Computer-implemented method for operating a processing line, and processing line

Abstract

Computer-implemented method for operating a processing line (1), wherein the processing line (1) comprises a first plant module with a first control device and a second plant module with a second control device. An evaluation device with a computing device is provided, wherein the evaluation device is operatively connected to the first control device of the first plant module and to the second control device of the second plant module. The evaluation device receives a data set from the first control device and a data set from the second control device, wherein the computing device is suitable and designed for checking a functionality using an evaluation based on the joint consideration of the data sets using an automated application. The processing line (1) according to the invention comprises a first plant module with a first control device and a second plant module with a second control device and an evaluation device, which is suitable and designed for carrying out such a computer-implemented method.

Description

[0001] Computer-implemented method for operating a processing line and processing line

[0002] Description

[0003] The present invention relates to a computer-implemented method for operating at least one processing line, wherein the processing line comprises at least one first system module with at least one first control device and at least one second system module with at least one second control device. The present invention further relates to at least one processing line comprising at least one first system module with at least one first control device and at least one second system module with at least one second control device.

[0004] Machines or assemblies of systems in a wide variety of technical fields often have at least one control device that controls the respective machine or assembly.

[0005] Typically, at least one sensor or similar device is installed or provided to monitor and / or control the relevant work steps of the machine. This data can then be used, among other things, to control and / or regulate the machine or assembly.

[0006] These data are also stored and / or retained in the control device, for example in the event of defects and / or

[0007] REPLACEMENT SHEET (RULE 26) to be able to read out information about the operation of the machine during maintenance.

[0008] If a machine or the control device detects a malfunction during operation or if a predetermined result is not achieved, an error message is often displayed or a so-called log file is created or stored.

[0009] In a system with several machines or assemblies, it can happen that a certain machine detects an error, which is then stored, for example, in the control device. A corresponding error message can also often be output. Depending on the type of error, it may, however, already have occurred in another (upstream) assembly, but only have an effect in the current assembly (which detects / outputs the error). An operator cannot usually recognize this from the error message in the current assembly, so they can be mistakenly led to make settings on the machine or assembly that issued the error message.

[0010] While this may restore the desired end result under certain circumstances, as the error is corrected by a modified workflow in the current machine, such an approach does not correct the cause of the error and is therefore not beneficial.

[0011] Especially in more complex systems with multiple components, it can often be very difficult and time-consuming to correctly localize a malfunction and thus eliminate the actual cause of an error.

[0012] It is therefore the object of the present invention to improve the interaction of several machines or systems in such a way that the origin of an error or malfunction or undesirable property can be better localized and preferably eliminated.

[0013] This object is achieved by a computer-implemented method having the features of claim 1 and by a processing line having the features of claim 16. Preferred developments of the invention are the subject of the subclaims. Further advantages and features of the present invention will become apparent from the general description and the description of the exemplary embodiment.

[0014] The computer-implemented method according to the invention is provided for operating a processing line, wherein the processing line comprises at least one first system module with at least one first control device and at least one second system module with at least one second control device. Furthermore, at least one evaluation device with at least one computing device is provided, wherein the evaluation device is operatively connected at least to the first control device of the first system module and to the second control device of the second system module.The evaluation device receives at least one data set from the first control device and at least one data set from the second control device, wherein the computing device is suitable and configured to check at least one functionality using an evaluation based on the synopsis of the data sets from the first and second control devices with at least one automated application. At least one predetermined action is then performed.

[0015] The evaluation device preferably comprises a storage device in which the data records generated by the control devices are continuously stored and processed, depending on the design also in different storage locations according to the data record type.

[0016] According to the application, a processing line is understood in particular to mean the interaction of at least two systems or system components or machines or assemblies which interact at least partially or at least temporarily at least indirectly. In particular, the two system modules can carry out directly consecutive processing steps and / or actions. However, other processing steps or actions can preferably also be provided between the two system modules. In particular, it is also possible for the system modules to be spatially separated from one another and for at least one transport step to be provided, for example to process a product first with the first system module and after transport with the second system module.

