterogeneous data;

[0019] The data storage unit adopts a distributed storage architecture to divide the database into a real-time database and a historical database, wherein the real-time data is stored in the real-time database in a time series format, and the historical data is stored in the historical database according to production batches;

[0020] The production scheduling prediction unit performs equipment failure rate prediction and order delivery cycle prediction, and integrates a discrete event simulation engine to generate a production scheduling prediction solution.

[0021] Furthermore, the equipment failure rate prediction in the production scheduling forecast unit is based on the equipment's historical operation data and real-time operation data, and adopts a multi-parameter weighted risk index algorithm to capture the historical dependence of the equipment status. By comprehensively considering the equipment's real-time status parameters, performance degradation trends, and historical failure records, the predicted value of the equipment failure rate is calculated. ,in, Is the device at time The predicted failure rate, is the number of state parameters, performance parameters, and historical fault parameters, Is the device The standardized value of the state parameter, is the state parameter The importance weight and initial =0.8, is the degradation coefficient of the mth performance parameter of the equipment, that is, the ratio of the designed capacity to the current capacity, is the weight coefficient, satisfying ,default value , Is the performance parameter The influence coefficient of =0.6, is the influence coefficient of the pth historical fault of the equipment and =0.5, is the time decay factor of the pth historical fault of the equipment and , It is The number of historical occurrences of this type of fault, It is The last time a fault occurred and the default value is 0.01. is a decay exponential and =1.5.

[0022] Furthermore, the order delivery cycle prediction in the production scheduling forecast unit is based on the basic production time, and by introducing correction factors such as resource constraints and equipment risks, an algorithm for associating external factors with the delivery cycle is established. ,in is the order forecast lead time, is the basic production time and , is the quantity of product u in the order, is the standard production time of product u, M is the number of available equipment, H is the effective working hours, is the overall equipment efficiency and is initially 0.85, is the resource shortage coefficient of type a, that is, the ratio of demand quantity to inventory quantity, is the resource shortage impact weight and initially =0.6, is the bth equipment failure risk factor, taken from the equipment failure rate prediction results , is the impact weight of equipment failure and the initial =0.4, and the actual order delivery cycle is predicted through this cross-linking algorithm.

[0023] Furthermore, the dynamic production scheduling module includes an initial production scheduling unit and a production scheduling optimization unit;

[0024] The initial production scheduling unit is based on the basic production data of production cost, processing time, total number of available equipment and total number of orders, combined with the predicted equipment failure rate. and order delivery cycle , build an initial production schedule with risk constraints ,Right now Indicates order Assign to device , otherwise it is 0, and the risk constraint is: ,in, is the total number of orders currently to be scheduled, M is the total number of available equipment, is the standard production cost of order i on equipment j, is the equipment failure risk cost coefficient and the default value is 0.3, is the customer-required lead time for order i, is the lead time deviation penalty coefficient and the default value is 0.5, It is a device The predicted failure rate during the production schedule, is the predicted lead time for order i.

[0025] Furthermore, the production scheduling optimization unit uses the real-time information of order demand, equipment status, material inventory, and production progress to optimize the initial production scheduling plan. Optimize and get the final production schedule ,in, is the longest order delay time, is the average equipment utilization rate, is the total energy consumption cost, and the optimization conditions are specifically as follows: ,in, is the actual completion time of order i on device j, is the scheduled delivery time of order i, M is the total number of available devices, is the utilization rate of device j and , is the processing time of order i on equipment j, is the planned working time of equipment j, is the unit energy cost coefficient of device j and its default value is 0.5, is the expected energy consumption of equipment j during the production scheduling cycle.

[0026] On the other hand, a method for intelligent management of a packaging workshop production line based on big data is provided, wherein the specific steps of the method are as follows:

[0027] S100, using the IoT data collection module to collect data on equipment status, production progress, material inventory, and environmental parameters in the packaging workshop in real time;

[0028] S200: Conduct in-depth analysis of the collected data to predict equipment failure rates and order delivery cycles;

[0029] S300: Generate an initial production schedule based on real-time information on order demand, equipment status, material inventory, and production progress, combined with the forecast results provided by S200, and optimize the initial production schedule to obtain a final production schedule.

