Method for operating a resource management system for a production plant for at least one product, computer program product, computer-readable storage medium, resource management system and production plant
The resource management system addresses the inefficiencies of monolithic control systems by integrating data from machines, networks, and machine learning platforms to optimize resource allocation, ensuring continuous operation and increased efficiency in flexible manufacturing environments.
Patent Information
- Application Number
- PCT/EP2024/062012
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-05-02
- Filing Date
- 2024-05-02
- Publication Date
- 2024-11-07
AI Technical Summary
Modern production facilities face challenges in efficiently managing resources due to monolithic resource management systems that lack unified control over machines, networks, and machine learning platforms, leading to potential shutdowns and inefficiencies, especially in flexible manufacturing environments where quick adaptations to customer demands are necessary.
A resource management system with multiple interfaces collects and evaluates data from machines, networks, and machine learning platforms to automatically optimize resource allocation, enabling continuous operation and increased efficiency by selecting appropriate configurations or triggering optimization algorithms.
This approach allows for uninterrupted production by integrating information from all system components, optimizing resource usage, and adapting to changing conditions, thereby enhancing overall production line efficiency and preventing complete shutdowns.
Smart Images

Figure EP2024062012_07112024_PF_FP_ABST
Abstract
Description
[0001] Description
[0002] Method for operating a resource management system for a production plant for at least one product, computer program product, computer-readable storage medium, resource management system and production plants
[0003] The invention relates to a method for operating a resource management system for a production plant for at least one product according to the applicable patent claim 1. Furthermore, the invention relates to a computer program product, a computer-readable storage medium, a resource management system and a production plant.
[0004] In today's production plant environment, such as a factory environment, where a factory operator initializes corresponding device networks, a problem of resource allocation may arise. After initial settings, the network and corresponding devices remain in a status quo for operation. The operator can change this configuration if a problem with, for example, a quality of service occurs. For example, a machine learning application may exhibit poor performance, such as poor prediction reliability. In this case, the operator can manually take various countermeasures. One such measure may be an analysis and possible reconfiguration of the network that connects the machine and its sensors to the application server. However, such an analysis may be too costly and time-consuming and therefore cannot be performed in an acceptable time.Reconfiguration can mitigate the problem by adding more resources to the connection or prioritizing traffic. If reconfiguration does not achieve the desired result, the operator's only option may be to shut down the affected computer and / or production line and / or machine until service quality is restored. However, restoring service quality may not occur within an acceptable timeframe. Shutting down a machine represents the worst-case scenario in a production plant, as it impacts the efficiency of all production chains on the line.
[0005] From US20190324440A1, self-organizing data acquisition in an industrial environment that takes into account the characteristics of a network is known. For data acquisition, improved methods for using collected data are used to enable monitoring, control and diagnosis of problems as well as optimization of processes in industrial environments. In an industrial system that includes a large number of components that are operatively coupled to respective sensors, a sensor communication device is provided. The sensor communication device interprets the data values collected by the sensors and forwards them via a system cooperation device, from where the data values collected by the sensors are transmitted via the network to a target computer. The transmission to the target computer takes place using a sensor data transmission protocol.A transmission device determines transmission feedback regarding the sensor data and collaborates with a network management device, which updates the transmission protocol used to transmit the sensor data in response to the transmission feedback. The network management device uses a machine learning algorithm, for example, to adapt the transmission protocol.
[0006] The object of the present invention is to provide a method, a computer program product, a computer-readable storage medium, a resource management system, and a production plant by means of which a more efficient manufacture of a product can be realized. This object is achieved by a method, a computer program product, a computer-readable storage medium, a resource management system, and a production plant according to the independent patent claims. Advantageous embodiments are specified in the subclaims.
[0007] One aspect of the invention relates to a method for operating a resource management system for a production plant for at least one product. Performance metrics are received from a machine learning platform of the production plant for a production process of the product by means of a first interface of the resource management system. Network data for a network device of the production plant for the production process is received by means of a second interface of the resource management system. Machine data is received from at least one machine of the production plant involved in the production process by means of a third interface of the resource management system. The performance metrics and the network data and the machine data are evaluated by means of an electronic computing device of the resource management system.A configuration is selected from a configuration database of the resource management system based on the evaluation. At least one control command is generated to change a setting parameter of the machine learning platform and / or the network device and / or at least one participating machine based on the selected configuration.
