EP4143642A1 - Container treatment machine and method for monitoring the operation of a container treatment machine - Google Patents
Container treatment machine and method for monitoring the operation of a container treatment machineInfo
- Publication number
- EP4143642A1 EP4143642A1 EP21722388.2A EP21722388A EP4143642A1 EP 4143642 A1 EP4143642 A1 EP 4143642A1 EP 21722388 A EP21722388 A EP 21722388A EP 4143642 A1 EP4143642 A1 EP 4143642A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- container
- machine
- treatment machine
- container treatment
- control unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims description 23
- 238000012544 monitoring process Methods 0.000 title claims description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 88
- 238000012545 processing Methods 0.000 claims abstract description 8
- 239000002537 cosmetic Substances 0.000 claims abstract description 6
- 238000005516 engineering process Methods 0.000 claims abstract description 6
- 238000010017 direct printing Methods 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 claims description 8
- 238000000071 blow moulding Methods 0.000 claims description 6
- 235000013361 beverage Nutrition 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000007689 inspection Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 239000000945 filler Substances 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 238000002203 pretreatment Methods 0.000 claims description 2
- BSYNRYMUTXBXSQ-UHFFFAOYSA-N Aspirin Chemical compound CC(=O)OC1=CC=CC=C1C(O)=O BSYNRYMUTXBXSQ-UHFFFAOYSA-N 0.000 claims 2
- 230000007257 malfunction Effects 0.000 description 12
- 230000008859 change Effects 0.000 description 7
- 238000001514 detection method Methods 0.000 description 7
- 238000003909 pattern recognition Methods 0.000 description 7
- 238000007639 printing Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 5
- 230000015654 memory Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000004064 recycling Methods 0.000 description 2
- 238000007493 shaping process Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 239000006071 cream Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65B—MACHINES, APPARATUS OR DEVICES FOR, OR METHODS OF, PACKAGING ARTICLES OR MATERIALS; UNPACKING
- B65B57/00—Automatic control, checking, warning, or safety devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B67—OPENING, CLOSING OR CLEANING BOTTLES, JARS OR SIMILAR CONTAINERS; LIQUID HANDLING
- B67C—CLEANING, FILLING WITH LIQUIDS OR SEMILIQUIDS, OR EMPTYING, OF BOTTLES, JARS, CANS, CASKS, BARRELS, OR SIMILAR CONTAINERS, NOT OTHERWISE PROVIDED FOR; FUNNELS
- B67C3/00—Bottling liquids or semiliquids; Filling jars or cans with liquids or semiliquids using bottling or like apparatus; Filling casks or barrels with liquids or semiliquids
- B67C3/007—Applications of control, warning or safety devices in filling machinery
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
- G05B23/0254—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/34—Director, elements to supervisory
- G05B2219/34477—Fault prediction, analyzing signal trends
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/45—Nc applications
- G05B2219/45048—Packaging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Definitions
- the present invention relates to a container treatment machine according to claim 1 and a method for monitoring the operation of a container treatment machine according to claim 8.
- Container treatment machines for treating containers are sufficiently known from the prior art. It is particularly known to "block" the container handling machines of various types (for example blow molding machines, fillers, closers and direct printing machines) so that their operation can be jointly controlled and monitored.
- various types for example blow molding machines, fillers, closers and direct printing machines
- the status of the individual container treatment machines can then be monitored, for example, and impending errors can be recognized or early recognized during the operation of the container treatment machines.
- state variables parameters that are continuously monitored and examined by appropriate computing units, such as servers in a cloud architecture, to determine whether there are any anomalies in the entirety of the state variables. If such anomalies or a specific one occur Constellation of state variables or state vectors can then be concluded that there is a malfunction or an imminent malfunction.
- neural networks are also used in corresponding cloud solutions to evaluate such large amounts of data, in particular for pattern recognition.
- the technical problem to be solved consists in specifying a method for monitoring the operation of a container treatment machine and a corresponding container treatment machine that ensure reliable operation monitoring and at the same time a high level of data security and, if possible, low use of components and realize low costs during ongoing operations.