[0030] S400: Send the final production schedule to the production equipment and execution mechanism to achieve real-time control of the production process, monitor the equipment's operating status and production progress in real time, and dynamically adjust the production schedule based on actual conditions;

[0031] S500, through the visual operation interface, real-time viewing of production data, production schedule, equipment status information, manual adjustment and intervention of the production schedule.

[0032] Compared with the existing technology, this intelligent management system and method for packaging workshop production line based on big data has the following beneficial effects:

[0033] 1. The present invention uses the Internet of Things data acquisition module to capture multi-dimensional data on equipment status, order requirements, and material inventory in real time, and deeply analyzes it through the big data analysis module, so that the dynamic production scheduling module can respond to changes in production factors in real time, fully integrate the equipment failure rate prediction and order delivery cycle prediction results, and accurately generate a production scheduling plan that takes into account efficiency, cost, and delivery reliability. It also dynamically adjusts the matching relationship between orders and equipment based on real-time data to avoid equipment idleness and overload operation, achieve the optimal configuration of materials, equipment, and human resources, and greatly improve the production system's adaptability to complex and changing production environments, reduce the risk of production delays and resource waste from the source, and ensure the efficient and orderly operation of the production process.

[0034] 2. The real-time control module of the present invention is closely linked to the dynamic production scheduling module to implement full-time monitoring of the operating status and production progress of production equipment. Combined with the equipment failure prediction of the big data analysis module, maintenance is planned in advance to reduce unplanned downtime. At the same time, the human-computer interaction module provides a visual decision-making interface. Managers can accurately adjust the production scheduling strategy based on real-time data and system optimization suggestions, effectively ensure the stability of the production process, and improve the consistency of product quality.

[0035] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0037] Figure 1 This is an operational flow chart of an intelligent management system for a packaging workshop production line based on big data;

[0038] Figure 2 This is a composition diagram of an intelligent management system for packaging workshop production lines based on big data. DETAILED DESCRIPTION

[0039] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0040] Example 1

[0041] This embodiment focuses on the intelligent management of the packaging workshop production line and elaborates on the working principle of an intelligent management system based on big data. Figure 2 As shown in the figure, the system integrates multiple modules of IoT data collection, big data analysis, dynamic scheduling, real-time control and human-computer interaction. Through collaborative work, it realizes comprehensive optimization of the production process and improves the production efficiency of the packaging workshop.

[0042] In the packaging workshop, the Internet of Things data acquisition module is used to obtain real-time information on the production site. It is coordinated by the equipment status acquisition unit, the production progress acquisition unit, the material inventory acquisition unit and the environmental parameter acquisition unit. Among them, the equipment status acquisition unit deploys vibration sensors, current sensors and temperature sensors on various production equipment. The vibration sensor monitors the vibration frequency of the equipment in real time during operation, the current sensor obtains the working current of the motor, and the temperature sensor measures the temperature of the component. These sensors convert the collected analog signals into digital signals and transmit them to the big data analysis module wirelessly; the production progress acquisition unit is installed at key nodes of the production line, such as the location where the product is assembled and packaged. The photoelectric counter accurately counts the number of completed orders by detecting the pulse signal generated by the light blocked when the product passes through. The industrial vision camera uses image processing technology to monitor the appearance of the packaging in real time and identify information such as the printing quality, label sticking status, and product integrity on the packaging. The material inventory acquisition unit is in the warehouse area with the help of RFID readers, shelf weight sensors and RFID electronic Tags enable precise management of material inventory. Each raw material, semi-finished product and finished product is affixed with a unique RFID electronic tag to store its detailed information. The RFID reader scans the tag regularly to obtain the inventory quantity and storage location information of the material. The shelf weight sensor monitors the weight changes of the shelf to grasp the increase and decrease of materials in real time, and thus accurately track the material flow path; the environmental parameter collection unit evenly distributes temperature and humidity sensors, dust concentration sensors and gas detectors in the workshop. The temperature and humidity sensors monitor the temperature and humidity changes in the production area in real time to ensure that the production environment meets the process requirements and avoids the impact of temperature and humidity on product quality or equipment performance. The dust concentration sensor detects the concentration of dust particles in the air to prevent dust accumulation from causing safety accidents or affecting product accuracy. The gas detector is used to monitor the content of volatile organic compounds to protect employee health and production environment safety. The real-time collection of these environmental parameter data helps to maintain a stable production environment and improve product quality and production safety. The collected operating data such as equipment status, production progress, material inventory and environmental parameters are transmitted to the big data analysis module via wireless communication.