[0017] A processing line can, in particular, be a processing center, for example, wherein the two system modules of such a processing center can be, for example, a handling device and a conveyor device. In preferred embodiments, a processing line can also be, for example, a classic packing line or a packing shop. Thus, the processing line can preferably be a packing system for filling bulk goods, liquids and / or the like, wherein such a packing system comprises, for example, a rotating packing machine and a bag filler assigned to the packing machine. Alternatively, the packing system can also be provided for filling other containers, in particular when, for example, liquids are being filled. In this case, the container to be filled can be, for example, barrels, containers, bottles, big bags, octabins, pouches and / or the like.According to the application, the fact that the computing device is suitable and designed to check at least one functionality on the basis of an evaluation means, in particular, that if, for example, at least one specific property, at least one malfunction or at least one error is detected, the automated application analyses the functionality or the malfunction or the error or the property in order to find out the cause of the specific property or the error or the malfunction.

[0018] According to the application, a computing device preferably comprises at least one computer and / or the like and / or is provided by at least one computer and / or the like. Thus, a computer can also provide the evaluation device that contains the computing device.

[0019] An automated application is in particular at least one processor-based application or a computer-based application which processes, further processes or analyses the data acquired by the control devices.

[0020] The computer-implemented method according to the invention offers many advantages. A significant advantage is that in the event of malfunctions or errors or undesired results and / or characteristics, it is not only recognized that something is not running according to specifications, but that the automated application can also perform automated analysis or troubleshooting or malfunction detection. According to the invention, not only the data from one system module is taken into account, but the data records from various control devices are combined and analyzed in a synopsis to obtain a detailed picture of the processes on the processing line or the individual system modules, thus better classifying the functionality or a malfunction or error. Depending on the design, the individual data records can be analyzed individually initially, in parallel, or subsequently.

[0021] This allows the cause of the detected functionality (error, property, etc.) to be identified and remedied accordingly. For example, properties of a system module can be automatically adjusted and / or a user can be given appropriate instructions.

[0022] Since the data of several control devices are taken into account in a synopsis, it is not only possible to identify a specific functionality or an error, but also to identify non-trivial, complex or immediately non-obvious relationships between work steps and a specific functionality.

[0023] The automated application can, in particular, take stored functionalities or examples of malfunctions and / or errors into account. In particular, normal parameters for certain processes can be stored in a database, for example, whereby the automated application then compares, for example, target and actual values ​​of certain processing steps and sets them in relation to the entire processing process. Depending on the design, different threshold values ​​can also be taken into account and / or drifting or tendentially changing values ​​(trends) can be detected or taken into account. For example, an automated application can detect that a certain error occurs in a second system module whenever a certain parameter for a certain processing step is present in the first system module.Depending on the design, for example, the wear of certain components on a first system module can be detected, even if this means that a certain functionality is only detected or an error occurs in the second or subsequent system module.

[0024] This allows for better and faster error detection, preferably through synchronous recording of events from different system components and the synopsis of these events in a unified system for root cause analysis. Appropriate actions and / or settings can then be implemented automatically or by command to eliminate the error functions. Furthermore, this synopsis can be used to optimize processes.

[0025] Preferably, an error pattern is recognized based on error frequencies in the overall context.

[0026] Preferably, a predetermined action performed based on a verified functionality comprises an instruction, a note, and / or a report, or the output of an instruction, a note, or a report. However, an action to be performed may also include, for example, at least one change and / or adjustment of at least one setting.

[0027] Reports can preferably be sent automatically and, in particular, shared between systems. The distribution group can be preferentially adjusted depending on the functionality tested and / or the results of the test and / or at certain thresholds. Internal and external distribution, as well as to different individuals and / or groups of individuals, are particularly possible.

[0028] Preferably, KPIs (Key Performance Indicators) are determined / created across all machines and output as a report or displayed in at least one system dashboard. Also preferred is chat between machines (from dashboard to dashboard), between the hotline and machine, between machine and production management, and / or similar, as well as the use of pre-defined reports for rapid communication, especially AI-supported reports for quick responses.

[0029] During the review, outliers are preferably eliminated or identified. In this case, outliers preferably stand out (significantly) from the averaged majority of values ​​or

[0030] events, so that they can be statically ignored.

[0031] Changing and / or adjusting at least one setting or adjusting specific parameters can also be used, in particular, for process optimization. For example, waiting times can be eliminated if a process on a downstream system is experiencing waiting times, even though the upstream system can still increase performance. Conversely, if weight fluctuations occur during a filling process, performance can also be reduced to achieve better filling accuracy.

[0032] The automated application preferably comprises at least one AI application and / or at least one machine learning application. By using artificial intelligence or machine learning, it is particularly advantageous to draw conclusions about a specific functionality, error, or faulty property when evaluating the data sets, and to take appropriate actions or provide instructions for action.

