Optimize maintenance and / or assembly plans in machine production lines
By using computer-based methods and artificial intelligence systems, optimized maintenance and assembly plans for machine production lines are automatically generated, solving the problems of suboptimal results and downtime caused by reliance on human experience in existing technologies, and improving equipment efficiency and product quality.
Patent Information
- Application Number
- CN202610658184.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2025-05-14
- Filing Date
- 2026-05-13
- Publication Date
- 2026-11-17
AI Technical Summary
In existing technologies, the maintenance and assembly planning of machine production lines mainly rely on the operator's experience, lacking a unified digital platform for forward-looking planning and action recommendations, leading to suboptimal results, unplanned downtime, and equipment damage.
Using a computer-based approach, planning data and preferences are input through a graphical user interface. An artificial intelligence system is used to generate optimized maintenance and assembly plans. By combining expert systems and formal system models, the optimal plan for the machine production line is automatically generated.
It has enabled the automation of machine production lines, optimized maintenance and assembly plans, reduced unplanned downtime, improved equipment efficiency and product quality, and reduced operating costs.
Smart Images

Figure CN123113701A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to a computer-implemented method for optimizing maintenance and / or assembly plans in machine production lines, particularly for machine production lines for filling and packaging food and / or beverages. Background Technology
[0002] In the filling and packaging industry, production equipment is becoming increasingly complex, modular machine concepts are being widely adopted, and demands for efficiency, availability, and product quality are constantly rising. To meet these challenges, equipment operators are increasingly relying on software solutions to plan and control their production lines. Currently, various software solutions exist, primarily for customized planning of individual equipment components. These solutions are typically tailored to their specific production environments and require comprehensive expertise from operators of such equipment.
[0003] One problem with this approach is that, to date, basic planning processes, such as loading and maintenance planning, have been primarily performed manually and are based on the experience and knowledge of the machine production line operators. Among other things, consumables and auxiliary materials, such as labels, closures, preforms, lubricants, or cleaning agents, must be provided as needed and in a timely manner to ensure trouble-free equipment operation. Simultaneously, maintenance measures must be rationally planned to avoid unnecessary downtime and maximize the machine's lifespan.
[0004] The quality of these programs largely depends on the experience, availability, and qualifications of the staff. In practice, this often leads to suboptimal results. Unplanned downtime due to lack of operating tools, increased scrap due to insufficient supplies or maintenance delays, and the resulting machine damage are not uncommon. These impacts have a direct negative effect on overall equipment efficiency (OEE), product quality, and operating costs.
[0005] While there are already some machine-specific applications for status-based supply and maintenance, such as label level monitoring in labeling machines or level monitoring in preformed silos in stretch blow molding machines, status monitoring capabilities for individual machines, such as filling or labeling machines, exist, these solutions are selective and siloed. Cross-line functionality based on a manufacturer's extensive domain knowledge and offered as a digital service product specifically designed to optimize the entire production line is currently unavailable.
[0006] In particular, there is a lack of a unified digital platform that not only monitors the status of individual machines, but also aggregates and interprets this information, and provides forward-looking plans and action recommendations for loading and maintenance of the entire machine production line. Summary of the Invention
[0007] Therefore, improved methods and systems are needed to optimize maintenance and / or assembly plans in machine production lines.
[0008] According to the present invention, this objective is achieved by a computer-implemented method for optimizing maintenance and / or assembly plans in a machine production line, a system for optimizing maintenance and / or assembly plans in a machine production line, and a computer-readable storage medium having program instructions recorded thereon.
[0009] One implementation relates to a computer-implemented method for optimizing maintenance and / or assembly plans in a machine production line, particularly for filling and packaging food and / or beverages. The method includes providing an input interface. For example, this input interface could be a graphical user interface with an input mask specifically adapted for this purpose. Users can input: maintenance and / or assembly plan data for the machine production line, production plan data, and one or more preferences. Preferences are boundary conditions defined by the user in the maintenance and / or assembly plan. A formal system model of the machine production line is then obtained. The formal system model describes the operational relationships of data flow, energy flow, and / or material flow in the machine production line. For example, this system model can be derived from equipment engineering development data and simulation data. The formal system model, along with the maintenance and / or assembly plan data, production plan data, and one or more preferences, is then input into an artificial intelligence (AI) system. The AI system then expands a solution space with multiple possible maintenance and / or assembly options. For example, all physically possible sequence of plans can be included in the solution space. An optimized maintenance and / or assembly plan is then searched in the solution space based on one or more preferences, and the optimal plan for maintenance and / or assembly of the machine production line is output. For example, the output plan can be converted or output into control parameters suitable for controlling the machine production line. These output control parameters can then be directly implemented in the machine controller.
