Method and system for controlling thin film production

Abstract

The present application relates to the technical field of film production, and specifically relates to a film production control method and system, comprising receiving film production work order information; determining a production line node according to the film production work order information; configuring an initial moving path of a tray according to the production line node; constructing a first operation time prediction model of an operating device of the first production line node according to historical operation data, and obtaining a first operation prediction time according to the first operation time prediction model; obtaining a production delay rate of the first production line node according to the first operation prediction time, a moving time and a queuing time; adjusting the initial moving path of the tray according to the production delay rates of all production line nodes to obtain a dynamic moving path; and controlling finished product roll production according to the dynamic moving path. The method and system of the present application guide the movement of finished product rolls based on the dynamic moving path, adapt to changes in production line load, improve production efficiency, and ensure orderly and efficient operation of large-batch and multi-specification production.

Description

Technical Field

[0001] The present invention relates to the technical field of film production, and in particular to a film production control method and system. Background Art

[0002] BOPP (Biaxially Oriented Polypropylene) film, also known as biaxially oriented polypropylene film, is produced through a production line process that includes several key steps, such as slitting, weighing, labeling, and packaging. Automated guided vehicles (AGVs) and assembly lines are used to move finished rolls between different production processes, requiring operators to travel back and forth between stations to assist. To reduce operator involvement, fully automated production lines are gradually emerging, using MES systems for control and scheduling to automate this process. Currently, material movement between BOPP film production processes follows a pre-set, fixed route. While this fixed route simply ensures automated production, it makes the process unresponsive to unexpected changes, equipment failures, or bottlenecks. For example, if equipment in a particular process fails, the production line must halt while the equipment is repaired, preventing timely adjustments to bypass that process or alter the process. This results in low production efficiency and an inability to adapt to changes in production load. Summary of the Invention

[0003] To this end, the technical problem to be solved by the present invention is to overcome the problems in the prior art of guiding the movement of finished material rolls according to a set fixed path during the production of BOPP film, resulting in low production efficiency and inability to adapt to changes in the production line load. A film production control method and system are provided, which guide the movement of finished material rolls based on a dynamic movement path, thereby improving production efficiency while adapting to changes in the production line load. In addition, the dynamic movement path comprehensively considers the operating equipment's own working conditions, equipment load and path status, further optimizes the path, and ensures orderly and efficient operation of large-scale, multi-specification production.

[0004] In a first aspect, in order to solve the above technical problems, the present invention provides a thin film production control method, comprising:

[0005] Determine the production line nodes based on the film production work order information;

[0006] The initial movement path of the pallet is configured according to the production line node; wherein the pallet is used to transport the finished product roll bound to the pallet and move on the film production line;

[0007] Inputting the work order task of the operating equipment of the first production line node into a pre-built first operation time prediction model to obtain a first operation prediction time;

[0008] acquiring a moving time of the finished product roll from a first line node to a second line node; and acquiring a queuing time according to a path state between the first line node and the second line node; wherein the second line node is a next node in a moving direction of the first line node;

[0009] obtaining a production delay rate of the first line node according to the first operation prediction time, the moving time and the queuing time;

[0010] adjusting an initial moving path of the tray according to the production delay rate of all line nodes to obtain a dynamic moving path;

[0011] controlling finished product roll production according to the dynamic moving path.

[0012] In an embodiment of the present application, further comprising,

[0013] measuring a weight of the finished product roll online to obtain a weight measurement value of the finished product roll;

[0014] extracting an order weight of the finished product roll from the film production work order information;

[0015] judging whether a difference between the weight measurement value and the order weight exceeds a weight error range;

[0016] if the difference between the weight measurement value and the order weight exceeds the weight error range, guiding the tray into an NG moving path;

[0017] if the difference between the weight measurement value and the order weight does not exceed the weight error range, adjusting the initial moving path of the tray according to the production delay rate.

[0018] In an embodiment of the present application, configuring an initial moving path of a tray according to the line nodes comprises,

[0019] extracting finished product roll specification data and node attribute parameters from the film production work order information; wherein the node attribute parameters comprise operation specifications of the finished product roll at each line node;

[0020] matching corresponding devices in the film line according to the finished product roll specification data, the line nodes and the node attribute parameters to obtain a plurality of path nodes;

[0021] planning the initial moving path according to the plurality of path nodes.