[0033] The automated application is at least one AI application and / or a machine learning application and / or comprises at least one of these applications. In particular, at least one computer vision application can also be provided. Computer vision refers in particular to the analysis of images and videos using computer programs. The aim of these analyses is, in particular, to extract information contained in the image. Depending on the design, probabilistic methods, methods of image processing, projective geometry, deep learning, and computer graphics are preferably used.

[0034] In the area of ​​AI application, any application in the field of artificial intelligence can be used which can be used advantageously with regard to the respective intended evaluation of data sets.

[0035] The use of machine learning (ML) is particularly advantageous here, with such machine learning being a subfield of artificial intelligence (AI). A central component of machine learning are algorithms and methods that enable programs to learn from data without being explicitly programmed. This allows these programs to make decisions, preferably independently.

[0036] A distinction is made between supervised, unsupervised, and semi-supervised learning. Supervised learning methods include convolutional neural networks (also known as space-invariant artificial neural networks) and further developments of convolutional neural networks, such as region-based convolutional neural networks. These modifications of conventional neural networks are particularly, but not exclusively, suitable for image processing applications, as one or more preprocessing steps are performed before the neural network, depending on the design, including, for example, convolution operations depending on the application.

[0037] In particular, sensors (e.g. optical sensors such as a color or black / white camera, thermal imaging, temperature sensors, vibration sensors, noise sensors, etc.) are used to record data from certain conditions and store them in the respective control device.

[0038] The received, processed and declared information is then transferred / trained into a CNN (convolutional neural network), preferably using machine learning or AI methods or AI applications.

[0039] Data sets from similar processing lines are particularly preferred for the automated application. This allows the automated application to learn not only from the respective processing line but also benefit from the "experience" of other similar processing lines.

[0040] In order to train the AI ​​application or machine learning application with standard values, it is preferable to pre-train them with standard values ​​of such a system that has already been repeatedly built, or to have a trained operator record the system values ​​or data sets during on-site commissioning in a trouble-free standard operation and declare them as correct, or in the event of deviations occurring, to teach the AI ​​application these as faulty.

[0041] Preferably, guided or instructed troubleshooting with a feedback loop can also be provided for training the AI ​​or the automated application in general. This allows the AI ​​to be retrained in a system-specific and controlled manner.

[0042] In expedient embodiments, at least one data set comprises at least one value. A data set can in particular comprise at least one and preferably a plurality of values, which can include, for example, the temperature, the speed, the conveying speed, the weight, and / or the like. In the simplest case, a data set can also comprise a single value, which, for example, indicates a snapshot of a specific parameter.

[0043] Preferably, at least one data set comprises at least one progression of at least one value. In particular, the development of at least one value, for example, temperature, over time can be included in a data set. Thus, conclusions about specific events can be drawn from the progression of this value and / or a plurality or multiplicity of values ​​or value progressions. In particular, the data or the development of the data on different days and / or from different shifts can also be taken into account.

[0044] Particularly preferably, at least one data set comprises at least one wear indicator (derived, for example, from longer cylinder running times, increased engine current consumption, longer braking curves, etc.), at least one event log or event and / or at least one setting change and / or depicts such properties.

[0045] In expedient further developments, at least one event log is at least one alarm event log. For example, an alarm event log can be an error message describing an incorrect property and / or an undesirable result. For example, in the area of ​​packaging systems, an alarm event log can be the incorrect weight of a filled bag or an excessive weight deviation and / or, during the subsequent palletizing of filled bags, a skewed layer pattern or a crookedly packed pallet. Depending on the system, an alarm event log can preferably also be created and / or triggered when predetermined threshold values ​​are reached and / or when drifting or tending to change values ​​are detected.

[0046] In practical embodiments, the data from more than one control device is taken into account per system module. This makes it possible, in particular, for a system module to identify multiple control devices that can receive and output different data sets. This also allows the automated application to perform a particularly precise, targeted analysis of functionalities.

[0047] Preferably, the data from the control systems of more than two system modules is taken into account. Especially in more complex processing lines, such as packing systems, which may include, among other things, a bag production line, a bag opening device, a packing machine, and a subsequent loading device, the combined view of data records from more than two system modules can be used particularly effectively to analyze functionalities or malfunctions.