[0010] Further implementations include systems for optimizing maintenance and / or assembly schedules and corresponding computer-readable storage media. Attached Figure Description
[0011] Exemplary aspects of the invention are illustrated in the accompanying drawings. In the drawings: Figure 1 An exemplary schematic diagram of a system for optimizing maintenance and / or assembly schedules in a machine production line is shown. Figure 2 An exemplary device configuration for PET containers and adhesive bundles is shown; Figure 3 An exemplary equipment configuration for PET containers and shrink packaging machines is shown; Figure 4An exemplary device configuration for jars or glass bottles is shown; and Figure 5 An exemplary device configuration for a tank is shown. Detailed Implementation
[0012] Embodiments of the present invention relate to various strategies for loading and / or maintenance planning, depending on equipment configuration and the operator's preferences for equipment behavior on the equipment or machine production line. According to embodiments, the planning is implemented as an expert system across the entire production line, rather than being created manually as is common in the prior art. The purpose of the expert system is to extend production planning through loading order planning and / or maintenance planning, or to create cross-optimal production and maintenance plans and / or loading plans, respectively.
[0013] Production planning depends on various constraints arising from the interaction of data, energy, and material flows, and the operational relationships between these constraints and operating conditions, geometries, materials, processes, functions, customer requirements, and optimization objectives. For example, structural operational relationships can be formalized as a product commutation matrix. These constraints must also be adhered to in loading and maintenance planning. Furthermore, additional time constraints must be considered during loading and / or maintenance planning, such as the time periods during which loading and / or maintenance must be performed, and the dependency on previously performed loading or maintenance.
[0014] For operators of such equipment, it can be useful if the optimization potential of their equipment / machine production line or any desired system combination (e.g., logistics system + BPE equipment) within the prescribed production cycle (e.g., 1-5 days, 1-4 weeks, 1-2 months, etc.) is best demonstrated and can be implemented in production according to specific customer preferences. In this case, downtime may be due to product changeover time or dedicated maintenance and loading time, which has been explicitly prohibited from use in the production schedule. It should be noted that there is not always sufficient downtime in the production schedule to plan the necessary loading or maintenance orders, and downtime is also required during ongoing production. Downtime may also originate from product changeover time or dedicated maintenance time, which has been explicitly prohibited from use in the production schedule.
[0015] The implementation described herein can automatically generate a formal system model of the machine equipment based on a formal product exchange matrix and the auxiliary and consumable items (films, cartons, lids, labels, adhesives, etc.) required to produce the product, including its planning-related data (transportation time, storage location, available transportable units, and the likelihood of receiving units via transport vehicles and receiving stations in the machine / equipment), rather than through explicit customer-specific programming that takes into account different preferences.
[0016] Furthermore, if available, the loading possibilities for various materials can be predetermined using AGVs (Automated Guided Vehicles). To this end, the loading function range of each AGV, the possible workshop routes, and their limitations (e.g., one-way operation only, maximum speed, etc.) are formally predetermined.
[0017] For maintenance and / or loading plans, a formal system model of the machine production line can be derived based on the constraints of the aforementioned production and maintenance plans.
[0018] To optimize machine production line / machine loading or maintenance plans, a formal system model, including the current production plan (e.g., from ERP), current data from loading-related and / or maintenance-related monitoring systems (status monitoring, forecasting systems, etc.) of the machine / equipment to be planned, preferences (e.g., minimum changeover time, maximum OEE, minimum wear, minimum changes to existing production plans, etc.), and planning specifications (e.g., planning cycles, partial definitions in the loading plan, and machine customer- or equipment-specific planning rules, etc.), can be translated into a declarative logic language. This language can then be processed as a request by a knowledge-based AI system (expert system). The expert system has its own internal declarative formal logic knowledge model regarding the importance of the request and the transmitted system context. To determine the optimal response to the query, the process described below can be performed. For illustration, Figure 1 Exemplary components of the basic system 100 are shown.
[0019] In the first step, user 150 can input planning data for loading and / or maintenance planning into the system via input interface 140. In this case, system 100 includes a computer device equipped with specialized software and hardware. Input interface 140 can be, for example, a graphical user interface. In this case, input interface 140 can include a graphical user interface with query and input masks, by means of which the user is guided to preferences and / or other relevant data through a query process.
[0020] User 150 can input planning data, production planning data, and one or more preferences for machine production line maintenance and / or assembly into the system via input interface 140. Preferences, according to the implementation, are user-defined boundary conditions for planning maintenance and / or assembly. User 150 can directly input data via input interface 140, for example, via a keyboard or similar input unit. However, user 150 can also access database 120 via input interface 140, where at least a portion of the required data is already stored.