[0022] In an embodiment of the present application, configuring an initial moving path of a tray according to the line nodes further comprises,

[0023] Obtaining attribute parameters of equipment corresponding to each production line node in the film production line, and obtaining equipment completion indicators based on the attribute parameters of the equipment;

[0024] Calculating a task index based on the finished product roll specification data, production line nodes, and node attribute parameters, matching equipment whose equipment completion index is greater than or equal to the task index in the film production line to obtain a plurality of path nodes;

[0025] Obtaining a set of moving paths according to the plurality of path nodes;

[0026] The moving path set is traversed, and the initial moving path is searched for with the shortest path as the goal.

[0027] In one embodiment of the present invention, constructing a first operation time prediction model includes:

[0028] Obtain the historical operation log table of the film production line;

[0029] Taking the operating device of the first production line node as a search target, traversing the historical operation log table to extract historical record data of the operating device of the first production line node;

[0030] Filtering operation data samples, fault and maintenance record data samples, operation task data samples and operation time samples from the historical record data;

[0031] Construct a neural network model, use the operation data samples, fault and maintenance record data samples and operation task data samples as input data, and use the operation time samples as output data to train the neural network model until the convergence condition is met to obtain the first operation time prediction model.

[0032] In one embodiment of the present invention, a training set and a test set are constructed to train the first operation time prediction model, which includes:

[0033] Step 1: Divide the historical record data into m subsets, and perform sequence identification on the m subsets;

[0034] Step 2: Extract one of the subsets as the test set, combine the remaining m-1 subsets as the training set, and record the performance parameters of the current subset as the test set; and repeat step 2 until each subset is used as the test set once;

[0035] Step 3: Calculate the evaluation result of the first operation time prediction model based on the performance parameters of each of the subsets as the test set.

[0036] In an embodiment of the present application, the production delay rate of the first production line node is obtained according to the first operation prediction time, the moving time and the queuing time, comprising,

[0037] The production delay rate is obtained based on the following manner:

[0038] ; wherein, represents the production delay rate; T1 represents the first operation prediction time; T2 represents the moving time; T3 represents the queuing time; represents a nonlinear function; 、 and respectively represent the weight corresponding to the first operation prediction time, the moving time and the queuing time.

[0039] In an embodiment of the present application, the initial moving path of the tray is adjusted according to the production delay rate of all the production line nodes to obtain a dynamic moving path, comprising,

[0040] The production delay rate of the current first production line node is compared with a production delay rate threshold value;

[0041] If the production delay rate of the current first production line node is less than the production delay rate threshold value, the next production line node is moved to according to the initial moving path;

[0042] If the production delay rate of the current first production line node is greater than or equal to the production delay rate threshold value, the next production line node of the initial moving path is taken as a target production line node, and the first production line node with the minimum production delay rate is taken as a starting production line node, and the dynamic moving path is obtained by moving from the current first production line node to the starting production line node and the target production line node in sequence.

[0043] In an embodiment of the present application, the tray communicates with the film production line based on RFID, and the tray returns the position information of the finished product roll in real time by binding with the finished product roll information; wherein, the tray is unbound with the finished product roll execution information when the tray moves to the last production line node of the film production work order.

[0044] In a second aspect, based on the same inventive concept, the present application also provides a film production control system, comprising,

[0045] a work order receiving module for receiving film production work order information;

[0046] a production line node determining module for determining a production line node according to the film production work order information; wherein, the production line node comprises one or any combination of slitting, weighing, labeling, packaging, buffering and warehousing;

[0047] a pallet path configuration module, configured to configure an initial movement path of a pallet according to the production line node, wherein the pallet is used to bind information with the finished roll obtained by slitting and to transport the finished roll bound thereto on the film production line;

[0048] An operation time prediction module, which is trained based on historical operation data and is used to obtain the predicted operation time of the equipment based on the work order task;

[0049] a path status acquisition module, configured to acquire the travel time of the finished coil from the first production line node to the second production line node; and to acquire the queue time based on the path status between the first production line node and the second production line node; wherein the second production line node is the next node in the direction of travel of the first production line node;

[0050] A production delay rate calculation module, configured to calculate the production delay rate according to the operation prediction time, the movement time, and the queuing time;

[0051] A dynamic path adjustment module, configured to dynamically adjust the initial moving path according to the production delay rate of each production line node;

[0052] A production control module is used to control the production of the finished product roll according to the dynamically adjusted movement path.