[0048] Particularly preferably, in the case of an alarm event log from a system module, the evaluation device or the computing device or the automated application examines this data set with the data sets from various other system modules. In particular, in the case of an alarm event log from a control device, a comparison can be made with the data or event logs or alarm event logs from other system modules. The analysis can, for example, be carried out consecutively, simultaneously and / or sequentially. In particular, it is possible for the automated application to search for the cause of an error when an error is detected in a system module or in an alarm event log. In particular, it can be analyzed up to which processing step or in which system module all work steps or work results still corresponded to the norm or were normal.In particular, if an error occurs, a user can be notified that an action that at first glance appears obvious, such as changing or adjusting a parameter, should be avoided, as the error in question cannot be found at the obvious level, but rather at a completely different location based on the evaluation of the data records from the various control devices. In particular, the alarm event logs from different days and / or different shifts can also be considered and compared.

[0049] Preferably, at least one system module from at least one technical field is provided, which is selected from a group of technical fields comprising filling technology, packaging systems, conveyor technology, processing technology, storage technology and / or logistics.

[0050] In particular, the processing line comprises at least one packing system and / or is designed as such. A packing system can, in particular, be designed as a packing system for filling bulk goods or flowable and / or pourable solids and / or a filling system for filling liquid and / or pasty products. The containers to be packed or filled can then be, for example, sacks, barrels, pouches, bottles, containers, canisters, big bags, octabins, and / or the like.

[0051] Preferably, at least one system module of the packing system is then selected from a list, which includes: feed hopper, bucket elevator, intermediate silo, filter system (with fan), screening system, distribution chute, bunker battery, silo discharge technology (e.g. screw conveyor), mixing and / or batch silos, mixer, dosing device, distribution chute, conveyor belt, product silos, silo discharge technology, loose loading head, vehicle logistics, pre-bunker, discharge slide, (rotating) packing machine, empty bag storage, bag production, return meal collector and transport, bag plug, discharge line (e.g. comprising: discharge belt, bag cleaning), side channel compressor, belt checkweigher, bag discharge, conveyor line, metal detector, stirrup belt, bag distribution, palletizer (e.g. comprising deposit table, lifting table, etc.), empty pallet feed, full pallet transport (e.g. as Roller conveyor, chain conveyor, etc.), corner transfer unit, pressing and / or turning device, hood applicator and / or stretch wrapper, pallet removal, mobile conveyor technology (e.g., forklifts), and warehouse logistics. In particular, all system modules of the packaging system are taken from the list or the technical field of packaging systems. If a filling system is included, correspondingly known system modules for such a system can be included.

[0052] Preferably, at least one universal diagnostic interface is provided for a service technician.

[0053] In appropriate further training, maintenance and repair records are stored and taken into account in the evaluation.

[0054] Preferably, at least one sensor is provided that detects system-wide characteristics, such as unusual noise, temperature (change), dust development, and / or the like. Suitable thermal, acoustic, optical, vibration-sensitive sensors, and / or the like can be used for this purpose at a suitable location.

[0055] Preferably, based on the evaluation, notes, instructions, and / or videos are selected from a library and offered to a user. This can be done, for example, by displaying them on a monitor, using VR glasses, and / or the like. These notes, instructions, and / or videos can be created based on previous evaluations of similar systems and / or system types. The notes, instructions, and / or videos are preferably stored in a database on the local network or in a cloud application, or are accessible from anywhere (Internet).

[0056] The processing line according to the invention comprises at least one first system module with at least one first control device and at least one second system module with at least one second control device. Furthermore, it comprises at least one evaluation device with at least one computing device, which is suitable and designed to carry out at least one computer-implemented method as described above.

[0057] The processing line according to the invention also offers the advantages already described for the computer-implemented method according to the invention.

[0058] Further advantages and features of the present invention will become apparent from the exemplary embodiment which is explained below with reference to the accompanying figures.

[0059] The figures show:

[0060] Fig. 1 is a purely schematic representation of two embodiments of processing lines according to the invention arranged side by side in a lateral sectional view;

[0061] Fig. 2 is a purely schematic representation of two further embodiments of processing lines according to the invention arranged side by side in a lateral sectional view; Fig. 3 is a purely schematic representation of two next embodiments of processing lines according to the invention arranged side by side in a lateral sectional view; and

[0062] Fig. 4 shows the left processing line from Figure 2 in an enlarged view.

