Method and system for optimizing product sequencing in a machine line

Abstract

Embodiments of the invention relate to a method and a system for optimizing product sequencing in a machine line, in particular in a machine line for filling and packaging food and / or beverages. According to the invention: a formal system model is generated for the machine line, said formal system model describing cause-effect relationships between data, energy, and / or material streams; the formal system model is input together with backlog data and boundary conditions into an artificial intelligence (AI) system; the AI system defines a solution space with a plurality of product sequencing possibilities for processing orders contained in the backlog data; the solution space is then searched for an optimized product sequencing on the basis of the boundary conditions and / or on the basis of an optimization preference; and at least one product sequencing plan or the cause of the failure of the plan calculation is output together with possible corresponding actions for a corrective process.

Description

[0001] Method and system for optimizing product sequencing in a machine line

[0002] The invention relates to a method and a system for optimizing product sequencing in a machine line, in particular in a machine line for filling and packaging food and / or beverages.

[0003] Currently, software solutions exist for machine lines used to manufacture, package, and fill various products, which are used to plan each system on a customer-specific basis. Production sequencing, i.e., the creation of a production order sequence, is traditionally based on the planners' empirical knowledge. Currently, there is no service functionality available that enables the domain knowledge of a machine line manufacturer to be used for optimization for its customers as a digital service product. The planning quality therefore depends on the customer's personnel.

[0004] Currently, software solutions are used to plan each plant on a customer-specific basis. This approach is time-consuming and costly, as it requires individual customization for each customer. Furthermore, there is a risk of inconsistencies, as each solution is developed and implemented differently. Since production sequencing is traditionally based on the planners' experiential knowledge, this approach is error-prone and unsystematic, as it depends on the individual skills and experience of each planner. Furthermore, it is difficult to train new staff in this area of ​​expertise, further limiting efficiency.

[0005] Due to the lack of a service functionality that enables a machine line manufacturer's domain knowledge to be used for optimization for its customers as a digital service product, a gap exists in the value chain, as manufacturers with current systems are not optimally positioned to provide customers with continuous support and improvements in product sequencing.

[0006] The disadvantages described above result in weaknesses in the planning and control of machine lines for production in terms of efficiency, flexibility, quality and reliability.

[0007] There is therefore a need for improved methods and systems for optimizing product sequencing in a machine line. The present invention aims to overcome these disadvantages by flexibly creating and appropriately applying different strategies depending on the plant configuration and customer preference for machine line behavior, instead of manually creating and specifying them. This aims to improve existing technology, which can increase the efficiency of machine lines while reducing costs.

[0008] The object is achieved according to the invention by a method according to claim 1 and a system according to claim 8. Embodiments and further developments are covered in the subclaims.

[0009] One embodiment of the invention relates to a method for optimizing product sequencing in a machine line, in particular in a machine line for filling and packaging food and / or beverages. The method comprises creating a formal system model for the machine line. The formal system model describes, as required, causal relationships between data, energy, and / or material flows. According to further embodiments, the formal system model can be a semantic and formal extension of a digital design model of the machine line. Furthermore, the formal model can describe dependencies to and between operating states, geometries, materials, processes, functions, customer requirements, and / or optimization goals. The method further comprises inputting the formal system model, together with order backlog data and boundary conditions, to an artificial intelligence (AI) system.The AI ​​system then creates a solution space with a multitude of possible product sequencing options for processing orders contained in the order backlog data. The solution space is then searched for an optimized product sequencing based on the constraints and / or an optimization preference, and a product sequencing plan is output.

[0010] The constraints can include customer preferences and / or planning specifications, such as minimum changeover times, maximum OEE, minimum energy consumption, minimum media consumption (cleaning agents, acids, bases, etc.), delivery capability for specific products, planning period, partial specifications in the production program, product-specific scheduling rules, etc. The causal relationships and dependencies can be formalized in the form of a product changeover matrix. Spanning the solution space can involve creating all possible courses of action for product sequencing using a grounder and generating a variable-free logic program as the result of the spanning. Searching the solution space for an optimized product sequencing can be done by a solver searching the variable-free logic program to determine the optimized plan based on the constraints and / or the optimization preference.