[0021] For example, to support input operations, system 100 may have appropriate interfaces to user 150's production planning system (e.g., ERP / MES system) and to equipment / machine monitoring systems (specifically regarding the availability and expected range of consumables in the equipment / machine), which in Figure 1 This is generally represented as access to database 120.
[0022] After fully inputting / selecting relevant data (including production plans during the loading period), preferences, and planning specifications from the production planning system, a formal system model of the machine production line can be obtained in the second step. For example, the formal system model describes the operational relationships of data, energy, and / or material flows within the machine production line. The formal system model can be generated, for example, by an AI system such as expert system 110 based on data from database 120. The formal system model can then be passed to the artificial intelligence (AI) system (expert system 110) along with maintenance and / or assembly planning data, production planning data, and one or more preferences.
[0023] The AI system or expert system 110 then expands the solution space with multiple possible maintenance and / or assembly options. Taking into account relevant production planning data (e.g., from ERP), data from equipment / machine monitoring systems, preferences, planning specifications, and the expert system 110's internal declarative formal logic knowledge model, the solution space for all possible actions can be automatically expanded. All possible action options are established by a so-called grounding ball. As a result, a variable-free logic program can be generated. If information needs to be propagated within the system (e.g., to propagate changes or constraints to other components or machines), this so-called propagation either occurs in parallel across several system modules, one after another in a prescribed order, or directly during the grounding process, i.e., during the preparation and concretization of possible action options.
[0024] Subsequently, an optimized maintenance and / or assembly plan is searched in the solution space based on one or more preferences, and the maintenance and / or assembly plan for the machine production line can be output.
[0025] The behavior plan output by the solver system 130 can then be (re)translated into a format usable for equipment / system control. For example, this can be done in the form of control parameters, which can be directly implemented by the control system. Equipment loading (e.g., via AGVs) can also be automatically controlled via output parameters. For example, this could be an optimal plan with routes for each AGV to load at the optimal time. Alternatively or additionally, the output plan can be presented to equipment operators in the form of a schedule, providing the exact loading time for each material on the machine production line, along with the collection and destination locations.
[0026] However, user 150 can also reject or refuse the output plan, for example, due to incorrect input or a new preference for the new plan. Then the process starts again.
[0027] In the event of unplanned events, such as AGV failure, system 100 can attempt reactive rescheduling based on the current processing status of the loading and / or maintenance plans, as well as the unplanned new state of the equipment. In this case, the final state of the machine production line and the loading or maintenance plan can be compared with the previously established solution space. In this case, planning data can be used as input for planning adjustments around new facts (e.g., AGV failure; route blocked for 2 hours), as input in input interface 140.
[0028] To implement System 100, Expert System 110 can be specifically tailored to a particular product design, including necessary standard optimization objectives, standard features, and standard user interfaces. In this case, the formal knowledge base of Expert System 110 is combined with an AI planning system (e.g., Grounder and solvers for answer set programming, constraint solvers, SMT or SAT solvers) to map further formal planning / preferences and performance optimizations. In this case, Expert System 110 is also extended to the specifications of loading and maintenance dependencies for individual machines in a machine production line, providing them with automated planning. Furthermore, integration layers can be created in ERP, MES, and monitoring systems, for example, as APIs, enabling Expert System 110 to be integrated into cloud systems. By connecting the machine production line online to Expert System 110 in the cloud, or by installing equipment-level Expert System 110 at the user's site, optimization of equipment loading and maintenance plans can be automatically implemented according to the described use cases.
[0029] In the following Figures 2 to 5 The present invention or at least some aspects thereof is described herein for various bottle filling equipment. Figures 2 to 5 The description is intended only to provide a general overview of machines that can benefit from monitoring the implementations described herein.
[0030] Figure 2 An exemplary device configuration 1000 for PET bottles or PET containers and adhesive bundles is shown. Figure 2 As shown, equipment configuration 1000 includes different modules that form a line, at the end of which fully filled PET containers are distributed onto pallets in bundles. Some of the modules and machines may be optional, and the invention is not limited to the specific form and arrangement of the equipment configuration.
[0031] Equipment configuration 1000 includes an oven 1002 for preforms, a preform sorter 1004 with a feeder, and a blow molding machine 1008. Modules 1002, 1004, and 1008 typically form a stretch blow molding machine in which PET containers are made and shaped from initial materials. The produced PET containers are then conveyed to a filler 1010, where bottles are filled. The filler may optionally include a rinsing device. During storage or transportation, various particles, such as dust, cardboard, or wooden pallet residue, may accumulate in the preforms. These particles can be removed using the rinsing device. A sealing machine may be arranged at the end of the filler to seal the PET containers after filling.