[0063] Figures 1 to 3 show a total of six embodiments of processing lines 1 (la to lf) according to the invention, which are assigned here as examples to the field of processing or packaging of bulk materials such as cement.

[0064] The processing line la, for example, is an open-cast mining line for rock with primary crushing, crushing and classifying plants, as well as storage silos.

[0065] The processing line lb is a mixing and storage plant for mineral building materials and a loading terminal

[0066] The processing line lc is a packing system, which includes, among other things, bulk material bagging, palletizing, and a load / weather protection hood cover.

[0067] The processing line ld is another example configuration of a packing plant.

[0068] The processing line le is a ship loading facility (especially for bulk materials) and the processing line lf is a ship unloading terminal with further processing facility.

[0069] Each of these processing lines 1a to 1f consists of a plurality of system modules 2, 4, 6, wherein a processing line 1 according to the invention basically comprises at least a first system module 2 and a second system module 3.

[0070] The exemplary embodiments of processing lines 1 according to the invention (1a-1f) shown here each comprise a first system module 2, a second system module 3, and several further system modules 6, which are only schematically indicated in the figures. These system modules 2, 4, 6 each have a control device 3, 5, 7, which are not shown in detail in Figures 1 to 3.

[0071] Each system module 2, 4, 6 can, for example, be a standalone machine, a system, and / or an assembly. Each system module comprises a control device 3, 5, 7, which receives, records, and / or stores data or values ​​relating to the status and / or operation of the system modules 2, 4, 6 and / or the like via sensors or other suitable monitoring. Such data is then stored as a data record in the storage device. Different storage locations can be provided for different data records.

[0072] In particular, characteristic values ​​and / or value curves for the operation of the corresponding module can be stored. Examples of this could be temperature, pressure, speed, and / or weight. However, a data set can also represent or include at least one wear indicator, at least one event log, and / or at least one setting change.

[0073] According to the invention, a processing line 1 comprises at least one evaluation device 50 with at least one computing device 51, wherein the evaluation device 50 or the computing device 51 can receive at least data or data sets from the first control device 3 and the second control device 5. In the exemplary embodiments shown in Figures 1 to 3, the evaluation device 50 or the computing device 51 is operatively connected to the control devices 3, 5, 7 of all system modules 2, 4, 6.

[0074] Depending on the embodiment, the evaluation devices 50 of different processing lines 1 (la-lf) can also exchange data with each other. Networking several similar processing lines 1 can also be advantageous.

[0075] The evaluation device 50 or the computing device 51 is suitable and designed to receive data records from a plurality of (at least two) control devices 3, 5, 7 and to check at least one functionality using an evaluation based on the synopsis of the data records with at least one automated application.

[0076] In this case, the evaluation device 50 or the computing device can in particular use a Kl application or a machine learning application, as described by way of example in this application.

[0077] Through the automated application, analysis, and synopsis of data sets from different system modules 2, 4, 6, and their control devices 3, 5, 7, it becomes possible to analyze even complex relationships between changes in parameters, properties, errors, and malfunctions. This allows for much better and faster localization of error sources.

[0078] An operator of such a processing line 1 or a system module 2, 4, 6 would generally be overwhelmed by the need to constantly monitor all data pools of all control devices 3, 5, 7 of all system modules 2, 4, 6, and even if the data trends were visualized in diagrams, an operator would not be able to overlay them and thus recognize deviations or complex relationships.

[0079] Figure 4 shows a purely schematic embodiment of a processing line 1, as already shown in Figure 2 (processing line lc).

[0080] This processing line 1 is designed here as a packing system 100, which comprises a plurality of system modules 2, 4, 6 with the respective control devices 3, 5, 7. The control devices 3, 5, 7 are not specifically shown, but are only indicated by the dotted arrows.

[0081] The packaging system 100 comprises in particular a packaging machine 101 as system module 2, which is designed here as an FFS packaging machine (form-fill-seal).

[0082] The packaging machine shown here comprises a net scale 102, to which a dosing device 103 is assigned, to which product to be filled is fed from a silo 110.

[0083] Further system modules 4, 6 include a conveyor line 104 with a checkweigher 105, a palletizer 106 with a storage table 107 under which empty pallets can be placed. Furthermore, a full pallet transport 108 and a hood stretcher 109 are provided.