- the container treatment machine for treating containers, such as bottles, cans or the like, in particular in the beverage processing industry, medical technology or the cosmetics industry, comprises a control unit for controlling the function of the container treatment machine and at least one treatment unit for treating the containers, the The container handling machine is designed for treating the container in exactly one way, the container handling machine comprising at least one component that can output data relating to its operating state and / or the operating state of the container handling machine to the control unit, and wherein the control unit comprises a neural network that is designed and is trained to use the data to determine whether a deviation of the operating state of the container treatment machine from a normal state is present and / or is imminent.
- component is to be understood here as any part of the container treatment machine that can record / generate / record any data relevant to its operation or the operation of other parts of the container treatment machine and transmit it to the control unit. Accordingly, these components do not necessarily have to be sensors.
- the fact that the container treatment machine is designed to treat the containers in exactly one way is to be understood as meaning that the container treatment machine performs exactly one (i.e. not two or more, but only one) functional intervention on a container or can only perform one .
- a functional intervention on a container means changing at least one property of the container. This includes, for example, shaping a preform into a container, filling the container, closing the container, providing the container with decorative elements, pretreating the outer and / or inner surface of the container and inspecting the container.
- This also includes the packaging of the container or a large number of containers, such as the compilation of several containers to form corresponding containers and the creation of a plastic cover for these containers.
- the cleaning of containers to be recycled or the crushing of the plastic containers to produce new containers from recycled plastic are to be understood as corresponding functional interventions in the container and thus as an individual treatment on the container.
- the container treatment machine With the container treatment machine according to the invention, it is possible to monitor the operation of the container treatment machine, with a further development of the monitoring based on the learning of the neural network being ensured analogously to the previous methods.
- a permanently available data connection for example via the Internet, to a server architecture set up remotely from the actual container handling machine is no longer necessary.
- the neural network is also expediently only supplied with the data that are relevant for the operation of the container handling machine, so that the neural network and in particular the computing capacity of the control unit can be correspondingly smaller. This means that, for example, the reserved storage capacity of the control unit can also be lower.
- the component comprises at least one of a sensor, a rotary encoder, a camera, a container guide, a component of the control unit, a component of the network architecture of the container treatment machine.
- control unit can be designed to output information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from a normal state is present and / or is imminent.
- the information can be visual, acoustic or haptic information or a combination of these three or two different types of information.
- the information can be shown on a display or a warning signal (acoustic) can be output. In this way, the operator can be effectively informed of any problems that may be imminent or that have already occurred during the operation of the container treatment machine, so that any downtimes or the amount of scrap can be reduced.
- the neural network is designed to learn from operation of the container treatment machine.
- the neural network can learn, for example, not only from the operation of the container handling machine in the normal state, but also from the occurrence of errors and in particular the behavior of the data before the error occurs, in order to improve error detection. In this way, despite the limited data available, reliable error detection and prediction of errors that may occur is realized.
- control unit can be designed to only supply the neural network with data during the operation of the container treatment machine that have been obtained from the component or components of the container treatment machine.
- the container treatment machine is designed as one of an inspection machine, a direct printing machine, a labeling machine, a filler, a closer, a packer, a blow molding machine, a container cleaning machine, a form filling machine, a pretreatment machine.
- This method allows reliable monitoring of the operating status of a container handling machine, while at the same time ensuring the security of the data, but also the security of the operation due to the isolation of the control unit and the neural network from external access.
- the neural network can be designed as a deep neural network (DNN).
- DNN deep neural network
- Deep Neural Networks are those neural networks that have an (extensive) structure of intermediate layers. These neural networks are particularly suitable for recognizing patterns in large amounts of data and can therefore be used advantageously in the context of monitoring the operation of the container handling machine.
- the neural network learns from the operation of the container handling machine.
- control unit only forwards data of the component or the components of the container treatment machine during operation of the container treatment machine for learning to the neural network.
- control unit transmits additional data to the neural network during maintenance of the container handling machine and the neural network learns from the additional data.
- a data volume of additional data (for example several 100 MB of additional data) can be transmitted to the container handling machine and in particular to the neural network for learning via a suitable data carrier (USB stick, external hard drive or the like).
- a suitable data carrier USB stick, external hard drive or the like.