[0008] In particular, this can lead to an increase in efficiency within the production of a product.
[0009] Modern production facilities and factories in particular are facing a new challenge. Production parts either change quickly according to individual customer requirements, or only small batch sizes of production parts need to be manufactured. This modern type of production environment requires highly flexible production stations. To achieve this and ensure high quality, digital factories use intelligent systems to monitor and control the production stations. One example of such a system in modern production facilities is the automation of quality control through machine-assisted, optical inspections. A variety of machine learning algorithms are now available for the automation of optical inspections, in particular represented by the machine learning platform.These systems monitor the production equipment and the manufactured parts, for example through automatic optical inspection. However, the network that connects the machine learning platforms to the optical system, for example, often remains in a status quo after the initial setup. Network controllers that actively control the network based on information about the Quality of Service (QoS) are not yet common in industrial environments. Furthermore, not only machine learning is used to improve the operation of production lines, but digital twins based on machine learning are also being integrated into the optimization of the production line process. According to the state of the art, there is no uniform control of all resources involved, in particular machines, networks, machine learning or digital twin platforms.
[0010] The problem arises from the architecture of the resource management systems mentioned. Each system, whether it manages the production station or the network, consists of its own control loop. These control loops carry out their work in their own encapsulated environment, without detecting data states from the rest of the domain. The problem with these monolithic systems is their limited range of action. For example, a network controller that manages the shared media network in the factory, such as a 5G network, can only react within its environment, meaning it can only control the network resources. In the factory environment, this lack of resource control can lead to a complete standstill of an assembly line. For example, the network system may not provide enough resources for the current operating mode of the production line, so production has to be stopped.To overcome the limitations of current systems, a module and method are proposed that integrate information from all involved technological components, particularly machines, network devices, and machine learning platforms. This results in, for example, that production lines do not need to be stopped, unlike the state of the art, thus enabling increased production line efficiency.
[0011] In particular, a method and a module, especially the resource management system, are proposed that implement the concept of network-, machine-learning-, and production-oriented resource management. The resource management system collects all relevant information from the participating system components, i.e., in particular, from the network facility, the participating machines or production components, and the machine learning components or a so-called digital twin platform. This collection of monitoring information takes place continuously. If multiple resources are available, the resource management system can accelerate the entire production process wherever possible.In general, based on the information collected, the resource management system can select an operating configuration from an available configuration database that provides many configurations for different operating speeds, or it can trigger the execution of a resource management algorithm, i.e., in particular, an optimization system. The result of the optimizations are actions. These actions contain the control commands for controlling all components, i.e., the network or network equipment, the machines, and / or the machine learning component. This means that the resource management system also provides interfaces to the corresponding components. As a result, the plant operators experience uninterrupted operation of their plants and not one that halts entire production processes.
[0012] In particular, a system architecture is proposed which takes machine learning, manufacturing, and networks into account. According to the invention, automatic and joint optimization of an industrial factory scenario is provided. A system controller with three corresponding interfaces for connecting to the critical infrastructure is provided in order to move from a network-capable to a manufacturing-capable system controller. Each of the interfaces is used in particular to collect data for one of the three aforementioned aspects, in particular manufacturing, network, and machine learning platform. It should be noted that the resource management system can also be connected to a digital twin platform. The digital twin platform can include machine learning modules.In contrast to the state of the art, the proposed architecture introduces joint optimization across the entire production plant or factory.
[0013] According to an advantageous embodiment, quality assurance features of a monitoring device in the production plant are received as performance metrics. In particular, the first interface collects metrics on the performance of task-critical machine learning applications or artificial intelligence applications. Task-critical means that certain steps in a supply chain can only be carried out with appropriate performance, e.g. accuracy, of the respective application. The quality of the result of the machine learning application is the decisive factor for the corresponding evaluation procedures as to whether resource management is required in the network or in the production plant. Since the artificial intelligence application is a closed system, the first interface only receives data in one direction.An example of such a scenario is automated optical inspection in an assembly line. Camera systems can use machine learning to automate certain quality assurance tasks to detect defects in manufactured parts. This enables the first interface of the electronic computing device to be machine-learning capable. In particular, the interface enables metrics collection and the control of external ML / AI applications. The resource management system itself is also machine-learning capable via this interface.
