Container treatment machine for treating containers

Abstract

The invention relates to a container treatment machine for treating containers, comprising at least two treatment units for treating containers, at least one sensor for determining a state parameter indicating a state of the containers after and / or during the treatment and / or an operating state of the at least one treatment unit, and a control unit, the control unit is configured to detect whether there is a deviation and a cause of the deviation in operation of the container processor based on the state parameter and the digital image of the container processor and at least one operating parameter of the processing unit, and to control the container processor based thereon.

Description

[0001] The present invention relates to a container processor for processing containers according to claim 1, and a method for controlling the container processor according to claim 7. Background Technology

[0002] Container processors and their control methods are largely known from the prior art. To achieve specific objectives in container processing, operating parameters are specified for the container processor, which then uses these parameters to process containers during operation. During operation, deviations or disturbances may occur, which are reflected in status parameters, such as indicators of the operation of the container processor itself or the containers being processed. This may indicate an error and is typically monitored by the operator for intervention if necessary.

[0003] However, as container processors become increasingly complex, especially with the increasing number of components, each of which introduces deviations in the operation of the container processor, manual monitoring becomes quite difficult and may result in errors being detected too late or the cause being incorrectly identified.

[0004] Purpose

[0005] Therefore, based on the known prior art, the technical problem to be solved is to specify a container processor for handling containers and a method for controlling the container processor, which can reliably identify any deviations in operation and respond to them appropriately.

[0006] Solution

[0007] According to the invention, this objective is achieved by the container processor according to claim 1 and the method for controlling the container processor according to claim 7. Advantageous improvements of the invention are included in the dependent claims.

[0008] The container processor according to the present invention includes at least two processing units for processing containers, at least one sensor for determining state parameters, and a control unit, wherein the state parameters indicate the state of the container after and / or during processing and / or the operating state of at least one processing unit, wherein the control unit is configured to detect whether there is a deviation in the operation of the container processor and the cause of the deviation based on the state parameters of the container processor and digital images and at least one operating parameter of the processing unit, and to control the container processor accordingly.

[0009] The control unit is understood to be, for example, a computer with allocated memory and processor or other suitable data processing device that communicates with sensors and container processors.

[0010] State parameters indicating the state of a container after or during processing, or the operational state of at least one processing unit, can be, for example, physical, chemical, or thermal parameters of the container being processed, or such parameters determined during container processing. Alternatively or additionally, state parameters can also be measured parameters indicating the operational state of a processing unit. Essentially, measured state parameters are actual state parameters and therefore can indicate the actual state of the processing unit and / or its components (e.g., actuators, valve circuits, or pumps) and / or functional groups and / or the container. In this context, a functional group is understood as multiple cooperating components and / or processing equipment (processing units). This can include, for example, the actual medium flow or temperature associated with the operation of the processing unit. Furthermore, state parameters can include, for example, drive torque, valve switching clearance, or heating profiles, which indicate the operational state of the processing unit and / or functional groups. Typically, state parameters are measured actual values ​​associated with the container processing machine, rather than predetermined parameters for operating the container processing machine.

[0011] In contrast, the operating parameters of the processing unit are, for example, parameters predetermined by the control unit for operating the container processor. These may include, for example, the heating power of the heating element, the flow rate of the cleaning medium in the cleaning nozzle, the drive torque of the machine drive or dirt discharge system or bottle loading or unloading, the switching cycle and switching interval of the media guidance, or the power and / or frequency of the pump operation.

[0012] A processing unit should be understood as any element of a container handling machine that can act directly and / or indirectly chemically, thermally, and / or mechanically on the container. Indirect action refers to the influence on the container handling process where the processing unit does not directly interact with the container itself but affects its handling, such as a heating element of an immersion bath or its water supply. Possible processing units are, for example, cleaning nozzles capable of applying cleaning media to the container or ultrasonic transmitters capable of emitting ultrasonic waves in the direction of the container to remove impurities from it. These also include, for example, processing units that apply labels to the container or apply printed images to the container surface. These may also include, for example, filling members capable of filling products into the container. The invention is not limited to processing units.

[0013] The fact that the control unit controls the container processor based on possible detected deviations should be understood as meaning that controlling the container processor based on the detection of deviations in the operation of the container processor is different from the situation where there are no deviations in the operation of the container processor.

[0014] A digital image of a container processor should be understood as a parameterized digital representation of the container processor and its operation. This representation specifically includes the probability of determining processing results, or particularly state parameters, based on the operating parameters of the container processor's processing units. Discrepancies can then be detected by comparing the state parameters determined by the digital image of the container processor with those determined by sensors.