[0043] The big data analysis module receives data from the Internet of Things data acquisition module, and includes a data processing unit, a data storage unit and a production scheduling forecast unit, wherein the data processing unit cleans, denoises, fills missing values ​​and removes abnormal data for the collected heterogeneous data; the data storage unit adopts a distributed storage architecture, and divides the database into a real-time database and a historical database. The real-time database stores the latest collected data in a time series format to ensure the timeliness of the data and facilitate real-time monitoring and analysis of the production process. The historical database stores historical data by production batch, providing rich historical information for data analysis and mining; the production scheduling forecast unit predicts the equipment failure rate and order delivery cycle, and generates a production scheduling forecast plan. For the equipment failure rate prediction, the equipment historical operation data and real-time operation data are used to apply a multi-parameter weighted risk index algorithm to calculate the predicted value of the equipment failure rate. ,in, Indicates the time at which the device The predicted failure rate takes into account the real-time status parameters, performance degradation trend and historical failure records of the equipment. n, m and p are the number of status parameters, performance parameters and historical failure parameters respectively. It is the standardized value of the nth state parameter of the device, which is obtained by normalizing the original state parameter to make it comparable. is the state parameter The importance weight of the state parameter reflects the influence of the state parameter on the equipment failure rate, and the initial =0.8, It is the degradation coefficient of the mth performance parameter of the equipment, which is calculated by the ratio of the design capacity to the current capacity, and reflects the changing trend of the equipment performance; Is the performance parameter The influence coefficient is used to measure the impact of this performance parameter on the equipment failure rate. 、 、 is the weight coefficient, satisfying , the default value is 、 、 , which determine the relative importance of different types of parameters in predicting equipment failure rates, is the time attenuation factor of the kth historical fault of the equipment, and the calculation formula is , is the historical number of occurrences of the k-th fault, is the last occurrence time of the k-th fault, is the attenuation coefficient, the default value is 0.01, is the attenuation index, with a default value of 1.5. According to this formula, recent failures have a greater impact on the current failure rate prediction, while the impact of historical failures gradually weakens over time. For the order delivery cycle prediction, based on the basic production time, resource constraints and equipment risk correction factors are introduced to establish an association algorithm to predict the order delivery cycle. The basic production time ,in, is the quantity of product u in the order, is the standard production time of product u, M is the number of available equipment, H is the effective working hours, It is the overall equipment efficiency, order forecast delivery cycle , is the resource shortage coefficient of type a, which is calculated by the ratio of demand quantity to inventory quantity, reflecting the degree of resource shortage. is the resource shortage impact weight, initially set to 0.6, which is used to measure the impact of resource shortage on delivery cycle. is the bth equipment failure risk factor, taken from the equipment failure rate prediction results , It is the weight of equipment failure impact, initially set to 0.4, reflecting the degree of impact of equipment failure on delivery cycle. The algorithm comprehensively considers multiple factors such as order product quantity, production hours, available equipment, equipment efficiency, resource shortage and equipment failure to more accurately predict the actual delivery cycle of orders. The production scheduling forecast unit outputs the equipment failure rate prediction and order delivery cycle prediction results to the dynamic production scheduling module to provide a reference for subsequent dynamic production scheduling.