[0014] According to a further advantageous embodiment, a used bandwidth of the network device and / or a latency of the network device is / are received as network data. In particular, the network device and the resulting network play a crucial role in modern industrial production plants in general. A connection with a high bandwidth and low latency for machine learning tasks and control tasks must be provided. Therefore, the second interface is set up to monitor the status of the network device. Since the network may not offer any QoS functions, is used by other applications or is dependent on a shared medium, the monitoring of and connection to the network is crucial. Some examples of these metrics are in particular the used bandwidth and the latency.The interface not only receives data in one direction but can also communicate with the network elements. This allows the electronic computing device to control parts of the network in the event of a service degradation.
[0015] A further embodiment provides that, on the basis of the evaluation, a control command for reconfiguring the network device, in particular reordering a slice allocation of the network device, is generated. Slices refer to the time slots available to a device for sending data. The larger the slice, the more data can be sent per unit of time. For example, the electronic computing device can thus reorder the slice allocation for a shared medium, such as a 5G slice. This reordering helps a degraded task to achieve a specific QoS target again, while at the same time it can be ensured that no other parallel tasks are degraded, which improves the overall throughput and efficiency.
[0016] It is also advantageous if, on the basis of the evaluation, a control command is generated to increase the bandwidth for machine learning performance for the at least one machine. In particular, since certain network architectures only offer limited scope for resource management, a separate third interface to the production devices, in particular to the at least one machine, is required as a fallback option. A critical point is the buffer state between, for example, two robots. Both the robots and the buffer themselves can be viewed as machines involved in the production process. In the event of an overflow or underflow, one of the two robots must wait until, for example, the other has caught up with it. Countermeasures in the network can help to a certain extent, for example by making more bandwidth available to the slower machine for better machine learning performance.It will be obvious to a person skilled in the art that other embodiments, for example with multiple robots or buffers, as well as other machines, can also be read. It has also proven advantageous if, on the basis of the evaluation, a control command for reducing the production speed for at least one machine is generated. For example, if all network-related options have been exhausted, the machines can also participate in this resource management. Each machine can, for example, adjust the production speed so that a buffer remains fed. This method offers the greatest scope for adjustments, but only offers a last-minute selection option and should therefore only be used if necessary.The reason for this is that , in contrast to managing the networks , in this case the achievable overall efficiency of the production station decreases , while on the other hand only adjusting the network potentially allows all machines to run at full speed .
[0017] A further advantageous embodiment provides that a multitude of different operating strategies are made available in the configuration database and, depending on the evaluation, an operating strategy adapted to a current situation is selected. In particular, the configuration database can store current values about how the system controller interacts with and influences its environment. These values monitor the behavior of the system controller in certain scenarios. The configuration database also represents a point of influence on the control loop, which makes it possible to limit the scope of action of the system controller, i.e. the electronic computing device, via its various interfaces to other components.
[0018] Furthermore, it has proven advantageous to save the currently received performance metrics, network data, and machine data with the selected configuration and to consider them during future operation of the resource management system. In particular, the configuration database thus stores solutions to resource problems. In a similar case, the electronic computing device can thus search for a previous solution and apply it accordingly.
[0019] Furthermore, it has proven advantageous if the currently received performance metrics and network data and machine data are transmitted to an external electronic computing device. In this case, it can further be provided that at least one external configuration relating to the current performance metrics and network data and machine data is received by the external electronic computing device and that the at least one control command is generated as a function of the external configuration. In this case, it can further be provided that the at least one external configuration is stored in the configuration database and taken into account in future operation. Thus, in particular the electronic computing device or the resource management system has a fourth interface for resource management.For example, if the electronic computing device cannot develop a reasonable solution or nothing is stored in the configuration database, this interface provides a gateway to an external management system. In this case, the electronic computing device sends the system status to the external electronic computing device to resolve the existing problem. If the external electronic computing device can resolve the problem, it is stored in the configuration database for later use.
[0020] The method presented is, in particular, a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means that cause an electronic computing device, when the program code means are processed by the electronic computing device, to perform a method according to the preceding aspect.