[0011] One embodiment of the invention relates to a corresponding system for dynamically creating instructions for operator-guided changeover of a machine line.

[0012] Exemplary aspects of the invention are illustrated in the drawings. They show:

[0013] Figure 1 : a flowchart showing the steps of a method according to the

[0014] invention shows;

[0015] Figure 2: an exemplary plant configuration for PET containers and

[0016] adhesive packaging;

[0017] Figure 3: an exemplary plant configuration for PET containers and

[0018] shrink packer;

[0019] Figure 4: an exemplary system configuration for cans or glass bottles; and

[0020] Figure 5: an example system configuration for cans.

[0021] Embodiments of the invention relate to the optimization of production planning and sequencing in a machine line, such as a beverage bottling plant. For example, a bottling plant may have a number of different orders, each relating to different products (e.g., different beverages for different containers). The aim is to provide a system that creates optimal production planning and creates an optimal sequence of production orders based on constraints and practical information of the machine line. For example, a common preference may be that products with a high sugar content are filled after products with less sugar have been filled first, since the opposite would require greater cleaning effort.The aim of the invention is to derive various strategies, depending on the plant configuration and customer preference for the plant behavior, from formal system models in the form of an expert system in a flexible and automatic manner and to apply them appropriately, instead of creating and specifying them manually as is usual in the prior art.

[0022] The automatic derivation of the plant behavior can be carried out on the basis of a formally logically and semantically extended digital design model of the machine line, which is available in machine-readable form and is passed on to the machines / plants as a knowledge model.

[0023] The semantic and formal extensions can make the causal relationships of data, energy, and material flows available for use in artificial intelligence. Furthermore, they can describe the dependencies to and between operating states, geometries, materials, processes, functions, customer requirements, and / or optimization goals, if applicable. The structural causal relationships can be formalized in the form of product change matrices.

[0024] For the technical implementation and the required provision of the infrastructure, a cloud service can be used on which the calculations are carried out.

[0025] For example, if a customer wants to have the optimization potential in production sequencing during product changeover for their machine line(s) or any system network (e.g. logistics systems + BPE system) for a defined production period (e.g. 1-5 days, 1-4 weeks, 1-2 months, etc.) optimally demonstrated and implemented in production through a flexibly usable service depending on customer-specific preferences, the cloud service can be used via a corresponding user interface.

[0026] According to some embodiments, the formal system model can be used to optimize production processes and sequencing. Instead of creating the optimization potential for each machine line, taking different preferences into account, through explicit customer-specific programming, embodiments of the invention are capable of automatically generating a formal system model of the machine line and / or the individual components, which can be derived, for example, based on the formal product change matrices.

[0027] To optimize the plant production sequence, this system model, including current order backlog data from an Enterprise Resource Planning (ERP) system, customer preferences (e.g., minimum changeover times, maximum OEE, delivery capability for specific products, etc.), and the planning specifications (planning period, partial specifications in the production program, product-specific scheduling rules), can be translated into a declarative logic language, which can be processed as a query by a knowledge-based artificial intelligence (AI) system (hereinafter also referred to as an expert system). The AI ​​system / expert system can contain its own internal declarative formal logic knowledge model regarding the meaning of the query and the transmitted system relationships. To determine the optimal response to the query using the formal system model and the AI ​​system, the following procedure can be used:

[0028] A user can enter planning data for production sequencing into an electronic system, such as a processing unit, via a user interface. The planning data can include order backlog data and / or other constraints, such as customer preferences. The user interface can be a graphical user interface through which the user can transmit the data to the cloud service. The AI ​​system can have appropriate interfaces to the ERP system to support this. After the relevant order backlog data, for example from the ERP, customer preferences, and planning specifications have been fully entered / selected, the AI ​​system can generate a solution space.

[0029] The solution space for possible actions can be spanned automatically, i.e., for example, taking into account all relevant order backlog data from the ERP, customer preferences, planning specifications and the internal declarative formal logical knowledge model of the expert system, all possible options for action can be founded by a so-called grounder.