- the additional data include data about an operating state of at least one further container treatment machine of a container treatment system to which the container treatment machine belongs; and / or wherein the additional data include data about an operating state of a container handling machine of the same type.
- the use of data from the same container treatment system can be advantageous because it can also influence the operation of the container treatment machine directly or indirectly.
- the use of data on the operating status of container handling machines of the same type can be used to learn errors that only occur after a large number of operating hours in the neural network, so that an early detection of these errors, such as only after 10 years of the Operation of a single container treatment machine can occur statistically in a timely manner.
- the component can comprise at least one of a sensor, a rotary encoder, a camera, a container guide, a component of the control unit, a component of the network architecture of the container treatment machine and / or the component can transmit the data to the control unit in real time.
- the data output by these components can be used advantageously for the detection of impending or occurring errors.
- control unit outputs information to an operator when the neural network determines that a deviation of the operating state of the container treatment machine from a normal state is present and / or is imminent.
- This information can help the operator to recognize occurring errors in good time and, for example, to stop the operation of the container treatment machine or to carry out maintenance.
- Fig. 1 is a schematic view of a container treatment machine according to an embodiment
- FIG. 2 shows a schematic view of the method running within the control unit.
- FIG. 3 shows a schematic illustration of the method, taking additional data into account
- the container treatment machine 100 is designed as a direct printing machine that can at least partially provide the container with a print image as a decoration element.
- the container treatment machine or the container treatment machines are in particular container treatment machines that are used in the beverage processing industry or the cosmetics industry or medical technology to treat containers in any way. These are in particular machines that are designed to produce containers with the usual dimensions in the above-mentioned industries, such as 11, 21, 1, 51, 0.51, 0.751 bottles or jars for creams with a volume of 100ml, 150ml , 200ml or syringes or containers with a volume of 5ml, 10ml or 20ml.
- the direct printing machine 100 comprises a carousel 101 with a series of container receptacles 102 in which containers for transport along the carousel (along the shown direction of rotation R of the carousel) can be received.
- the container receptacles 100 are basically known devices from the prior art and can, for example, comprise stationary plates or turntables and centering bells assigned to them, so that the container can be clamped between the plate on the one hand and the centering device on the other hand.
- a number of printing modules 103, 104 and 105 are located on the periphery of the carousel 101. These are arranged and designed in such a way that they can apply printing ink to the surface of the container.
- print modules While three print modules are shown here, more or fewer print modules can also be provided.
- the arrangement on the periphery of the carousel is also not restrictive. Printing modules that rotate with the individual container receptacles 102 are also conceivable, so that each container in its container receptacle can be printed by the modules assigned to the container receptacle 102 during transport along the carousel 101.
- transport devices for the containers are shown schematically.
- the transport device 106 is designed as a feed device so that it can feed non-printed containers to the direct printing machine.
- the transport device 107 is designed as a transport device which can remove containers from the carousel 101 after printing and remove them from the direct printing machine 100.
- the container treatment machine 100 comprises a control unit 130.
- this control unit is connected to individual components 131 to 137 of the container treatment machine, for example via a number of lines for data exchange 138. Wireless connections are also conceivable here.
- each container receptacle 102, each printing module 103 to 105, as well as the carousel 101 and the transport devices 106 and 107 comprise components 131 to 137 assigned to them.
- these components can be understood as “sensors” which can record data on the operating state of the part of the container handling machine assigned to them (for example, component 135 from printing module 104) and feed it to control unit 130.
- the components 131 to 137 do not have to be Sensors.
- (moving) parts of the container treatment machine come into consideration as components, which can output data relating to an operating state either about themselves and / or the entire container treatment machine and / or other parts of the container treatment machine.
- a servo motor can be viewed as such a component.
- the servomotor can, for example, be part of the container receptacle 102, but usually does not provide any information to the control unit 130 about the centering device of the container receptacle 102, but only about its own operating state, such as whether the operating voltage is correct or control signals are correctly received from the control unit will.
- temperature sensors moisture sensors, pressure sensors, light sensors, speed sensors and the like come into consideration as sensors, since all values measured by such sensors can usually be indicative or relevant for the operating state of a container handling machine.