[0021] The invention also relates to a computer-readable storage medium with at least one computer program product according to the preceding aspect.
[0022] A further aspect of the invention relates to a resource management system for a production plant for at least one product, having at least a first interface, a second interface, a third interface and an electronic computing device, wherein the resource management system is designed to carry out a method according to the preceding aspect. In particular, the method is carried out by means of the resource management system.
[0023] The electronic computing device comprises, for example, processors, circuits, in particular integrated circuits, as well as other electronic components in order to be able to carry out corresponding process steps.
[0024] Furthermore, the invention also relates to a production plant for at least one product, with at least one machine learning platform, with a network device, with a machine involved in a production process of the product and with a resource management system according to the preceding aspect.
[0025] Advantageous embodiments of the method are to be regarded as advantageous embodiments of the computer program product, the computer-readable storage medium, the resource management system and the production plant. The resource management system and the production plant have, in particular, material features for this purpose in order to be able to carry out corresponding method steps. A computing unit / electronic computing device can be understood in particular as a data processing device which contains a processing circuit. The computing unit can therefore, in particular, process data for carrying out computing operations. This may also include operations for carrying out indexed access to a data structure, for example a conversion table, LUT (English: "look-up table").
[0026] The computing unit can in particular contain one or more computers, one or more microcontrollers and / or one or more integrated circuits, for example one or more application-specific integrated circuits, ASIC (English: "application-specific integrated circuit"), one or more field-programmable gate arrays, FPGA, and / or one or more single-chip systems, SoC (English: "system on a chip"). The computing unit can also contain one or more processors, for example one or more microprocessors, one or more central processing units, CPU (English: "central processing unit"), one or more graphics processing units, GPU (English: "graphics processing unit") and / or one or more signal processors, in particular one or more digital signal processors, DSP.The computing unit may also include a physical or virtual network of computers or other of the aforementioned units.
[0027] In various embodiments, the computing unit includes one or more hardware and / or software interfaces and / or one or more memory units.
[0028] A memory unit can be a volatile data memory, for example a dynamic random access memory (DRAM) or a static random access memory (SRAM), or a non-volatile data memory, for example a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or flash EEPROM, a ferroelectric random access memory (FRAM), a magnetoresistive random access memory (MRM),MRAM (magnetoresistive random access memory) or phase-change random access memory, PCRAM (phase-change random access memory).
[0029] For use cases or application situations that may arise during the method and which are not explicitly described here, it may be provided that, in accordance with the method, an error message and / or a request to enter user feedback is issued and / or a default setting and / or a predetermined initial state is set.
[0030] Regardless of the grammatical gender of a particular term, persons with male, female or other gender identities are included.
[0031] Showing:
[0032] FIG 1 shows a schematic block diagram according to an embodiment of a production plant with an embodiment of a resource management system;
[0033] FIG. 2 shows a schematic flow diagram according to an embodiment of a method according to the invention; FIG. 3 shows a further schematic flow diagram according to a further embodiment of the method; and
[0034] FIG 4 shows a further schematic block diagram according to an embodiment of the production plant with an embodiment of the resource management system.
[0035] In the figures, identical or functionally identical elements are provided with the same reference symbols.
[0036] FIG. 1 shows a schematic block diagram according to one embodiment of a production plant 10 for at least one product 12. The production plant 10 has at least one machine learning platform 14, a network device 16, and at least one machine 18 involved in a production process of the product 12. In particular, the network device 16 and the machine 18 involved in the production process form a so-called production environment 20. Furthermore, the production plant 10 has at least one resource management system 22.
[0037] The resource management system 22, in turn, has a first interface 24, a second interface 26, and a third interface 28. Furthermore, the resource management system 22 has at least one electronic computing device 30. Furthermore, FIG. 1 shows that the resource management system 22 also has a fourth interface 32 for communicating with an external electronic computing device 34. Furthermore, the resource management system 22 can have a configuration database 36 and an input or output device 38 for a person 40.
[0038] In particular, the resource management system 22 can be used to perform a method for operating the resource management system for a production plant, in which performance metrics 42 are received from the machine learning platform 14 via the first interface 24. Furthermore, network data 44 is received from the network device 16 via the second interface 26. Furthermore, machine data 46 is received from the at least one machine 18 involved in the production process.