[0044] The dynamic production scheduling module generates and optimizes the production scheduling plan based on the real-time information of order demand, equipment status, material inventory, and production progress, combined with the prediction results provided by the big data analysis module. It mainly includes the initial production scheduling unit and the production scheduling optimization unit. Among them, the initial production scheduling unit is based on basic production data such as production cost, processing time, total number of available equipment and total number of orders, while taking into account the predicted equipment failure rate. and order delivery cycle , build an initial production schedule with risk constraints , is a binary decision variable, Indicates that order i is assigned to device j, otherwise it is 0. The risk constraint is , where N is the total number of orders currently to be scheduled, and M is the total number of available equipment. is the standard production cost of order i on equipment j, including raw material cost, energy cost, labor cost, etc. The default value is 0.3, which is used to convert the risk of equipment failure into a cost factor. When the equipment failure rate is high, the cost of allocating orders to the equipment increases, thereby guiding the system to reduce the allocation of orders to high-risk equipment. is the predicted failure rate of equipment j during the production scheduling cycle, is the customer-required lead time for order i, It is the delivery cycle deviation penalty coefficient, with a default value of 0.5. It is used to penalize the deviation between the order delivery cycle and the customer's required delivery cycle, prompting the system to give priority to orders with tight delivery cycles. By solving this optimization problem with risk constraints, the initial production scheduling plan is obtained and the matching relationship between orders and equipment is preliminarily determined. The production scheduling optimization unit uses the real-time information of order demand, equipment status, material inventory, and production progress to optimize the initial production scheduling plan through optimization conditions. Optimize and get the final production schedule , the optimization conditions include minimizing the longest order delay time , maximize average equipment utilization and minimize total energy costs , among which, the longest order delay time It's an order The actual completion time on device j, is the scheduled delivery time of order i, by minimizing , ensure that the longest delay time is as short as possible in all orders, improve the on-time delivery of orders and the average equipment utilization rate ,in , is the processing time of order i on equipment j, is the planned working time of equipment j. Maximize , can improve the overall utilization efficiency of equipment, reduce equipment idle time, reduce production costs, and total energy consumption costs is the unit energy cost coefficient of device j, the default value is 0.5, is the expected energy consumption of equipment j during the production schedule, by minimizing , reduce the energy consumption cost in the production process, the production scheduling optimization unit searches for the optimal production scheduling plan F under the condition of satisfying the production constraints, so that 、 、 The three goals achieve comprehensive optimization.

[0045] The real-time control module sends the optimized final production scheduling plan to the production equipment and the executive mechanism to achieve real-time control of the production process, and synchronously monitors the execution status of the equipment, and dynamically adjusts the final production scheduling plan according to actual production needs. Specifically, the final production scheduling plan is converted into a specific control instruction and sent to the controller of the production equipment. The controller controls the start, stop, operating speed, processing parameters, etc. of the equipment according to the instruction, and collects the operating status data of the equipment in real time through sensors, such as the actual operating speed, temperature, pressure, etc. of the equipment, and compares it with the preset normal operating parameters. Once the equipment operating status is found to be abnormal, an alarm is immediately issued and the abnormal information is fed back to the system. At the same time, the production progress collection unit is used The data is used to monitor the production progress in real time and determine whether the production tasks are completed on time according to the production schedule. When abnormal situations such as equipment failure, material shortage, order change, etc. occur, the real-time control module dynamically adjusts the production schedule according to the actual situation. For example, if a device fails, the orders on the device will be reallocated to other available devices based on the equipment failure rate prediction results and repair time, and the production sequence will be adjusted. If there is a material shortage, the production plan will be reasonably adjusted according to the data of the material inventory collection unit and the material replenishment time, giving priority to the production of orders that are not in urgent need of materials, or suspending some production lines to wait for material replenishment. The adjusted production schedule will be sent to the production equipment and execution agency again to ensure the continuity and stability of the production process.