- Cameras can also be used as components, which are used, for example, as an inspection device in the implementation of the container handling machine, in order to check the containers.
- the components are sensors, rotary encoders, cameras, container guides or parts of the control unit (such as the network cables or the processor or the internal memory or the like) or generally part of the network architecture (shown here schematically by the data connections 138) of the Container handling machine.
- the network architecture can include all devices and components used for the purpose of data exchange (in particular processors, memories, data connections and the like). These can provide information about their status to the control unit in order to enable control and monitoring of these components.
- the embodiment of the container treatment machine 100 shown here is only to be understood as an example and the invention is not restricted to use in the field of direct printing machines.
- the container treatment machine can also be a blow molding machine, a labeling machine, an inspection machine, a filler, a closer, a packer, a blow molding machine, a container cleaning machine, a recycling machine for plastic containers, a Act form filling machine or a pre-treatment machine.
- each container treatment machine which is implemented according to embodiments of the invention treats containers in exactly one way.
- the handling of the container includes a functional change in the container or an inspection.
- a functional change can be seen, for example, in printing, labeling, closing, filling, shaping, shredding, recycling, cleaning, packaging or combining with other containers.
- the container treatment machine performs precisely such a functional treatment of a container.
- the transport of the containers by the transport devices 106 and 107 or along the periphery of the carousel in the container receptacles 102 is not to be seen as a separate functional change of the container, but as part of such a change, since the functional change for a direct printing machine, for example Treatment can be seen in the fact that a print image is applied to the container, but the container is inevitably transported in some way during this time.
- container treatment machine does not include mere transport devices, but the treatment of the container within the meaning of the invention can also include transport, in addition to the functional change of the container, as described above.
- control unit 130 has a neural network or is assigned such a network and the control unit transfers the data received from the at least one component (for example component 134) about the operating state of the component and / or the container handling machine to the neural network Net feeds.
- the neural network is preferably such a neural network that has been trained to use data on the operating state of components and / or the entire container handling machine to determine whether the machine is in normal operation or in the normal state or whether a malfunction has occurred (for example, a direct print module has failed or the ink level is too low) or such a malfunction is (imminent).
- the neural network has preferably been trained in such a way that it is specialized on the basis of the data obtained from the components as part of a pattern recognition for which neural networks and particularly preferably deep neural networks (DNN) are specialized, for example by comparison with already known patterns (of parameters) draws conclusions as to whether the operation of the container treatment machine is running correctly.
- DNN deep neural networks
- the neural network can be trained to view a specific curve of the torque applied to a servomotor over an entire process cycle as the “normal state” of the turntable. In this sense, even slight changes can be interpreted by the neural network as data that still characterize normal operation. However, if a change occurs that does not match the normal state within the framework of the pattern recognition, the neural network can recognize this either as an indication of an imminent malfunction or as a malfunction that has occurred and thus determine that no operating state of the container handling machine is normal. State exists or a deviation from the normal state is imminent.
- the neural network and / or the control unit can preferably be designed in such a way that information is output to an operator of the container handling machine.
- This information can indicate to the operator, for example, that there is a malfunction or that it is about to occur.
- the information can be output to the operator, for example, on a display or other suitable display device of the control unit or on a display device assigned to the control unit.
- Corresponding information can thus be transmitted to the operator on a mobile terminal device carried by him, such as a tablet computer, a smartphone or the like, and displayed on its display device. Acoustic and / or haptic information is also conceivable here.
- an acoustic message in the sense of an acoustic alarm or beep or a haptic signal, such as a vibration of the mobile device carried by the user (smartphone, tablet or the like), can be used by the operator indicate that a malfunction is imminent or threatened.
- the information made available to the operator can differ, in particular, depending on whether a deviation from the operating state is only imminent or already exists.
- FIG. 2 shows an embodiment of the method according to the invention, in which the neural network evaluates the data transmitted to the control unit by the individual components (see also FIG. 1).
- control unit receives data only from components 131 which are assigned to the container handling machine in which the control unit is implemented.
- the control unit can be in a Embodiment Data from several or all components 131-137, which have already been described with reference to FIG. 1, are obtained and evaluated (with the aid of the neural network).