[0030] In this step, a variable-free logic program can be generated. If propagation is necessary, this can be executed in other system modules in parallel, sequentially, or as part of the grounding process.

[0031] The solution space created in this way can then be searched for an optimization preference. For example, a solver can search the variable-free logic program to determine the optimal plan based on the preferences. The optimal plan can be identified, for example, using a quality measure, such as a threshold value for one or more parameters. In addition, it is possible to generate plans for different preference profiles (e.g., OEE-optimal as the default, Alternative 1: energy and media optimal, Alternative 2: inventory optimal, etc.) for comparison in the user interface. For example, a user can also give the AI ​​system a specific time for the optimization search, and the AI ​​system outputs the optimum of the search found within this time as the solution.

[0032] The optimal solution found, or the created plan(s), can then be displayed to the user. In the following, the invention refers to one plan that is determined and displayed to the user, but this should not exclude the possibility of finding, determining, and / or displaying a plurality of plans. This can be done, for example, via the user interface. The user can then compare the output plans, accepting one of them, or rejecting it. In the first case, the behavior plan output by the solver is back-translated so that it is suitable for plant / system control. The translated plan can then be implemented and executed directly by the user's machine line.

[0033] It may also happen that the user does not accept the output plan, e.g., due to incorrect input or because the user has new preferences and revises the input for a new plan. In this case, the process can be started again from the beginning.

[0034] By connecting the machines / plants online with the Kl system in the cloud or installing the Kl system at the plant level at the user's site, the optimization of plant production sequences can be implemented automatically.

[0035] The embodiments described herein offer several advantages over previous practice. For example, machine line users do not require experts for the production sequencing of their systems, as the machine line manufacturers can provide this expertise as a service to users.

[0036] The AI ​​system for controlling plant behavior can be regularly improved and updated online without interrupting production, with the aim of generating functional upgrades without additional effort, since manual configuration / programming adjustments are no longer required on site.

[0037] Figure 1 shows an exemplary flowchart illustrating a method 100 according to embodiments of the invention.

[0038] The method 100 for optimizing product sequencing in a machine line begins with step S102, in which a formal system model for the machine line is created. The formal system model describes causal relationships between data, energy, and / or material flows and can also be a semantic and formal extension of a digital design model of the machine line, which further describes dependencies to and between operating states, geometries, materials, processes, functions, customer requirements, and / or optimization goals.

[0039] In step S104, data is entered into an AI system. The data may include the formal system model if the AI ​​system does not already have one. The data may also include order backlog data and constraints, such as customer preferences and / or planning specifications.

[0040] In step S106, the AI ​​system creates a solution space with a multitude of possible product sequencings for processing the orders contained in the order backlog data. Creating the solution space can include creating all possible actions for product sequencing using a grounder and generating a variable-free logic program as the result of the creation.

[0041] In step S108, the solution space is searched for an optimized product sequencing based on the constraints and / or based on an optimization preference, before a determined optimal plan is output to the user in step S110. Alternatively, the computing unit can output violated relationships for problem resolution if no valid product sequencing, and thus no plan, is found in the solution space. The violated relationships can then be output to a user for further analysis via the user interface. The user can flexibly relax previously hard-to-fulfill planning rules for problem analysis. For example, the user can specify that as many products as possible should be planned instead of planning all.This enables a systematically supported solution to the planning problem by calculating and comparing different scenarios, allowing the user to make an input adjustment that then leads to one or more valid plans.

[0042] The user can decide in step S112 whether the output product sequencing plan should be accepted or not.

[0043] If the user accepts the plan, the process proceeds to step S114, and the plan output by the solver can be implemented in the plant. The plan can then be back-translated so that it is suitable for plant / system control. The translated plan can then be directly implemented and executed by the user's machine line. If the user does not accept the output plan, the process returns to step S104.

[0044] The following Figures 2 to 5 describe various exemplary system configurations for different bottling plants in which the invention, or at least parts and aspects of the invention, can be implemented. The description of Figures 2 to 5 is intended only to provide a general overview of machines for which status data can be collected, on the basis of which the expert system can process user queries.