[0015] Based on digital images, possible changes in operating parameters or possible changes in machine behavior indirectly related to operating parameters can be identified as the causes of deviations.

[0016] Using the container processor according to the invention, deviations in the operation of the container processor can be continuously checked. Therefore, despite the complexity of the container processor, errors or impending errors in its operation can be detected and identified promptly and reliably. This allows for targeted intervention in the operation of the container processor when problems occur. Furthermore, monitoring the status of the container processor is possible, for example, and this may include outputting error and / or notifications to third parties (e.g., to maintenance departments to plan optimized maintenance and upkeep procedures).

[0017] The control of the container handler may include changing at least one operating parameter and / or providing the operator with an output indicating the detected deviation.

[0018] In particular, operating parameters can be changed in a way that reduces or completely eliminates the deviation, for example, by addressing the identified causes. The output may include technical information, including the deviation and / or its causes and / or possible solutions for eliminating the deviation, and in particular may include graphical output on a user interface (e.g., a monitor).

[0019] This implementation method ensures continuous operation even in the event of potential deviations during operation.

[0020] The control unit can be configured to use a prediction module, including probabilistic models, neural networks, or fuzzy logic, to detect the presence of bias and the cause of the bias.

[0021] The prediction module is understood as a software component or software module. The probabilistic model should be understood as a closed mathematical and deterministic model (or associated program code) that allows the determination of possible deviations in the output based on state parameters and the current operating parameters of the digital image and processing unit, and preferably the determination of the potential causes of the deviations with relevant probability values.

[0022] As neural networks, specialized training can be used to determine deviations from state parameters, digital images, and processing parameters. For this purpose, neural networks for pattern recognition in operational parameters are largely known from existing technologies. Even in complex systems, the use of probabilistic models, neural networks, or fuzzy logic allows for the reliable identification of possible causes of deviations and the detection of the deviations themselves.

[0023] In particular, the prediction module can be configured to learn based on deviations detected during the operation of the container processor.

[0024] Using this implementation, even during continuous operation, the prediction module can respond sensitively to, for example, wear of components or processing units of the container processor, so that deviations can be reliably identified even during long-term operation.

[0025] It can provide deviation indicators of operational errors or impending operational errors.

[0026] Operational errors are understood as actual mistakes that occur during machine operation. This may include malfunctions of the processing unit or the container's status parameters exceeding or falling below a certain limit. If, despite the deviation, the machine operates within specified limits (e.g., the status parameters remain within the limit values ​​or lie between a first limit value characterizing the deviation and a second limit value characterizing the operational error), the deviation indicates an impending operational error. Using this implementation, not only can errors that occur be reliably responded to, but potential operational errors can also be avoided, or the operation of the container processor can be intervened in a timely manner to prevent serious operational errors.

[0027] Container handling equipment can be a cleaning machine or includes a cleaning machine.

[0028] Since cleaning machines (used herein synonymously with container cleaning machines) typically comprise a large number of processing units, the advantages of the present invention can be particularly advantageously utilized as a container cleaning machine when implemented within the framework of a container handling machine.

[0029] According to the present invention, a container processor is also provided, comprising at least two processing units for processing containers, at least one sensor for determining state parameters, and a control unit, wherein the state parameters indicate the state of the container after or during processing, or the operating state of at least one processing unit, wherein the control unit detects whether there is a deviation in the operation of the container processor and the cause of the deviation based on the state parameters of the container processor, digital images, and at least one operating parameter of the processing unit, and controls the container processor accordingly.

[0030] This method ensures reliable operation of the container processor even under conditions where deviations may occur.

[0031] The control of the container handler may include changing at least one operating parameter and / or providing the operator with an output indicating the detected deviation.

[0032] This implementation method can reliably eliminate any deviations that occur.

[0033] In the context of the second alternative, the output can include at least two possible causes of the deviation. This provides the operator with guidance to optimize the troubleshooting of potential errors.

[0034] In one implementation, a control unit is provided that uses a prediction module, including a probabilistic model, neural network, or fuzzy logic, to detect the presence and cause of a deviation. This implementation achieves reliable detection of the deviation and its cause.

[0035] The prediction module can learn based on deviations detected during the operation of the container processor. This implementation allows the prediction module to be adjusted so that it can account for any wear and tear even during continuous operation in order to detect deviations.

[0036] When the container processor starts, the prediction module and / or digital images can be verified.

[0037] For example, startup can be the first startup of the container processor, as part of a controlled test run of the container processor and / or its functional groups and / or its components, and / or include a restart of the container processor, such as after a specific maintenance interval or type conversion. Here, validation of the predictive model and / or digital image can specifically include setting parameters characterizing the predictive model or image so that these parameters can be used to reliably distinguish between deviations and correct operation present in a controlled environment.