[0032] Optionally, the equipment configuration 1000 may include a rotating device after the filling machine 1010 for hot filling of PET containers. The filled PET containers are conveyed to a separator 1020 and then to a drying unit 1024 via one or more conveyor belts 1016 (which may also include a buffer 1018 for intermediate loading of filled containers), where the PET containers are dried.
[0033] After drying, the PET containers are conveyed to labeling machine 1026. Labeling machine 1026 can be designed for various labeling techniques, such as hot glue, cold glue, self-adhesive labels, or sleeve labels. After printing or labeling, the PET containers are conveyed to handle applicator via second drying unit 1028, production line distributor 1030, conveyor belt 1032, adhesive bundle production device 1034, and curing path. In adhesive bundle production device 1034, PET containers are grouped together in specific bundle sizes and packaged into bundles, such as "six-packs". In handle applicator, handles are attached to the containers, making it possible to comfortably carry the bundles. The finished bundles are then correspondingly arranged into layers by robot 1042 and packed on pallets by palletizer 1044.
[0034] In equipment configuration 1000, so-called format carriages or format racks can be arranged at various modules and machines to provide quickly changeable format kits for short changeover times and automated tool switching. Examples of format carriages are format carriage 1006 for blow molding machine 1008, format carriage 1012 for filling machine 1010, format carriage 1022 for labeling machine 1026, format carriage 1038 for adhesive bundling production device 1034, and format carriage 1046 for palletizer 1044.
[0035] Figure 3 Another exemplary device configuration 1100 for PET containers and shrink packaging machines is shown. Figure 3 Equipment 1100 includes Figure 2 The equipment configuration includes many modules and machines of 1000, but some differences exist. Therefore, for Figure 3 The already combined part is omitted. Figure 2 The description of the module being described.
[0036] A significant difference between the two exemplary device configurations 1000 and 1100 is that the labeling machine 1126, with labeling module 1127, can be installed after the blow molding machine 1008 and before the filling machine 1010. For this purpose, device configuration 1100 may include up to six transport tracks 1150 into which PET containers can be extruded. After the PET containers have been correspondingly extruded into one of the six tracks 1150, they are conveyed to a film wrapping module 1152 and then to a shrink tunnel 1154.
[0037] Figure 4 An exemplary device configuration 1200 for jars or glass bottles is shown. Figure 4 The exemplary device configuration 1200 is again with Figure 2 and Figure 3 The device configurations 1000 and 1100 have some similarities, so the description of the device configuration is limited to the differences in device configuration.
[0038] like Figure 4 As shown, an exemplary device configuration may include two separate supplies. Figure 4 The first supply on the left shows a branch of cans, or optionally a branch of new reusable bottles. Here, the containers (i.e., cans or new bottles) are guided into the machine by the depalletizer 1302, where they are guided to the filling machine 1010 via a conveyor belt. Figure 4 The second supply on the right shows a portion of a reusable bottle being introduced into the equipment from a reusable sorting device (not shown).
[0039] In the case where used reusable bottles are introduced into device configuration 1200 via a sub-branch for reusable bottles, the reusable bottles first pass through a cleaning or washing machine 1304. Another possible difference in exemplary device configuration 1200 is a transshipment packaging machine 1306 following the labeling machine 1026. The transshipment packaging machine can sort bottles or cans into cardboard clip application devices or boxes, or both.
[0040] Figure 5An exemplary device configuration 1300 for cans is shown, wherein elements already described in other device configurations are not described again. In device configuration 1300, cans are introduced from a can magazine 1402 containing cans into a depalletizer 1302. After the cans have passed through a filling machine and been filled, the cans are sealed by means of a sealing magazine 1404, and the cans are further conveyed along device 1400 via a conveyor belt, as described above.
[0041] If not required, the optional pasteurizer 1408 can be bypassed via bypass 1412. In pasteurizer 1408, freshly filled products can be pasteurized for preservation.
[0042] Compared to device configurations 1000, 1100, and 1200, exemplary device configuration 1300 shows different tanks for corresponding consumables, such as tank 1410 with rinsing liquid and / or filling product, and tank 1406 with lubricant. These tanks may also be included in the exemplary device configurations already described above. For example, chemical products conveyed from the mixer to the machine may be stored in tanks 1406 and 1410.