[0053] The above technical solution of the present invention has the following beneficial effects compared with the prior art:

[0054] The film production control method and system described in the present invention guide the movement of finished material rolls based on a dynamic movement path, adapting to changes in the load of the BOPP film production line while improving production efficiency; in addition, the dynamic movement path comprehensively considers the operating conditions of the operating equipment itself, the equipment load and the path status, further optimizing the path to ensure the orderly and efficient operation of large-scale, multi-specification production; further, based on historical operation data, the operation prediction time of the corresponding equipment of each production line node is obtained, thereby discovering potential failures of the equipment and further refining the optimization of the movement path, reducing stagnation and delays in the production process, and further improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings, wherein:

[0056] Figure 1 Flowchart of a film production control method in a preferred embodiment of the present invention;

[0057] Figure 2 This is a flow chart of configuring the initial movement path of the pallet according to the production line nodes in a preferred embodiment of the present invention;

[0058] Figure 3 Flow chart for configuring initial moving path of tray according to line node in another embodiment of the present application;

[0059] Figure 4 Flow chart for constructing first operation time prediction model in preferred embodiment of the present application;

[0060] Figure 5 Flow chart for obtaining dynamic moving path in preferred embodiment of the present application;

[0061] Figure 6 Schematic diagram of initial moving path of line node A1 in one of embodiments of the present application;

[0062] Figure 7 Schematic diagram of adjusted moving path of line node A1 shown in the figure; Figure 6

[0063] Figure 8 Module block diagram of thin film production control system in preferred embodiment of the present application. DETAILED DESCRIPTION

[0064] The present application will be further described below in conjunction with the drawings and specific embodiments so that those skilled in the art can better understand and implement the present application, but the embodiments are not intended to limit the present application.

[0065] Embodiment one

[0066] ​The embodiment of the application discloses a film production control method, which is used for scheduling control of a BOPP film (hereinafter referred to as "film") production line. The film production line is configured with an MES system, and at least a slitting station, a weighing station, a labeling station, a packaging station, a buffer station and a storage station are configured according to the production process of the film. The slitting station is provided with a slitting device, the slitting device cuts a mother roll (for example, 30Km long and 8.7m wide) of the film into various finished product rolls (for example, 3Km long and 2m wide) of different specifications, and the finished product rolls are sequentially fed into the subsequent processes including weighing, labeling and packaging by means of an AGV trolley or an assembly line after being wound at the slitting station; the weighing station is provided with a weighing device, the finished product rolls fed into the weighing station are automatically weighed online, and the weighing result is fed back to the MES system in real time; the labeling station is provided with a labeling machine, labels are automatically printed according to order tasks, and the finished product rolls fed into the labeling station are labeled by manual or automatic operation; and the packaging station is provided with a packaging machine, the finished product rolls fed into the packaging station are packaged by the packaging machine. The finished product rolls are bound with pallet information in the circulation process of the film production line. The pallet communicates with the film production line based on RFID, and the pallet feeds back the position information of the finished product rolls in real time by being bound with the information of the finished product rolls. The pallet is unbound with the finished product rolls when moving to the last node of the film production order, so that the finished product rolls can be accurately tracked and managed in the subsequent handling, storage and processing process. Through information binding, the traceability, real-time monitoring, automatic management and other functions of the production link can be realized.

[0067] Of course, the film production line is provided with a plurality of slitting stations, a plurality of weighing stations, a plurality of labeling stations, a plurality of packaging stations, a plurality of buffer stations and a plurality of storage stations according to task requirements. The specifications and execution capabilities of the stations are partially consistent and partially different, and are configured according to order tasks. For example, the specifications of the finished product rolls wound by the slitting machine corresponding to different slitting stations are consistent or different. The specifications and execution capabilities of each station are input into the MES system, thereby providing a data basis for subsequent production scheduling.

[0068] Referring to Figure 1 The film production control method disclosed by the embodiment of the application comprises the following steps:

[0069] S100, receiving film production order information;

[0070] In a specific application scenario, a production order is made according to order information and a production plan, and the production order includes requirements and specific information of each link. The film production order information is one of the core data of production management, including production quantity, production date, production process requirement, raw material requirement, production equipment requirement, quality standard and product inspection requirement, tracking barcode or two-dimensional code, production process parameter, production mode, product specification (including length, width, weight, etc.), label requirement, customer delivery address and packaging requirement, etc. The film production order information is imported into the MES system as the basis for subsequent production control.

[0071] S200, determining a production line node according to the film production order information; wherein the production line node includes one or any combination of slitting, weighing, labeling, packaging, buffering and warehousing;

[0072] In a specific application scenario, the production line node is determined according to the film production order information. For example, according to the requirements of the current film production order, the finished product roll needs to be weighed, labeled and packaged, so that the weighing node, labeling node and packaging node required by the current film production order can be determined. If only the finished product roll needs to be weighed and packaged according to the requirements of the film production order, the weighing node and the packaging node can be determined. The production line node is determined according to the requirements of the customer order.