[0084] Here, too, the processing line 1 comprises at least one evaluation device 50 with at least one computing device 51, wherein the evaluation device 50 or the computing device 51 can receive data or data sets from the control devices 3, 5, 7. The networking or data connection between the evaluation device 50 or the computing device 51 is indicated by the dashed lines. The evaluation device 50 or the computing device 51 is suitable and designed to receive data sets from the control devices 3, 5, 7 and to check at least one functionality using an evaluation based on the synopsis of the data sets with at least one automated application.

[0085] The evaluation device 50 or the computing device can draw conclusions about certain functionalities or errors by means of a Kl application or a machine learning application.

[0086] In a system such as that shown by way of example in Figure 4, it can happen that after a longer system operating time (e.g. months), the bag weights of the net scale 102 of a packing machine 101 at the beginning of a batch during the check weighing on the check scale 105 tend to be higher than those weighed by the net scale 102, even though the net scale 102 has in principle weighed correctly and nothing else has actually been changed.

[0087] Later in the batch, the weights match again. The cause is identified as the dosing device 103 upstream of the net scale 102, whose sealing effect is deteriorating due to incipient wear.

[0088] At the beginning of a batch with a high silo fill level, the product pressure is higher and leads to a slight trickle, even with the dosing device 103 closed. This trickle is no longer detected by the net scale 102, as it is already emptying into the bag to be filled. If the product pressure drops with the fill level, the seal succeeds in preventing this trickle again. Such a relationship can be clarified using the method according to the invention, or possible sources of error can at least be better narrowed down.

[0089] Because the evaluation device 50 or the computing device 51 can view or evaluate the data sets from all system modules together, individually and / or sequentially, sources of errors can be found or determined more easily.

[0090] In the example described above, the automated application, in particular using at least one AI application or at least one machine learning application, can draw conclusions about the error or the determined functionality, namely temporary deviations between the values ​​of the net scale 102 and the check scale 105, for example from the data on the fill level of the silo 110, the data of the net scale 102 and the check scale 105 and, for example, the maintenance interval of the dosing device 103 or generally the operating time of the system 100 or packaging machine.

[0091] In abstract terms, the automated application, the AI ​​application, or the machine learning application would preferably perform a permanent comparison of data and report any anomalies, such as deviations that arise.

[0092] The automated application, the AI ​​application, or the machine learning application, is preferably trained with data over a certain period of time, for example, by operating the system while it is running correctly. This training phase is preferably supervised by a trained service technician. Such a training phase can be extended, for example, if the automated application detects conditions that do not comply with the trained standard.

[0093] Depending on the design, it may also be necessary for an operator to decide whether a detected condition is still tolerable, i.e., should be considered OK in the future, or whether it represents a faulty operating condition. However, such a procedure, with operator intervention options, can also have negative effects. On the one hand, this can make the system or automated application "smarter" and, to a certain extent, more fault-tolerant. On the other hand, it can also quickly "pull aside" typical gradual changes that, if detected early, can prevent major damage because it is easier for the operator at that moment. This would then make the system or automated application worse or "dumber."

[0094] Another application example for the processing line 1 shown in Figure 4 is in the area of ​​palletizing.

[0095] The so-called layer pattern of a pallet varies greatly. (Almost) perfect layers can occur. However, less optimal layer patterns, including protruding bags, also occur from time to time. This repeatedly causes problems when packing the pallet, for example, using a stretch hood wrapper.

[0096] The reason for this, as determined by the automated application, or in this case the AI ​​application or the machine learning application, is that after a fixed number of bags have been produced, the bagging machine must check-weigh a bag.

[0097] To do this, the machine's production speed is automatically reduced. As a result, the bags arrive at the palletizer with larger gaps. Due to this delay, bag conveyor belts may stop briefly. This can cause bags to lose their shape slightly. This is usually compensated for by guide and format plates in or on the palletizer.

[0098] However, before analyzing the automated application, the operators had suspected that the apparent problem of bag shape change had to be repeatedly adjusted or compensated for by correcting the bag positioning in the palletizer via inputs in the corresponding control system. These adjustments by the operators caused the strongly fluctuating pallet layer pattern.

[0099] The automated application, or in this case the AI ​​application or machine learning application, was able to find the cause by combining the event information from the various control devices 3, 5, and 7 of the individual system modules 2, 4, and 6 (alarm event log from the hood stretcher, FFS bag event from the packing machine, and parameter change event from the palletizer) and issue appropriate instructions to the operators. An operator would not have been able to understand this complex interrelationship or the interaction of several system modules 2, 4, and 6 for the alleged error.