Claims
1. A computer-implemented method for optimizing maintenance and / or assembly plans in a machine production line, particularly for machine production lines for filling and packaging food and / or beverages, wherein, The method includes: Provide an input interface for input: Planning data for the maintenance and / or assembly of the machine production line. Production planning data, and One or more preferences, wherein the preferences describe user-defined boundary conditions in the maintenance and / or assembly plan; Obtain a formal system model of the machine production line, wherein the formal system model describes the operational relationships of data flow, energy flow and / or material flow in the machine production line; The formal system model, along with the maintenance and / or assembly planning data, the production planning data, and the one or more preferences, are input into the artificial intelligence (AI) system. Expand the solution space with multiple possible maintenance and / or assembly options through AI systems; Based on one or more of the preferences, an optimized maintenance and / or assembly plan is searched within the solution space; and Output the maintenance and / or assembly plan for the machine production line.
2. The computer-implemented method according to claim 1, wherein, Expanding the solution space includes: Ground personnel shall determine all possible action options for maintaining and / or assembling the machine production line, based on: Relevant production planning data, especially production planning data from enterprise resource planning, ERP, and other systems. Data from the monitoring system of the machine production line, The one or more preferences The internal declarative formal logic knowledge model of the expert system, and Generate a variable-free logic program, wherein searching the solution space according to an optimized product sort includes searching the variable-free logic program by means of a solver.
3. The computer-implemented method according to claim 1, further comprising: The output plan is converted into control parameters suitable for controlling the machine production line; and Receives the output control parameters.
4. The computer-implemented method according to claim 1, wherein, The preferences include: Minimum turnaround time, maximum OEE, minimum scrap rate, minimum wear and tear, and / or minimum modifications to existing production schedules. Planning data for maintenance and / or assembly includes: Planning cycle, certain provisions in the maintenance plan, certain provisions in the loading plan, and / or machine-, customer-, and / or plant-specific planning rules.
5. The method according to claim 1, wherein, The operational relationships and dependencies are formalized in the form of product commutation matrices.
6. The method according to claim 1, wherein, The formal system model is a semantic and formal extension of the digital design model of the machine production line, and further describes the dependencies between operating states, geometries, materials, processes, functions, customer requirements, and / or optimization objectives.
7. The computer-implemented method according to any one of claims 1 to 6, wherein, The input interface includes a graphical user interface with query and input masks, by which users are guided to preferences and / or other relevant data through a query process, wherein the AI system takes user-input data into account when expanding and searching the solution space.
8. A system for optimizing maintenance and / or assembly schedules in a machine production line, particularly for a machine production line for filling and packaging food and / or beverages, wherein, The system includes: The machine production line; A computing unit, including an artificial intelligence (AI) system and an input interface, wherein the computing unit is adapted to... Received via the input interface Planning data for the maintenance and / or assembly of the machine production line. Production planning data, and One or more preferences, wherein the preferences describe user-defined boundary conditions in the maintenance and / or assembly plan; Obtain a formal system model of the machine production line, wherein the formal system model describes the operational relationships of data flow, energy flow and / or material flow in the machine production line; The formal system model, along with the maintenance and / or assembly planning data, the production planning data, and one or more preferences, are input into the AI system. The AI system unfolds a solution space with multiple possible maintenance and / or assembly options; Based on one or more preferences, an optimized product ranking is searched within the solution space; and Output the maintenance and / or assembly plan for the machine production line.
9. The system according to claim 8, wherein, Expanding the solution space with the help of the AI system includes: Ground personnel shall determine all possible action options for maintaining and / or assembling the machine production line, based on: Relevant production planning data, especially production planning data from enterprise resource planning, ERP, and other systems. Data from the monitoring system of the machine production line, The one or more preferences The internal declarative formal logic knowledge model of the expert system, and Generate a variable-free logic program, wherein searching the solution space according to an optimized product sort includes searching the variable-free logic program by means of a solver.
10. A computer-readable storage medium having program instructions recorded thereon, wherein when the program instructions are executed by at least one computer device, the program instructions configure the at least one computer device to: Provide an input interface for input: Planning data for the maintenance and / or assembly of the machine production line. Production planning data, and One or more preferences, wherein, The preferences describe the boundary conditions defined by the user in the maintenance and / or assembly plan; Obtain a formal system model of the machine production line, wherein the formal system model describes the operational relationships of data flow, energy flow and / or material flow in the machine production line; The formal system model, along with the maintenance and / or assembly planning data, the production planning data, and the one or more preferences, are input into the artificial intelligence (AI) system. Expand the solution space with multiple possible maintenance and / or assembly options through AI systems; Based on one or more preferences, an optimized product ranking is searched within the solution space; and Output the maintenance and / or assembly plan for the machine production line.