[0073] S300, configuring an initial movement path of the tray according to the production line node; wherein the tray is used to bind with the finished product roll obtained by slitting, and transport the finished product roll bound with the information on the film production line;

[0074] In a specific application scenario, after the slitting device slits the parent roll to obtain one or more finished product rolls, the finished product rolls are wound into the tray under the slitting station. Based on RFID technology, when the finished product roll is placed on the tray, the binding relationship between the finished product roll and the tray is automatically established. The movement path of the tray is preliminarily planned according to the production line node required by the production order, and the purpose is to load the finished product roll into each production line node in turn.

[0075] S400, constructing a first operation time prediction model of the operation equipment of the first production line node according to historical operation data, wherein the first operation time prediction model obtains a first operation prediction time according to the order task of the operation equipment of the first production line node;

[0076] In a specific application scenario, an operation time prediction model is constructed in advance for each operation device corresponding to all line nodes on the film production line (each line node has at least one operation device), the purpose of the operation time prediction model is to learn the historical operation data of the operation device, obtain the relationship between the operation time and the device operation data, the number of fault and maintenance records and the operation task data, apply the qualified operation time prediction model to the actual production line, and obtain the operation time of the operation device to complete the work order task according to the current work order task. The first line node is any one line node on the film production line, and the first operation time prediction model is the operation time prediction model of a device corresponding to any one line node.

[0077] S500, obtaining a moving time of the finished product roll from the first line node to the second line node; and obtaining a queuing time according to a path state between the first line node and the second line node; wherein the second line node is the next node in the moving direction of the first line node;

[0078] In a specific application scenario, the moving time is obtained according to the distance between the first line node and the second line node and the moving speed of the tray, and the queuing time is obtained according to the path state between the first line node and the second line node, for example, if there is no tray queuing between the first line node and the second line node, the queuing time is zero; if there is one tray queuing between the first line node and the second line node, the remaining time of the current device of the second line node to execute the current work order is the queuing time.

[0079] S600, obtaining a production delay rate of the first line node according to the first operation prediction time, the moving time and the queuing time;

[0080] In a specific application scenario, the line node delay is defined as the relationship between the actual time difference and the expected time difference of the finished product roll from entering a line node to entering the next line node, if the actual time difference is greater than the expected time difference, the current line node has line node delay; if the actual time difference is less than or equal to the expected time difference, the current line node has no line node delay. The production delay rate of the line node is defined as a quantitative index related to the operation prediction time, the moving time and the queuing time, and the production delay rate of the line node can directly and clearly indicate the execution of the work order task of each line node.

[0081] S700, adjusting the initial moving path of the tray according to the production delay rate of all the line nodes to obtain a dynamic moving path;

[0082] S800, controlling the production of the finished product roll according to the dynamic moving path.

[0083] The film production control method described in the present invention guides the movement of finished material rolls based on a dynamic movement path, adapting to changes in the load of the film production line while improving production efficiency; in addition, the dynamic movement path comprehensively considers the operating conditions of the operating equipment itself, the equipment load and the path status, further optimizing the path to ensure the orderly and efficient operation of large-scale, multi-specification production; further, based on historical operation data, the operation prediction time of the corresponding equipment of each production line node is obtained, thereby discovering potential failures of the equipment and further refining the optimization of the movement path, reducing stagnation and delays in the production process, and further improving production efficiency.

[0084] In other implementation plans of the embodiments of the present invention, it also includes measuring the weight of the finished material roll online to obtain the weight measurement value of the finished material roll; extracting the order weight of the finished material roll from the film production work order information; judging whether the difference between the weight measurement value and the order weight exceeds the weight error range; if the difference between the weight measurement value and the order weight exceeds the weight error range, guiding the pallet into the NG movement path; if the difference between the weight measurement value and the order weight does not exceed the weight error range, adjusting the initial movement path of the pallet according to the production delay rate.

[0085] In specific application scenarios, the weight of the finished coil is a key and important quality control indicator for production quality. The system calculates the theoretical weight of the finished coil based on the previous feeding and the specifications of the finished coil. This theoretical weight is determined based on the order weight. If the difference between the measured weight and the order weight exceeds the weight error range, the production quality of the finished coil is unqualified and it will be judged as an NG product and prohibited from leaving the factory. By setting up online weight detection, unqualified products can be eliminated as soon as possible, and only qualified products will be transferred through in-factory logistics. In addition, when a large number of unqualified products are detected, the process parameters of the previous process are adjusted through quality feedback.