[0039] The performance metrics 42, the network data 44, and the machine data 46 are evaluated by the electronic computing device 30. A configuration is selected from the configuration database 48 of the resource management system 22 based on the evaluation. At least one control command 50 is generated to change a setting parameter of the machine learning platform 14 and / or the network device 16 and / or at least one participating machine 18 based on the selected configuration 48.
[0040] In particular, it can be provided that quality assurance features of a monitoring device 60 (FIG. 4) of the production plant 10 are received as performance metrics 42. Furthermore, a used bandwidth of the network device 16 and / or a latency time of the network device 16 can be received as network data 44. Furthermore, it can be provided that, on the basis of the evaluation, a control command 50 for reordering a slice occupancy of the network device 16 is generated. It can also be provided that, on the basis of the evaluation, a control command 50 for increasing a bandwidth for a machine learning performance for the at least one machine 18 is generated. Furthermore, it can be provided that, on the basis of the evaluation, a control command 50 for reducing a production speed for the at least one machine 18 is generated.Furthermore, it can be provided that a plurality of different operating strategies are provided in the configuration database 36, and that, depending on the evaluation, an operating strategy adapted to the current situation is selected. It can also be provided that the currently received performance metrics 42 and network data 44 and machine data 46 are stored with the selected configuration 48 and taken into account during future operation of the resource management system 22.
[0041] Furthermore, FIG. 1 shows in particular that the currently received performance metrics 42 and network data 44 and machine data 46 can be transmitted to the external electronic computing device 34, wherein at least one external configuration 52 relating to the current performance metrics 42 and network data 44 and machine data 46 is received by the external electronic computing device 34, and the at least one control command 50 is generated as a function of the external configuration 52. Provision can be made for the at least one external configuration 52 to be stored by the configuration database 36 and taken into account during future operation.
[0042] Furthermore, it can be provided that the user 40 can input or output input or output signals 54 via the input or output device 38.
[0043] In particular, FIG 1 shows that the first interface has metrics for the performance of task-critical ML / AI applications (ML = machine learning; AI = artificial intelligence). Task-critical means that certain steps in a supply chain can only be carried out with appropriate performance, i.e. in particular accuracy, of the respective application. The quality of the result of the ML application is the deciding factor for the electronic computing device 30 as to whether resource management is required in the network or in the production plant 10. Since AI applications are a closed system, the first interface 24 only receives data in one direction. An example of such a scenario is the automatic, optical inspection on an assembly line. Camera systems can use machine learning to automate certain quality assurance tasks in order to detect defects in manufactured parts.As already mentioned, the first interface 24 thus enables the electronic computing device 30 to be capable of machine learning.
[0044] The network device 16 also plays a crucial role in the described embodiment and in modern industrial manufacturing plants in general. High bandwidth, low latency connections must therefore be provided for the machine learning tasks and the control tasks. Therefore, the second interface 26 is provided to monitor the status of the network device 16. Since the network may not offer QoS functions, is used by other applications, or relies on a shared medium, the monitoring of and connection to the network is very crucial. Examples of the metrics include, in particular, the used bandwidth and the latency. The second interface 26 not only receives data in one direction but can also communicate with the network elements.In this way, the electronic computing device 30 can control portions of the network device 16 in the event of a service degradation. For example, the electronic computing device 30 can reorder a slice allocation for a shared medium, such as a 5G slice. This reordering helps a degraded task achieve a specific QoS target while ensuring that no other parallel tasks are degraded, improving overall throughput and efficiency.
[0045] Since certain architectures only offer limited scope for resource management, the third interface 28 is provided, with a connection to the production devices or the machine 18 or machines 18, as a fallback option. A critical point can be seen, for example, as a buffer state of a buffer 62 (FIG. 4) between two robots 56, 58 (FIG. 4). The buffer state and the robots 56, 58 form, in particular, corresponding machines 18. In the event of an overflow or underflow, one of the robots 56, 58 must wait until the other has caught up with it. Countermeasures in the network can help to a certain extent, for example by making more bandwidth available to slower machines 18 for better machine learning performance. However, if all network-related options are exhausted, the machines 18 can participate in this resource management.Each machine 18 can adjust its speed so that the buffer 62 remains fed. This method offers the greatest scope for adjustment, but should only be used when necessary. The reason for this is that, unlike network management, the overall achievable efficiency of the production station decreases in this case, while, on the other hand, only network adjustment potentially allows all machines 18 to run at full speed.