[0046] The human-computer interaction module provides a visual operation interface for production management personnel, which is convenient for real-time viewing of production data, production scheduling, equipment status and other information, and manual adjustment and intervention of production scheduling. Production data, production scheduling and equipment status are intuitively displayed in the form of charts. For example, a bar chart is used to display the production progress of each order on different equipment. Production management personnel can clearly see the start time, expected completion time and actual completion status of each order. The operating status parameters of the equipment, such as temperature, pressure, speed, etc., as well as key indicators such as production efficiency and product quality, are displayed in real time through the dashboard. Production management personnel can manually adjust the production scheduling on the human-computer interaction interface according to the actual production situation. For example, when it is found that the delivery time of an order is advanced, the management personnel can The production sequence of the order can be manually adjusted on the interface to prioritize production, or when the equipment needs emergency maintenance, the manager can manually reallocate the order on the equipment to other equipment. At the same time, the system will update the production scheduling plan in real time according to the manager's adjustment operation, and send the adjusted plan to the real-time control module for execution. The human-computer interaction module also provides decision support functions, and provides optimization suggestions for production managers based on the analysis results of production data and production scheduling plans. For example, when the system detects that the equipment utilization rate is low, it will prompt the manager whether to adjust the order allocation to improve equipment utilization. When it finds that the order is delayed, it will provide corresponding solutions, such as adjusting the production sequence of other orders, increasing equipment resources, etc., to help managers make more scientific decisions.

[0047] To sum up, this embodiment demonstrates in detail the actual operation process of the intelligent management system of the packaging workshop production line based on big data. The Internet of Things data acquisition module obtains production site data in real time and comprehensively. The big data analysis module deeply processes and predicts the data to provide strong support for dynamic production scheduling. The dynamic production scheduling module generates and optimizes the production scheduling plan based on multiple factors. The real-time control module ensures the accurate execution and dynamic adjustment of the production scheduling plan. The human-computer interaction module provides convenient operation and decision-making support for production management personnel. The modules work closely together to realize the intelligent management of the packaging workshop production line, effectively improve production efficiency, reduce equipment idleness and material waste, reduce production costs, and at the same time ensure product quality and improve the timeliness of order delivery.

[0048] Example 2

[0049] like Figure 1 As shown, based on Example 1, this example describes in detail the specific steps of a packaging workshop production line intelligent management system based on big data in performing intelligent management of the production line. The specific steps are:

[0050] Equipment status monitoring: Vibration sensors, current sensors, and temperature sensors deployed on production equipment collect equipment operating parameters in real time;

[0051] Production progress tracking: Install photoelectric counters and industrial vision cameras to count the number of completed orders;

[0052] Material inventory management: Attach RFID electronic tags to raw materials, semi-finished products, and finished products, and use RFID readers and shelf weight sensors in the warehouse area to monitor material inventory quantity, storage location, and circulation path in real time;

[0053] Environmental parameter monitoring: Temperature and humidity sensors, dust concentration sensors, and gas detectors are distributed throughout the workshop to collect production environment data in real time;

[0054] Data cleaning and preprocessing: Clean the collected heterogeneous data (equipment status, production progress, material inventory, environmental parameters), remove noise, fill missing values, and eliminate abnormal data;

[0055] Data storage and classification: Using a distributed storage architecture, real-time data is stored in a time series database, and historical data is stored in a historical database by production batch;

[0056] Equipment failure prediction: Based on historical equipment operating data and real-time parameters, the equipment failure rate is evaluated through a multi-parameter weighted algorithm, focusing on equipment status parameters, performance degradation trends, and historical failure records;

[0057] Order delivery cycle forecast: This forecast combines factors such as order quantity, production hours, available equipment, equipment efficiency, resource shortages, and equipment failure risks to predict the actual order delivery cycle.

[0058] Initial production scheduling plan generation: Considering factors such as production costs, equipment failure rates, and order delivery cycles, orders are allocated to the optimal equipment combination to generate an initial production scheduling plan;

[0059] Production scheduling optimization: Iteratively optimize the initial production scheduling plan with the goal of minimizing order delays, maximizing equipment utilization, and minimizing energy costs;

[0060] Considering the real-time status of equipment and changes in order priorities, dynamically adjust production sequence and equipment allocation.