[0086] Specifically, refer to Figure 2 As shown, the initial moving path of the pallet is configured according to the production line node, including extracting finished material roll specification data and node attribute parameters from the film production work order information; matching corresponding equipment in the film production line according to the finished material roll specification data, the production line node and the node attribute parameters to obtain several path nodes; and planning the initial moving path according to the several path nodes.

[0087] In specific application scenarios, the specification data of the finished material roll includes length, width and weight, etc.; the node attribute parameters include the operating specifications of the finished material roll at each of the production line nodes; for example, for different batches of finished material rolls, the labeling positions are different, and the operating specifications of the equipment at the corresponding labeling stations are different, which means that the production line node positions that can complete the labeling operation are different. Specifically, in one of the application scenarios, according to the production work order requirements, the production line nodes include weighing, labeling and packaging. There are three weighing stations, five labeling stations and six packaging stations that can complete the production work order requirements. The above three weighing stations, five labeling stations and six packaging stations constitute path nodes, and the initial moving path is planned based on these path nodes.

[0088] Further, refer to Figure 3 As shown, the initial moving path of the pallet is configured according to the production line node, and also includes obtaining the attribute parameters of the equipment corresponding to each production line node in the film production line, and obtaining the equipment completion index according to the attribute parameters of the equipment; calculating the task index according to the finished material roll specification data, production line nodes and node attribute parameters, matching the equipment whose equipment completion index is greater than or equal to the task index in the film production line, and obtaining a plurality of the path nodes; obtaining a moving path set according to the plurality of path nodes; traversing the moving path set, and searching for the shortest path as the target to obtain the initial moving path.

[0089] In a specific application scenario, the attribute parameter of the device should be understood as the specification that the device can operate, for example, the weighing range of a weighing device is 20 Kg, 50 Kg, 100 Kg and 300 Kg, and the attribute parameter of the weighing device is the weighing range of the weighing device. For another example, the packaging specifications of a packaging machine are 2m*1m (2m corresponds to the width of the finished product roll, 1m corresponds to the diameter of the finished product roll), 4m*1m, 4m*1.5m, etc. The device completion index should be understood as the operation specification supported by the device, for example, the weighing device with a weighing range of 300 Kg can be compatible with all operation specifications, and the device completion index is large; and the weighing range of 20 Kg only supports weighing the finished product roll with a weight of 20 Kg or less, and the device completion index is small. The task index should be understood as the device configuration required according to the production order, for example, if the weight of the finished product roll in the production order is 70 Kg, the device completion index of the weighing device with a weighing range of 20 Kg and 50 Kg is less than the task index, and the device completion index of the weighing device with a weighing range of 100 Kg and 300 Kg is greater than the task index. All devices with a device completion index greater than or equal to the task index are screened, and the station where the device is located constitutes a path node, and all stations where the devices are located constitute a plurality of path nodes; a mobile path set is obtained according to the plurality of path nodes; the mobile path set is traversed to obtain the initial mobile path as the target of the shortest path. By screening the path node, it is ensured that all devices constituting the path node have load capacity, and the initial mobile path is planned in the path node meeting the load capacity as the target of the shortest path, so that the production order is stably and reliably performed.

[0090] Referring to Figure 4 As shown in the first operation time prediction model of the operation device of the first production line node is constructed according to historical running data, including obtaining a historical running log table of the film production line; traversing the historical running log table to extract historical record data of the operation device of the first production line node with the operation device of the first production line node as a retrieval target; screening running data samples, fault and maintenance record data samples, operation task data samples and operation time samples from the historical record data; constructing a neural network model, taking the running data samples, the fault and maintenance record data samples and the operation task data samples as input data, and taking the operation time samples as output data to train the neural network model until a convergence condition is met to obtain the first operation time prediction model.

[0091] In specific application scenarios, historical equipment operation data includes equipment ID and type, operating status data (including equipment operating time, downtime, load, efficiency, etc.), equipment wear (such as equipment usage frequency, operating hours, service life, etc.), task characteristics (such as work order type, operation content, complexity, etc.), and equipment maintenance and repair records (equipment maintenance history, downtime, repair records, etc.). Fault and repair records include fault type (such as electrical faults, mechanical faults), fault frequency (including the frequency of each fault and the time between faults), repair time, and performance changes after the fault is repaired. Operation task data includes task complexity, material characteristics (including material type, specifications, weight, etc.), and environmental conditions (such as temperature, humidity, etc.). Features related to equipment operation time, such as equipment wear, fault type, and operating load, are extracted from the raw data. Feature engineering is used to generate input features that serve as input to the operation time prediction model.