- the control unit can comprise a receiving device 251 for receiving the data from the components 131.
- This receiving unit 251 can also be designed as a pre-processing unit that already evaluates, manipulates, checks or processes (part of) the data received from the individual components before these data are ultimately fed to the neural network 253.
- the receiving unit 251 can furthermore be assigned a processor and / or storage unit 252 in which processing (of a part) of the data and / or storage of the data can also be carried out.
- the data are transmitted from the receiving unit 251 to the neural network 253, if necessary after a corresponding preprocessing.
- the neural network is preferably implemented as a pre-learned neural network in the container handling machine, the learning of the neural network preferably being carried out in such a way that it is trained to operate the container handling machine in whose control unit it was implemented. This means that a neural network 253 implemented in a control unit 130 of a direct printing machine has been learned with different parameters than a normal network of a control unit of a blow molding machine.
- the basic architecture of the neural networks can, however, be identical. In particular, they can have the same number of intermediate layers and / or nodes within the neural network.
- the learning of the neural network usually only changes the individual parameter values assigned to the nodes and layers of the neural network, so that the pattern recognition leads to different results in differently learned neural networks.
- the basic process of learning neural networks is, however, sufficiently known from the prior art.
- the neural network can access a memory 255 assigned to it, for example, in order to call up the learned parameters. Based on the evaluation of the data, the neural network then finally recognizes whether the data obtained are characteristic of a normal state of operation of the container handling machine or of a deviation or an imminent deviation from the normal state. The neural network can then transfer this information, for example, to the evaluation device 254 of the control unit 130, which evaluates the result of the neural network and, if necessary, outputs information to an operator, as has already been explained above. It is particularly preferred if the neural network learns during operation of the container handling machine, that is, it automatically carries out a further refinement of the pattern recognition that has already been learned.
- the neural network can be designed in such a way that it improves the parameters stored in the memory 255 during operation of the container handling machine to the effect that a recognized normal operation and / or a recognized malfunction and / or a recognized impending malfunction are included in the parameters that are required for the pattern recognition of normal operation and / or a corresponding pattern recognition of an impending and / or already occurred error are characteristic to improve during operation.
- the neural network preferably receives only data from components of the container treatment machine that installs the control unit 130 in which the neural network is involved (it does not matter whether it is operating in the normal state or an incorrect operation) is heard.
- the neural network preferably does not receive any data from other container treatment machines at least during the operating time of the container treatment machine, be it container treatment machines of the same container treatment plant or from container treatment machines that are distributed anywhere in the world, but belong, for example, to the same type of container treatment machine.
- control unit 130 does not receive such data (further components) from further container treatment machines. In normal operation, however, it is provided that this data is then at least not passed on to the neural network. This ensures that the neural network is not supplied with possibly compromised data via an unsafe data line, which could ultimately lead to malfunctions.
- the neural network can be trained with additional data from other container handling machines (either of the same type and / or of a different type).
- FIG 3 shows an embodiment in which the container treatment machine, to which the control unit 130 and the neural network 253 installed therein is assigned, is not operated in normal operation, but is operated, for example, in a maintenance mode. It is known that approximately annual maintenance cycles are carried out by container treatment machines, during which operation is stopped and, for example, worn parts are replaced. the According to the invention, however, the time sequence of such maintenance cycles is not restricted and can in particular be periodic or also non-periodic (for example in the case of an unplanned repair).
- data are transferred to the control unit 130 via an external data carrier 362 or via a corresponding line for data exchange with other container handling machines and thus from a component of such a container handling machine.
- These data can be data on the operating status of a container treatment machine of the same container treatment system in which the actual container treatment machine is also arranged, in which the control unit 130 is also arranged.
- it can also be data from a container treatment machine (of the same type) from another container treatment system that is set up, for example, in another region of the world.
- This pre-processing can also include processing of this data at a central point, for example in a server architecture outside the container handling machine, and make a modification of parameters of the neural network immediately available so that not original data from components, but rather updates "the parameters of the neural network can be made available from outside the container handling machine as part of the maintenance cycle.
- these additional data are not made available via an Internet connection or other network connection, but rather via a data storage unit to be connected to the container handling machine, which is for example protected against unauthorized access via suitable security mechanisms or whose data was previously checked by a (generally known) security program.