[0045] Figure 2 shows an exemplary system configuration 1000 for PET bottles or PET containers and adhesive packs. As shown in Figure 2, the system configuration 1000 comprises various modules that form a line, at the end of which finished PET containers are dispensed in the form of a pack on pallets. Some of the modules and machines may be optional, and the invention is not limited to the exact form and arrangement of the system configurations.

[0046] The system configuration 1000 comprises an oven 1002 for preforms, a preform sorter with a feeding machine 1004, and a blow molding machine 1008. The modules 1002, 1004, and 1008 generally form a stretch blow molding machine in which PET containers are produced and formed from a starting material. The produced PET containers are forwarded to a filler 1010, where the bottles are filled. The filler can optionally include a rinser. Various particles such as dust, cardboard, or remnants of wooden pallets can settle in the preforms during storage or transport. These can be removed with the rinser. A closer can be arranged at the end of the filler, by means of which the PET containers are closed after filling.

[0047] Optionally, the system configuration 1000 can include a rotating device downstream of the filler 1010, which is used for hot filling of the PET containers. Via one or more conveyor belts 1016, which can also include a buffer 1018 for intermediate loading of filled containers, the filled PET containers are conveyed to a separator 1020 and then to a drying device 1024, in which the PET containers are dried.

[0048] After drying, the PET containers are conveyed to a labeling machine 1026. The labeling machine 1026 can be designed for various labeling techniques, such as labeling using hot melt, cold melt, self-adhesive labels, or sleeves. After the PET containers have been printed or labeled, they are conveyed through a second drying device 1028, a line distributor 1030, conveyor belts 1032, an adhesive pack production line 1034, and a curing section to a handle applicator. In the adhesive pack production line 1034, the PET containers are grouped into specific group sizes and packaged into a pack, such as a "six-pack." In the handle applicator, a carrying handle is attached to the pack, which allows for comfortable carrying of the pack.The finished containers are then arranged accordingly by a robot 1042 for layer production and packed on pallets by a palletizer 1044.

[0049] In system configuration 1000, so-called format trolleys or format racks can be arranged on various modules and machines to provide quickly interchangeable format sets for short changeover times and automatic tool changes. Examples of format trolleys are format trolley 1006 for blow molding machine 1008, format trolley 1012 for filler 1010, format trolley 1022 for labeling machine 1026, format trolley 1038 for adhesive pack production 1034, and format trolley 1046 for palletizer 1044.

[0050] Figure 3 shows another example system configuration 1100 for PET containers and shrink packers. System 1100 in Figure 3 includes many of the modules and machines from system configuration 1000 in Figure 2, but there are some differences. Therefore, the description of the modules already described in connection with Figure 2 is omitted for Figure 3.

[0051] A key difference between the two exemplary system configurations 1000 and 1100 is that the labeling machine 1126 with the labeling modules 1127 can be installed downstream of the blow molding machine 1008 and upstream of the filler 1008. For this purpose, the system configuration 1100 can comprise six transport lanes 1150 into which the PET containers can be pushed. After the PET containers have pushed into one of the six lanes 1150, they are conveyed into the film wrapping module 1152 and then into the shrink tunnel 1154.

[0052] Figure 4 shows an exemplary system configuration 1200 for cans or glass bottles. The exemplary system configuration 1200 from Figure 4 again has some similarities to the system configurations 1000 and 1100 from Figures 2 and 3 and the description of the system configuration is therefore limited to the differences between the system configurations. As shown in Figure 4, the exemplary system configuration can comprise two separate feeds. A first feed, on the left in Figure 4, shows a branch for cans or optionally a partial branch for new reusable bottles. The containers, i.e. cans or new bottles, are fed into the machine by a depalletizer 1302, where they are guided via conveyor belts to the filler 1010. A second feed, on the right in Figure 4, shows a partial branch for reusable bottles, which are fed into the system from a reusable sorting system (not shown).