[0061] Production scheduling execution: Convert the optimized production scheduling plan into control instructions and send them to the controller of the production equipment to control the equipment startup and adjust the operating parameters;

[0062] Real-time production monitoring: Sensors collect real-time data on equipment operating status and production progress, compare it with the production schedule, and monitor for deviations.

[0063] Exception handling and dynamic adjustment: When equipment failure, material shortage or order change is detected, the production schedule is regenerated based on real-time data.

[0064] Data visualization: Graphically display key indicators such as production progress, equipment status, and material inventory;

[0065] Manual intervention and adjustment: Production management personnel can manually adjust the production schedule according to actual conditions, and the system will update and execute the adjusted plan in real time;

[0066] Decision support and optimization suggestions: The system provides optimization suggestions based on data analysis to assist managers in making decisions.

[0067] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent management system for packaging workshop production line based on big data, characterized in that: The system consists of: Internet of Things data acquisition module, big data analysis module, dynamic production scheduling module, real-time control module, and human-computer interaction module; The IoT data acquisition module is used to collect real-time operating data on equipment status, production progress, material inventory, and environmental parameters in the packaging workshop, and transmit it to the big data analysis module via wireless communication; The big data analysis module is used to clean, store, and pre-process the collected data, and predict equipment failure rates and order delivery cycles; The dynamic production scheduling module is used to generate an initial production scheduling plan based on the real-time information of basic production data and the prediction results provided by the big data analysis module, and optimize the initial production scheduling plan to obtain the final production scheduling plan; The real-time control module is used to send the optimized final production scheduling plan to the production equipment and the execution mechanism, synchronously monitor the execution status of the equipment, and dynamically adjust the final production scheduling plan according to actual production needs; The human-computer interaction module is used to provide a visual operation interface, which is convenient for production management personnel to view production data, production scheduling plans, and equipment status information in real time, and to manually adjust and intervene in the production scheduling plans.

2. The intelligent management system for packaging workshop production line based on big data according to claim 1 is characterized in that: The Internet of Things data acquisition module includes an equipment status acquisition unit, a production progress acquisition unit, a material inventory acquisition unit, and an environmental parameter acquisition unit; The equipment status acquisition unit is composed of a vibration sensor, a current sensor, and a temperature sensor deployed on the production equipment, and is used to collect equipment operating vibration frequency, motor operating current, and component temperature data in real time; The production progress collection unit includes a photoelectric counter and an industrial visual camera installed on the production line, which is used to collect order completion quantity, real-time count and packaging appearance image data; The material inventory collection unit consists of a warehouse area RFID reader and shelf weight sensor, using RFID electronic tags to collect inventory quantity, storage location and material flow data of raw materials, semi-finished products and finished products; The environmental parameter collection unit includes temperature and humidity sensors, dust concentration sensors and gas detectors distributed in the workshop, which are used to collect temperature and humidity, dust particle concentration and volatile organic compound content data in the production area.

3. The intelligent management system for packaging workshop production line based on big data according to claim 1 is characterized in that: The big data analysis module includes a data processing unit, a data storage unit, and a production scheduling forecasting unit; The data processing unit performs cleaning, denoising, missing value filling and abnormal data elimination on the collected heterogeneous data; The data storage unit adopts a distributed storage architecture to divide the database into a real-time database and a historical database, wherein the real-time data is stored in the real-time database in a time series format, and the historical data is stored in the historical database according to production batches; The production scheduling prediction unit performs equipment failure rate prediction and order delivery cycle prediction based on the data stored in the data storage unit.