- a connection to an external data source can also be established via a secure Internet connection, in particular via a VPN connection, in order to prevent access by unauthorized third parties.
- the components such as those described in FIG Monitoring of the operation of the container treatment machine is possible. It depends largely on the component or the component of the container treatment machine monitored by the component as to the time intervals at which data relevant to the operating state of the component and / or the container treatment machine can be sensed and transmitted. Some components, such as rotary encoders or servomotors, make monitoring within a tenth or a few hundredths of a second useful. Monitoring the level of an ink supply or monitoring a label supply of a labeling machine, however, can make a less time-resolved monitoring appear sensible.
- monitoring in a temporal order of magnitude of the process cycle for example a few tenths of a second between the application of a first label and the application of a second label to a subsequent container, can appear sensible.
- the invention is not limited with regard to the time intervals or sequence with which data are recorded and transmitted to the control unit.
- the data are preferably transmitted to the control unit and, accordingly, to the neural network with almost no time delay, in particular special in practically real time (taking into account the time delay caused by the data transfer).
- neural network is basically to be understood in such a way that other adaptive algorithms can also be used instead of the neural network in the above embodiments.
- the invention is therefore not limited to the application of neural networks, but can also be implemented with other adaptive algorithms in accordance with the above embodiments.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Filling Of Jars Or Cans And Processes For Cleaning And Sealing Jars (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102020111674.8A DE102020111674A1 (en) | 2020-04-29 | 2020-04-29 | Container handling machine and method for monitoring the operation of a container handling machine |
PCT/EP2021/060621 WO2021219499A1 (en) | 2020-04-29 | 2021-04-23 | Container treatment machine and method for monitoring the operation of a container treatment machine |
Publications (1)
Publication Number | Publication Date |
---|---|
EP4143642A1 true EP4143642A1 (en) | 2023-03-08 |
Family
ID=75746585
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP21722388.2A Pending EP4143642A1 (en) | 2020-04-29 | 2021-04-23 | Container treatment machine and method for monitoring the operation of a container treatment machine |
Country Status (5)
Country | Link |
---|---|
US (1) | US20230266752A1 (en) |
EP (1) | EP4143642A1 (en) |
CN (1) | CN115605813A (en) |
DE (1) | DE102020111674A1 (en) |
WO (1) | WO2021219499A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102021112484A1 (en) | 2021-05-12 | 2022-11-17 | Krones Aktiengesellschaft | Labeling machine and method for configuring a labeling machine |
DE102021131684A1 (en) * | 2021-12-01 | 2023-06-01 | Krones Aktiengesellschaft | Predictive maintenance of a container treatment plant |
DE102022123019A1 (en) | 2022-09-09 | 2024-03-14 | Krones Aktiengesellschaft | LABELING DEVICE |
CN117707097B (en) * | 2024-02-04 | 2024-05-10 | 广州泽亨实业有限公司 | Machining center control method and system |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5121467A (en) | 1990-08-03 | 1992-06-09 | E.I. Du Pont De Nemours & Co., Inc. | Neural network/expert system process control system and method |
US5566092A (en) | 1993-12-30 | 1996-10-15 | Caterpillar Inc. | Machine fault diagnostics system and method |
US5718852A (en) * | 1994-05-10 | 1998-02-17 | The Clorox Company | Process controlling a blow molding machine |
EP0950608B1 (en) * | 1998-04-15 | 2003-11-26 | Tetra Laval Holdings & Finance SA | Method of monitoring transverse sealing in a packaging unit for continuously forming sealed packages containing pourable food products and packaging unit |
US6416711B2 (en) * | 1998-11-06 | 2002-07-09 | Fmc Technologies, Inc. | Controller and method for administering and providing on-line handling of deviations in a rotary sterilization process |
JP4499601B2 (en) * | 2005-04-01 | 2010-07-07 | 日精樹脂工業株式会社 | Control device for injection molding machine |
EP2998894B1 (en) * | 2005-07-11 | 2021-09-08 | Brooks Automation, Inc. | Intelligent condition monitoring and fault diagnostic system |