[0053] In the case that the already used reusable bottles are introduced into the system 1200 via the sub-branch for reusable bottles, the reusable bottles first pass through the cleaning machine or washing machine 1304. Another possible difference in the exemplary system configuration 1200 is the transfer packer 1306 after the labeling machine 1026. The transfer packer can sort the bottles or cans into a carton clip application or into crates, or both.

[0054] Figure 5 shows an exemplary system configuration 1300 for cans, in which the elements already described in the other system configurations are no longer described. The cans in system configuration 1300 are fed into the depalletizer 1302 from a magazine 1402 containing cans. After passing through the filler and being filled, the cans are closed by means of a closure magazine 1404 and transported further along the system 1400 via the conveyor belts, as described above.

[0055] The optional Pasteurizer 1408 can be bypassed via the Bypass 1412 if not required. Freshly filled products can be pasteurized in the Pasteurizer 1408 for preservation.

[0056] In contrast to plant configurations 1000, 1100, and 1200, the exemplary plant configuration 1300 shows various tanks for corresponding consumables, such as tanks 1410 with rinsing liquid and / or the filling product and tanks 1406 with belt lubricant. These tanks can also be included in the exemplary plant configurations described above. For example, the chemical products 106 that are fed from the mixer 110 to the machines can be stored in tanks 1406 and 1410.

Claims

CLAIMS 1. A method for optimizing product sequencing in a machine line, in particular in a machine line for filling and packaging food and / or beverages, or in several machine lines or in system networks comprising logistics systems, the method comprising: Creating (S102) a formal system model for the machine line or the multiple machine lines or the system networks, wherein the formal system model describes causal relationships of data, energy and / or material flows; Inputting (S104) the formal system model together with order backlog data and boundary conditions to an artificial intelligence (AI) system; Spanning (S106), by the Kl system, a solution space with a multitude of possible product sequencings for processing orders contained in the order backlog data; Searching (S108) the solution space for an optimized product sequencing based on the constraints and / or based on an optimization preference; and Output (S110) a product sequencing plan.

2. The method according to claim 1, wherein the formal system model is a semantic and formal extension of a digital design model of the machine line or the plurality of machine lines or the system networks and further describes dependencies to and between operating states, geometries, materials, processes, functions, customer requirements and / or optimization objectives.

3. Method according to claim 1 or 2, wherein the boundary conditions comprise customer preferences and / or planning specifications.

4. Method according to one of claims 1 to 3, wherein the causal relationships and dependencies are formalized in the form of at least one product change matrix.

5. The method according to any one of claims 1 to 4, wherein the spanning of the solution space comprises: Creating all product sequencing options by a Grounder; Generating a variable-free logic program as a result of the spanning.

6. The method of claim 5, wherein searching the solution space for an optimized product sequencing comprises: Searching, by a solver, the variable-free logic program to determine the optimized plan based on the constraints and / or based on the optimization preference.

7. System for optimising product sequencing in a machine line, in particular in a machine line for filling and packaging food and / or beverages or in several machine lines or in system networks comprising logistics systems, wherein the system comprises: a computing unit with a user interface, wherein the computing unit is adapted to: Creating (S102) a formal system model for the machine line, whereby the formal system model describes causal relationships between data, energy and / or material flows; Inputting (S104) the formal system model together with order backlog data and boundary conditions to an artificial intelligence (AI) system, wherein at least some of the boundary conditions are transmitted to the computing unit via the user interface; Spanning (S106), by the Kl system, a solution space with a multitude of possible product sequencings for processing orders contained in the order backlog data; Searching (S108) the solution space for at least one optimized product sequencing based on the constraints and / or based on an optimization preference; and Outputting (S110), via the user interface, at least one product sequencing plan.

8. The system of claim 7, wherein the computing unit is further adapted to output violated relationships for problem solving if no valid product sequencing is found in the solution space.

9. The system of claim 8, wherein the computing unit is further configured to output the violated relationships to a user for further analysis via the user interface.

10. System according to one of claims 7 to 9, wherein the formal system model is a semantic and formal extension of a digital design model of the machine line and further describes dependencies to and between operating states, geometries, materials, processes, functions, customer requirements and / or optimization goals.

Images