[0092] The first production line node is any production line node on the thin film production line, and the first operation time prediction model is the operation time prediction model for a piece of equipment corresponding to any production line node. The first operation time prediction model should be understood as a neural network architecture constructed using a neural network base model. The neural network base model is trained using historical data. During training, the neural network model is trained using operating data samples, fault and maintenance record data samples, and operation task data samples. The neural network model is trained using operation time samples as output data. The model parameters are continuously optimized during training until convergence is met. The neural network base model that has been trained and verified as qualified is the first operation time prediction model. After obtaining the first operation time prediction model, operating data, fault and maintenance records, and operation tasks are input into the first operation time prediction model to obtain the equipment's operating time. The inclusion of fault and maintenance record data as model input allows the model to better understand the equipment's historical operation and failure patterns, identify potential equipment failure risks, and predict possible equipment failures in advance. Ultimately, by introducing the production line node delay rate to assess delays caused by potential failures, the model can dynamically adjust the movement path in a more refined manner, reducing delays and transition waits caused by irrational production scheduling and improving overall production efficiency.

[0093] Furthermore, a training set and a test set are constructed to train the first operation time prediction model, which includes: step 1: dividing the historical record data into m subsets, and sequence-marking the m subsets; step 2: extracting one of the subsets as the test set, and combining the remaining m-1 subsets as the training set, recording the performance parameters of the current subset as the test set; and repeating step 2 until each of the subsets is used as the test set once; step 3: calculating the evaluation result of the first operation time prediction model based on the performance parameters of each of the subsets as the test set.

[0094] In specific application scenarios, historical data is divided into multiple subsets, each of which is used as a test set. Historical data can be fully utilized for model training and evaluation. By using different subsets as test sets, the generalization ability of the model can be verified, that is, whether the model has good predictive ability for data in different time periods or situations, and the risk of model overfitting can be reduced. Because each subset is used as a test set, the model will not rely too much on a specific data set during training. Finally, the average or weighted average of the performance parameters of each subset as a test set is calculated to obtain a comprehensive evaluation result of the model on the entire historical data, thereby comprehensively evaluating the performance of the model.

[0095] Further, obtaining a production delay rate of the first production line node according to the first operation prediction time, the movement time, and the queuing time includes obtaining the production delay rate based on the following method:

[0096] ;in, represents the production delay rate; T1 represents the first operation prediction time; T2 represents the movement time; T3 represents the queue time; represents a nonlinear function; 、 and They represent the weights corresponding to the first operation prediction time, movement time and queuing time respectively.

[0097] In specific application scenarios, the production delay rate of a production line node is related to the operation time of the equipment, the movement time of the pallet, and the queuing time. A nonlinear weighting method is introduced to quantify the operation time, movement time, and queuing time into a production delay rate. Nonlinear functions include exponential functions, logarithmic functions, etc., which are used to simulate the interaction between various factors in the actual production environment, so that the change in the production delay rate has nonlinear characteristics, which can more accurately reflect the dynamic changes in production delays. In the embodiment of the present invention, the weights are obtained according to the nonlinear weighting method. 、 and Obtaining production delay rate , nonlinear weighted method is also called composite model method, weight 、 and The weight allocation can be based on model performance, or based on the training data coverage or diversity of the model, or based on a Bayesian method of weight allocation, etc. Of course, it can also be initially set according to industry regulations or expert experience, and then adjusted based on adaptive weights.

[0098] Further, as shown in Figure 5 , the initial movement path of the tray is adjusted according to the production delay rate of all the line nodes, and obtaining a dynamic movement path includes comparing the production delay rate of the current first line node with a production delay rate threshold; if the production delay rate of the current first line node is less than the production delay rate threshold, moving to the next line node according to the initial movement path; if the production delay rate of the current first line node is greater than or equal to the production delay rate threshold, taking the next line node of the initial movement path as a target line node, and taking the first line node with the smallest production delay rate as a starting line node, moving from the current first line node to the starting line node and the target line node to obtain the dynamic movement path.