US20090226032A1 (en) * | 2007-09-28 | 2009-09-10 | Matthew Allen Merzbacher | Systems and methods for reducing false alarms in detection systems |
DE102011017448A1 (en) * | 2011-04-18 | 2012-10-18 | Krones Aktiengesellschaft | Method for operating a container treatment plant with fault diagnosis |
DE102017108546A1 (en) * | 2017-04-21 | 2018-10-25 | Sig Technology Ag | Production parameter history view as part of a user interface to monitor and / or control a packaging plant |
JP6693919B2 (en) * | 2017-08-07 | 2020-05-13 | ファナック株式会社 | Control device and machine learning device |
KR20210059532A (en) * | 2019-11-15 | 2021-05-25 | 엘지전자 주식회사 | Home appliance and method for controlling home appliance |
-
2020
- 2020-04-29 DE DE102020111674.8A patent/DE102020111674A1/en active Pending
-
2021
- 2021-04-23 EP EP21722388.2A patent/EP4143642A1/en active Pending
- 2021-04-23 US US17/997,350 patent/US20230266752A1/en active Pending
- 2021-04-23 WO PCT/EP2021/060621 patent/WO2021219499A1/en unknown
- 2021-04-23 CN CN202180031274.5A patent/CN115605813A/en active Pending
Also Published As
Publication number | Publication date |
---|---|
DE102020111674A1 (en) | 2021-11-04 |
WO2021219499A1 (en) | 2021-11-04 |
CN115605813A (en) | 2023-01-13 |
US20230266752A1 (en) | 2023-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP4143642A1 (en) | Container treatment machine and method for monitoring the operation of a container treatment machine | |
DE102011006786B4 (en) | Product sensor, product with product sensor, system and method for communication between product sensor and system | |
EP3768902B1 (en) | Method and device for maintaining and/or repairing a construction machine | |
EP2447843B1 (en) | Method for verifying an application program of an error-free memory-programmable control device and memory-programmable control device for carrying out the method | |
EP3462260A1 (en) | Method and system for monitoring the condition of a production device | |
EP3411239B1 (en) | Printing machine for printing on containers | |
DE19814102C2 (en) | Data transmission method | |
EP2698213A1 (en) | Marking device for marking containers, container treatment device and a method for marking containers | |
WO2018024365A1 (en) | Packaging machine and method for providing a control program therefor | |
EP3745217B1 (en) | Device for monitoring the data processing and data transmission in a safety system | |
EP3474564A1 (en) | Sensor and method for serial transmission of data relating to the sensor | |
DE102017215508A1 (en) | Automation system with at least one field device and at least one control unit | |
EP3098673A1 (en) | Method and device for automated validation of security features on a modular security system | |
EP1811722A2 (en) | Method and device for converting messages on multiple channels into a safe single channel message | |
EP2035901B1 (en) | Replaceable drive system | |
DE102017007909A1 (en) | Production control equipped with a function for identifying the cause after an operation stop of a production facility comprising manufacturing facilities | |
WO2022238032A1 (en) | Labelling machine and method for configuring a labelling machine | |
EP2539782B1 (en) | Method for sensing events which occur in an electronically controlled production machine | |
DE102020131365A1 (en) | System and method for operating a system for treating containers | |
DE10319064A1 (en) | Method and device for controlling a manufacturing unit | |
DE102006056214B4 (en) | Industrial robot with a tool or sensor and method | |
EP1832417A2 (en) | Processing machine with at least a driving unit with at least drive controller controlled by a motor | |
DE102019105135A1 (en) | Method for monitoring an industrial network | |
DE102011006784A1 (en) | Method for adjusting manufacturing plant used in industrial production environment, involves selecting operation mode of plant among several operation modes based on plant state determined according to plant dependant information | |
EP3462263A1 (en) | Method and system for monitoring the condition of a production device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: UNKNOWN |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE |
|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE |
|
17P | Request for examination filed |
Effective date: 20221125 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
DAV | Request for validation of the european patent (deleted) | ||
DAX | Request for extension of the european patent (deleted) | ||
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: EXAMINATION IS IN PROGRESS |
|
17Q | First examination report despatched |
Effective date: 20240515 |