[0046] The configuration database 36 stores current values about how the system controller or the electronic computing device 30 interacts with and influences its environment. These values monitor the behavior of the system controller in certain scenarios. The configuration database 36 also represents a point of influence on the control loop, as it makes it possible to limit the scope of action of the system controller or electronic computing device 30 via its various interfaces 24, 26, 28 to the other components. In addition, the configuration database 36 stores solutions to previous resource problems. In a similar case, the core logic, i.e. the electronic computing device 30, can search for a previous solution and apply it.
[0047] For example, if the electronic computing device 30 fails to develop a reasonable solution or if nothing is stored in the configuration database 36, the fourth interface 32 provides a gateway to the external electronic computing device 34 as an external management system. In this case, the electronic computing device 30 sends the system status to the external electronic computing device 34 to resolve the existing problem. If the external electronic computing device 34 can resolve the problem, it is stored in the configuration database 36 for later use.
[0048] FIG 2 shows a schematic flow diagram according to one embodiment of the method. In particular, FIG 2 shows a managed process with an external solution. The external electronic computing device 34 is used to find a solution. In a first step S1, the electronic computing device 30 collects the data from all connected devices, in particular from the machine learning platform 14, the network device 16 and the machine 18. In a second step S2, this data is again analyzed internally, and in a third step S3, the electronic computing device 30 again requests a solution from the configuration database 36. In the present exemplary embodiment, the configuration database 36 cannot find a solution and therefore requests the external electronic computing device 34 in a fourth step S4.In a fifth step S5, the external electronic computing device 34 sends the at least one external configuration 52 back to the electronic computing device 30. In a sixth step S6, the corresponding setting parameters are then sent to the devices, in particular the machine learning platform 14, the network device 16, and the machine 18. In a seventh step S7, the electronic computing device 30 requests the configuration database 36 to save the transmitted external configuration 52 and to make it available in the future.
[0049] FIG. 3 shows a further exemplary embodiment of the method according to the invention, wherein in this case the configuration database 36 provides an internal solution, so that no external communication is necessary. In particular, steps S1 to S3 thus take place as already described for the method in FIG. 2. After the third step S3, an eighth step S8 takes place, which transmits the configuration 48 to the electronic computing device 30. Then, again after the eighth step S8, the sixth step S6 according to FIG. 2 is carried out and the corresponding setting parameters are transmitted to the devices, in particular the machine learning platform 14, the network device 16 and the machine 18.
[0050] FIG 4 shows a further schematic block diagram according to an embodiment of the production plant 10. In particular, the monitoring device 60 is designed as a camera in the present case. Furthermore, the buffer 62 between the first robot 56 and the second robot 58 is shown. In particular, this represents a concrete example of the application of the invention already described in a simple industrial environment which contains all the elements required for operation. This example again consists of the two robots 56, 58 which produce common parts. Furthermore, a buffer 62 is shown as an intermediate buffer. Both robots 56, 58 use image processing systems which are outsourced to an external server in order to fulfill their respective tasks. The cameras and the server are connected via a network which also includes a common medium, such as 5G.As described in the previous drawings, the manufacturing system, the network, and the machine learning platform are connected to the electronic computing device 30, which runs the corresponding algorithm. In the event of network problems, the electronic computing device 30 can, for example, slow down the operating speed of both robots 56, 58. In this case, the overall operation of the system is not interrupted. The effort of completely stopping production and then restarting from scratch is thus eliminated.
[0051] The invention also encompasses communication with a digital twin platform. Future factories, in particular, will integrate digital twins. Such digital twins may also integrate machine learning components and thus represent an alternative to the machine learning platform 14. Therefore, this invention can also be connected to digital twin platforms that use machine learning components. The electronic computing device 30 will then also integrate the resource management information and capabilities of the digital twin platform into the optimization process. If the digital twin platform offers different operating modes, the electronic computing device 30 may inform the platform so that it adapts to the requirements proposed by the electronic computing device 30.The combination with the digital twin platform can be considered as a complementary aspect or as an independent aspect of the invention.