[0099] In a specific application scenario, if the production delay rate of the current first line node is less than the production delay rate threshold, the next line node is moved according to the initial movement path. It needs to be explained here that the production delay rate threshold is pre-set, and is pre-set according to the actual production needs or order demand. If the production delay rate of the current first line node is less than the production delay rate threshold, it means that the production delay rate of the current first line node is allowed, or in other words, it is acceptable according to the order demand, and the initial movement path is not adjusted to avoid frequent adjustment of the movement path and cause efficiency to be reduced. If the production delay rate of the current first line node is greater than or equal to the production delay rate threshold, it means that the production delay rate of the current first line node is not allowed, triggering the movement path adjustment. The adjustment strategy includes: taking the next line node of the initial movement path as a target line node, and taking the first line node with the smallest production delay rate as a starting line node, moving from the current first line node to the starting line node and the target line node to obtain the dynamic movement path. In a specific application scenario, as shown in Figure 6 and Figure 7As shown, the current first production line node is a weighing node, and the weighing node has at least three (A1, A2, A3; wherein A1 is the current weighing node), according to the initial moving path, the next production line node is a labeling node B, and the production delay rate of the A1 node is greater than or equal to the production delay rate threshold, then the production delay rate of the A2 node is less than that of the A3 node, so the A1 node is moved to the A2 node first and then to the node B, and thus, the dynamic moving path from the A1 node to the B node is formed.

[0100] According to the production delay rate of each production line node, the moving path is optimized, the combined optimal path with the minimum delay and the shortest moving path is obtained, and the production efficiency is greatly improved.

[0101] Embodiment Two

[0102] Based on the same inventive concept, referring to Figure 8 As shown, the film production control system provided by the embodiment of the application comprises,

[0103] a work order receiving module configured to receive film production work order information;

[0104] a production line node determining module configured to determine a production line node according to the film production work order information; wherein the production line node comprises one or any combination of slitting, weighing, labeling, packaging, caching and warehousing;

[0105] a tray path configuration module configured to configure an initial moving path of a tray according to the production line node, wherein the tray is used to bind with the finished product roll information obtained by slitting, and the finished product roll bound with the information is transported to move on the film production line;

[0106] an operation time prediction module configured to be trained according to historical operation data, and used to obtain the operation prediction time of the equipment according to the work order task;

[0107] a path state acquisition module configured to acquire the moving time of the finished product roll from a first production line node to a second production line node, and acquire the queuing time according to the path state between the first production line node and the second production line node; wherein the second production line node is the next node in the moving direction of the first production line node;

[0108] a production delay rate calculation module configured to calculate the production delay rate according to the operation prediction time, the moving time and the queuing time;

[0109] a dynamic path adjustment module configured to dynamically adjust the initial moving path according to the production delay rate of each production line node;

[0110] A production control module is used to control the production of the finished product roll according to the dynamically adjusted movement path.

[0111] The thin film production control system described in the embodiment of the present invention is used to execute the above-mentioned thin film production control method and has the same technical effect.

[0112] In summary, the film production control method and system described in the present invention guide the movement of finished material rolls based on a dynamic movement path, adapting to the load changes of the BOPP film production line while improving production efficiency; in addition, the dynamic movement path comprehensively considers the operating equipment's own operating conditions, equipment load and path status, further optimizing the path to ensure the orderly and efficient operation of large-scale, multi-specification production; further, based on historical operation data, the operation prediction time of the corresponding equipment of each production line node is obtained, so as to discover potential failures of the equipment and further refine the optimization of the movement path, reduce stagnation and delays in the production process, and further improve production efficiency.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0117] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A film production control method, characterized in that: include, Determine the production line nodes based on the film production work order information; The initial movement path of the pallet is configured according to the production line node; wherein the pallet is used to transport the finished product roll bound to the pallet and move on the film production line; Inputting the work order task of the operating equipment of the first production line node into a pre-built first operation time prediction model to obtain a first operation prediction time; Obtaining the travel time of the finished coil from the first production line node to the second production line node; and obtaining the queuing time based on the path status between the first production line node and the second production line node; wherein the second production line node is the next node in the moving direction of the first production line node; Obtaining a production delay rate of a first production line node according to the first operation prediction time, the movement time, and the queuing time; Adjusting the initial movement path of the pallet according to the production delay rate of all production line nodes to obtain a dynamic movement path; Controlling the production of finished coils according to the dynamic movement path; Constructing the first operation time prediction model includes: constructing a neural network model, using equipment operation data samples, fault and maintenance record data samples, and operation task data samples as input data, and using operation time samples as output data to train the neural network model until the convergence conditions are met to obtain the first operation time prediction model.