[0100] List of reference symbols

[0101] 1 processing line la-f processing line

[0102] 2 first system module

[0103] 3 first control device

[0104] 4 second system module

[0105] 5 second control device

[0106] 6 additional system modules

[0107] 7 additional control devices

[0108] 50 Evaluation device

[0109] 51 computing device

[0110] 100 packing machines

[0111] 101 packing machine

[0112] 102 Net scale

[0113] 103 Dosing device

[0114] 104 conveyor line

[0115] 105 Checkweigher

[0116] 106 palletizers

[0117] 107 Storage table

[0118] 108 Full pallet transport

[0119] 109 Hood stretchers

[0120] 110 silos

Claims

Claims:

1. Computer-implemented method for operating at least one processing line (1), wherein the processing line (1) comprises at least one first system module (2) with at least one first control device (3) and at least one second system module (4) with at least one second control device (5), characterized in that at least one evaluation device (50) with at least one computing device (51) is provided, wherein the evaluation device (50) is operatively connected at least to the first control device (3) of the first system module (2) and the second control device (5) of the second system module (4), and that the evaluation device (50) receives at least one data set from the first control device (3) and at least one data set from the second control device (5), and that the computing device (51) is suitable and designed toto check at least one functionality using an evaluation based on the synopsis of the data records with at least one automated application in order to then carry out at least one predetermined action.

2. Computer-implemented method according to claim 1, wherein the action to be performed comprises issuing a hint, an instruction and / or a report and / or changing and / or adjusting at least one setting.

3. Computer-implemented method according to one of the preceding claims, wherein the automated application comprises at least one AI application and / or at least one machine learning application.

4. Computer-implemented method according to one of the preceding claims, wherein the automated application takes into account data sets of similar processing lines (1).

5. Computer-implemented method according to one of the preceding claims, wherein at least one data set comprises at least one value.

6. Computer-implemented method according to one of the preceding claims, wherein at least one data set comprises at least one history of at least one value.

7. Computer-implemented method according to one of the preceding claims, wherein the data records from different days and / or from different shifts are taken into account.

8. Computer-implemented method according to one of the preceding claims, wherein at least one data set depicts / comprising at least one wear indicator, at least one event log and / or at least one setting change.

9. Computer-implemented method according to the preceding claim, wherein at least one event log is an alarm event log.

10. Computer-implemented method according to one of the preceding claims, wherein the data from more than one control device (3, 5) per system module (2, 4) are taken into account.

11. Computer-implemented method according to one of the preceding claims, wherein the data from the control devices (3, 5, 7) of more than two system modules (2, 4, 6) are taken into account.

12. Computer-implemented method according to one of the preceding claims, wherein the evaluation device (50) in the case of an alarm event log of a system module (2, 4, 6), this data record is examined with the data records of different system modules (2, 4, 6).

13. Computer-implemented method according to one of the preceding claims, wherein at least one system module (2, 4, 6) is comprised of at least one technical field selected from a group of technical fields comprising filling technology, packaging systems, conveyor technology, processing technology, storage technology and / or logistics.

14. Computer-implemented method according to one of the preceding claims, wherein the processing line (1) comprises and / or is designed as at least one packing system (100) and / or at least one filling system.

15. Computer-implemented method according to the preceding claim, wherein at least one system module (2, 4, 6) of the packing system (100) is selected from a list comprising: feed hopper, bucket elevator, intermediate silo, filter system, screening system, distribution chute, bunker battery, silo discharge technology, mixing and / or batch silos, mixer, dosing device, distribution chute, conveyor belt, product silos, silo discharge technology, loose loading head, vehicle logistics, pre-bunker, discharge slide, (rotating) packing machine, empty bag storage, bag production, return meal collector and transport, bag plug, discharge line, side channel compressor, belt checkweigher, bag discharge, conveyor line, stirrup belt, bag distribution (usually integrated in the palletizer), palletizer, full pallet transport, corner transfer device, pressing and turning device, hood cover, stretch wrapper, pallet removal, mobile Conveyor technology and / or warehouse logistics.

16. Processing line (1) comprising at least one first system module (2) with at least one first Control device (3) and at least a second System module (3) with at least one second control device (4), characterized by at least one evaluation device (50) with at least one Computing device (51) which is suitable and designed to carry out at least one computer-implemented method according to one of the preceding claims.

Images