4. The intelligent management system for packaging workshop production line based on big data according to claim 3 is characterized in that: The equipment failure rate prediction in the production scheduling prediction unit is based on the equipment's historical operation data and real-time operation data. It uses a multi-parameter weighted risk index algorithm to capture the historical dependence of the equipment status. By comprehensively considering the equipment's real-time status parameters, performance degradation trends, and historical failure records, the predicted value of the equipment failure rate is calculated. ,in, Is the device at time The predicted failure rate, is the number of state parameters, performance parameters, and historical fault parameters, Is the device The standardized value of the state parameter, is the state parameter The importance weight and initial =0.8, is the degradation coefficient of the mth performance parameter of the equipment, that is, the ratio of the designed capacity to the current capacity, is the weight coefficient, satisfying ,default value , Is the performance parameter The influence coefficient of =0.6, is the influence coefficient of the pth historical fault of the equipment and =0.5, is the time decay factor of the pth historical fault of the equipment and , It is The number of historical occurrences of this type of fault, It is The last time a fault occurred and the default value is 0.

01. is a decay exponential and =1.

5.

5. The intelligent management system for packaging workshop production line based on big data according to claim 3 is characterized in that: The order delivery cycle prediction in the production scheduling forecast unit is based on the basic production time. By introducing correction factors of resource constraints and equipment risks, an algorithm is established to associate external factors with the delivery cycle. ,in is the order forecast lead time, is the basic production time and , is the quantity of product u in the order, is the standard production time of product u, M is the number of available equipment, H is the effective working hours, is the overall equipment efficiency and is initially 0.85, is the resource shortage coefficient of type a, that is, the ratio of demand quantity to inventory quantity, is the resource shortage impact weight and initially =0.6, is the bth equipment failure risk factor, taken from the equipment failure rate prediction results , is the impact weight of equipment failure and the initial =0.4, and the actual order delivery cycle is predicted through this cross-linking algorithm.

6. The intelligent management system for packaging workshop production line based on big data according to claim 1, characterized in that: The dynamic production scheduling module includes an initial production scheduling unit and a production scheduling optimization unit; The initial production scheduling unit is based on the basic production data of production cost, processing time, total number of available equipment and total number of orders, combined with the predicted equipment failure rate. and order delivery cycle , build an initial production schedule with risk constraints ,Right now Indicates order Assign to device , otherwise it is 0, and the risk constraint is: ,in, is the total number of orders currently to be scheduled, M is the total number of available equipment, is the standard production cost of order i on equipment j, is the equipment failure risk cost coefficient and the default value is 0.3, is the customer-required lead time for order i, is the lead time deviation penalty coefficient and the default value is 0.5, It is a device The predicted failure rate during the production schedule, is the predicted lead time for order i.

7. The intelligent management system for packaging workshop production line based on big data according to claim 6 is characterized in that: The production scheduling optimization unit uses the real-time information of order demand, equipment status, material inventory, and production progress to optimize the initial production scheduling plan. Optimize and get the final production schedule ,in, is the longest order delay time, is the average equipment utilization rate, is the total energy consumption cost, and the optimization conditions are specifically: ,in, is the actual completion time of order i on device j, is the scheduled delivery time of order i, M is the total number of available devices, is the utilization rate of device j and , is the processing time of order i on equipment j, is the planned working time of equipment j, is the unit energy cost coefficient of device j and its default value is 0.5, is the expected energy consumption of equipment j during the production scheduling cycle.

8. A packaging workshop production line intelligent management method based on big data, applicable to the packaging workshop production line intelligent management system based on big data according to any one of claims 1 to 7, characterized in that: The specific steps of this method are: S100, using the IoT data collection module to collect data on equipment status, production progress, material inventory, and environmental parameters in the packaging workshop in real time; S200: Conduct in-depth analysis of the collected data to predict equipment failure rates and order delivery cycles; S300: Generate an initial production schedule based on real-time information on order demand, equipment status, material inventory, and production progress, combined with the forecast results provided by S200, and optimize the initial production schedule to obtain a final production schedule. S400: Send the final production schedule to the production equipment and execution mechanism to achieve real-time control of the production process, monitor the equipment's operating status and production progress in real time, and dynamically adjust the production schedule based on actual conditions; S500, through the visual operation interface, real-time viewing of production data, production schedule, equipment status information, manual adjustment and intervention of the production schedule.

Images