2. The thin film production control method according to claim 1, characterized in that: Also includes, measuring the weight of the finished material roll online to obtain a weight measurement value of the finished material roll; Extracting the order weight of the finished roll from the film production work order information; Determine whether the difference between the weight measurement value and the order weight exceeds a weight error range: if so, guide the pallet into an NG movement path; if not, adjust the initial movement path of the pallet according to the production delay rate.

3. The thin film production control method according to claim 1, characterized in that: The initial movement path of the pallet is configured according to the production line node, including: Extracting finished product roll specification data and node attribute parameters from the film production work order information; wherein the node attribute parameters include the operation specifications of the finished product roll at each of the production line nodes; Matching corresponding equipment in the film production line according to the finished product roll specification data, the production line nodes, and the node attribute parameters to obtain a plurality of path nodes; The initial moving path is planned according to the plurality of path nodes.

4. The film production control method according to claim 1 or 3, characterized in that: Configuring the initial movement path of the pallet according to the production line node also includes: Obtaining attribute parameters of equipment corresponding to each production line node in the film production line, and obtaining equipment completion indicators based on the attribute parameters of the equipment; Calculating a task index based on the finished product roll specification data, production line nodes, and node attribute parameters, matching equipment whose equipment completion index is greater than or equal to the task index in the film production line to obtain a plurality of path nodes; Obtaining a set of moving paths according to the plurality of path nodes; The moving path set is traversed, and the initial moving path is searched for with the shortest path as the goal.

5. The thin film production control method according to claim 1, characterized in that: Constructing a first operation time prediction model, including, Obtain the historical operation log table of the film production line; Taking the operating device of the first production line node as a search target, traversing the historical operation log table to extract historical record data of the operating device of the first production line node; Operation data samples, fault and maintenance record data samples, operation task data samples and operation time samples are filtered from the historical record data.

6. The thin film production control method according to claim 5, characterized in that: Constructing a training set and a test set to train the first operation time prediction model, which includes: Step 1: Divide the historical record data into m subsets, and perform sequence identification on the m subsets; Step 2: Extract one of the subsets as the test set, combine the remaining m-1 subsets as the training set, and record the performance parameters of the current subset as the test set; and repeat step 2 until each subset is used as the test set once; Step 3: Calculate the evaluation result of the first operation time prediction model based on the performance parameters of each of the subsets as the test set.

7. The thin film production control method according to claim 1, characterized in that: Obtaining the production delay rate of the first production line node according to the first operation prediction time, the movement time, and the queuing time includes: The production delay rate is obtained based on the following method: ； in, represents the production delay rate; T1 represents the first operation prediction time; T2 represents the movement time; T3 represents the queue time; represents a nonlinear function; 、 and They represent the weights corresponding to the first operation prediction time, movement time and queuing time respectively.

8. The film production control method according to claim 1 or 7, characterized in that: Adjusting the initial movement path of the pallet according to the production delay rate of all the production line nodes to obtain a dynamic movement path, including: comparing the production delay rate of the current first production line node with a production delay rate threshold; If the production delay rate of the current first production line node is less than the production delay rate threshold, move to the next production line node according to the initial moving path; If the production delay rate of the current first production line node is greater than or equal to the production delay rate threshold, the next production line node of the initial moving path is taken as the target production line node, and the first production line node with the smallest production delay rate is taken as the starting production line node. The dynamic moving path is obtained by moving from the current first production line node to the starting production line node and the target production line node in sequence.

9. The thin film production control method according to claim 1, characterized in that: The pallet communicates with the film production line based on RFID, and the pallet transmits the location information of the finished material roll in real time by binding with the finished material roll information; wherein, when the pallet moves to the last production line node of the film production work order, the information is unbound from the finished material roll execution.

10. A film production control system, used to execute the film production control method according to any one of claims 1 to 9, characterized in that: include, Production line node determination module, which determines the production line node based on the film production work order information; a pallet path configuration module, configured to configure an initial movement path of a pallet according to the production line node, wherein the pallet is used to transport a finished product roll bound to the pallet to move on the film production line; The operation time prediction module is trained based on historical operation data and is used to obtain the predicted operation time of the equipment based on the work order task; a path status acquisition module for acquiring the travel time of the finished coil from the first production line node to the second production line node; and acquiring the queue time based on the path status between the first production line node and the second production line node; wherein the second production line node is the next node in the direction of movement of the first production line node; a production delay rate calculation module, which calculates the production delay rate according to the operation prediction time, the movement time and the queue time; A dynamic path adjustment module dynamically adjusts the initial moving path according to the production delay rate of all production line nodes; The production control module controls the production of the finished product roll according to the dynamically adjusted moving path.

Images