[0052] In particular, the invention proposed in FIGS. 1 to 4 offers the advantages of seamless, automated operation of, for example, three components that are involved in future production systems. These three components are the machine 18, the network device 16 and the machine learning platform 14 or the digital twin platforms. Instead of stopping production, production can be throttled. This makes it possible to achieve uninterrupted operation of industrial plants, leading to higher system utilization. Furthermore, adaptive process throttling can be carried out to avoid wasting resources, i.e., resources are released, particularly during throttling. Furthermore, configurations for the operation of all components are readily available. Runtime can also be optimized if necessary.Likewise, it is not necessary to completely stop the machine 18, but only to slow down the process. This allows for simplified human interaction.
Claims
Patent claims 1. A method for operating a resource management system (22) for a production plant (10) for at least one product (12), comprising the steps: - receiving performance metrics (42) from a machine learning platform (16) of the production plant (10) for a production process of the product (12) by means of a first interface (24) of the resource management system (22); - receiving network data (44) from a network device (16) of the production plant (10) for the production process by means of a second interface (26) of the resource management system (22); - receiving machine data (46) from at least one machine (18) of the production plant (10) involved in the production process by means of a third interface (28) of the resource management system (22); - evaluating the performance metrics (42) and the network data (44) and the machine data (46) by means of an electronic computing device (30) of the resource management system (22); - selecting a configuration (48) from a configuration database (36) of the resource management system (22) depending on the evaluation; and - generating at least one control command (50) for changing a setting parameter of the machine learning platform (14) and / or the network device (16) and / or the at least one participating machine (18) depending on the selected configuration (48).
2. Method according to claim 1, characterized in that quality assurance features of a monitoring device (60) of the production plant (10) are received as performance metrics (42).
3. Method according to claim 1 or 2, characterized in that a used bandwidth of the network device (16) and / or a latency time of the network device (16) are received as network data (46).
4. Method according to one of the preceding claims, characterized in that on the basis of the evaluation, a control command (50) for a reconfiguration of the network device (16), in particular a reordering of a slice assignment of the network device (16), is generated.
5. Method according to one of the preceding claims, characterized in that on the basis of the evaluation, a control command (50) for increasing a bandwidth for a machine learning performance for the at least one machine (18) is generated.
6. Method according to one of the preceding claims, characterized in that on the basis of the evaluation a control command (50) for reducing a production speed for the at least one machine (18) is generated.
7. Method according to one of the preceding claims, characterized in that a plurality of different operating strategies are provided on the configuration database (36) and, depending on the evaluation, an operating strategy adapted to a current situation is selected.
8. Method according to one of the preceding claims, characterized in that the currently received performance metrics (42) and network data (44) and machine data (46) are stored with the selected configuration (48) and are taken into account in a future operation of the resource management system (22).
9. Method according to one of the preceding claims, characterized in that the currently received performance metrics (42) and network data (44) and machine data (48) are transmitted to an external electronic computing device (34).
10. The method according to claim 9, characterized in that at least one external configuration (52) relating to the current performance metrics (42) and network data (44) and machine data (46) is received from the external electronic computing device (34) and the at least one control command (50) is generated as a function of the external configuration (52).
11. The method according to claim 10, characterized in that the at least one external configuration (52) is stored by the configuration database (36) and is taken into account in future operation.
12. Computer program product with program code means which cause an electronic computing device (30) to carry out a method according to one of claims 1 to 11 when the program code means are processed by the electronic computing device (30).
13. A computer-readable storage medium comprising at least one computer program product according to claim 12.
14. Resource management system (22) for a production plant (10) for at least one product (12), with at least a first interface (24), a second interface (26), a third interface (28) and an electronic computing device (30), wherein the resource management system (22) is designed to carry out a method according to one of claims 1 to 11.
15. Production plant (10) for at least one product (12), with at least one machine learning platform (14), with a network device (16), with at least one machine (18) involved in a production process of the product (12) and with a resource management system (22) according to Claim 14.
Citation Information
Patent Citations
Systems and methods for network-sensitive data collection
US20190324440A1
Cited By
Business data management method and system based on process industry digital factory, and cloud platform
CN119294760A