[0038] This implementation method enables a prediction module specifically designed for container processors, thereby allowing for more reliable detection of deviations and their causes.

[0039] It can provide deviation indicators of operational errors or impending operational errors.

[0040] Therefore, it can both handle actual errors in the container processor and preventatively change the operation of the container processor in the event of an impending operational error.

[0041] The container handling machine can be a cleaning machine or includes a cleaning machine. Utilizing this implementation method, the advantages of the method according to the invention are advantageously applied to cleaning machines that typically include multiple handling units.

[0042] The method may include detecting deviations for each container being processed or at predetermined time intervals during the operation of the container processor.

[0043] Detecting potential deviations for each processed container allows for improved deviation detection. Detecting deviations at predetermined time intervals (e.g., minutes or hours) reduces computational complexity while still allowing for reliable detection of deviations affecting the processing of all containers simultaneously. Brief description of the attached figures

[0044] Figure 1 A schematic diagram of a container processor is shown;

[0045] Figure 2 A flowchart of a method for controlling a container processor is shown. Detailed Implementation

[0046] Figure 1 A container processor 100 according to an embodiment is shown. Figure 1 In the illustration, the container handling machine 100 is shown as a container cleaning machine (also called a cleaning machine). This design is not mandatory, and the invention is applicable to all other container handling machines, such as blow molding machines, printing machines, labeling machines, inspection machines, or filling machines.

[0047] Container handling machine 100 typically includes at least two, preferably multiple, processing units 101, 102, and 103, for processing containers 130, such as bottles or jars. For this purpose, container handling machine 100 may include, for example, a transport device 111 along which containers 130 are transported by the container handling machine and optionally other machines in a transport direction T. In the embodiment of the container washing machine shown herein, containers 130 are transported in the transport direction T along a substantially linear transport device 111, which may transport containers 130, for example, by a neck handling method. Other embodiments are also conceivable, in which containers 130 are, for example, at least partially conveyed by a transport star to a container handling machine with a turntable supported in a manner rotatable about a rotational axis, and again conveyed from the container handling machine, for example, by a transport star. The invention is not limited to the transport equipment performing container transport.

[0048] The container handler 100 also includes at least one sensor 141, 142, 143, or 144 configured to determine state parameters. Although sensors are discussed herein, it should be understood that each of these sensors 141, 142, 143, and 144 can also be understood as a set of sensors capable of measuring the same or different physical and / or chemical quantities.

[0049] State parameters indicate the state of the container or the operational state of at least one processing unit. The state of the container can, for example, characterize the container's properties after or during processing by the processing unit. When a state parameter indicates or indicates actual chemical or physical parameters of the container processor (e.g., the actual temperature of the immersion bath), it can be understood as indicating the operational state. It is also conceivable to record multiple state parameters, each of which itself indicates the state of the container and / or the operational state of the processing unit. State parameters indicating the operational state of a processing unit can be, for example, actual values ​​of physical or chemical variables.

[0050] As Figure 1Taking a container cleaning machine as an example of an embodiment of the container handling machine 100, for instance, the first two processing units in the container transport direction T may be immersion baths through which the container 130 is guided. Sensors 141 and 142 may be, for example, temperature sensors that can measure the current temperature of the medium (e.g., hot water) in the respective immersion baths 101 and 102. However, one or both of sensors 141 and 142 may also determine the chemical composition of the immersion medium in the immersion bath, or provide this as a supplement or alternative to temperature determination. Alternatively or additionally, sensors may be provided that, for example, measure the heat released by heating elements in the area of ​​the immersion bath used to heat the immersion medium and / or measure the flow rate of the immersion medium, for example, through a valve.

[0051] Downstream of immersion baths 101 and 102, as an example of another processing unit 100, nozzles can deliver a medium to container 130. This medium can be, for example, cold or warm water or an alkaline solution. Sensors 143 assigned to this processing unit 103 can, for example, measure the flow rate or output of the medium from the respective nozzle. Alternatively or additionally, measurements of the medium's temperature or chemical composition can be provided.

[0052] Another sensor 144 is disposed downstream of the processing unit 103, for example in the form of an optical sensor, for optical inspection of the container 130. The optical sensor may be a camera, for example in the form of a CCD camera, and can record images of the container, so that, in the case of a cleaning machine, it can be checked for contamination of the container.

[0053] As previously stated, the design of the container processor 100 as a container cleaning machine is not mandatory. Other implementations, such as a labeling machine, can also be provided. In the case of a labeling machine, the first processing unit can apply adhesive to the surface of the container or label, for example, in a known manner. As an example, a sensor can be provided that determines the temperature of the applied adhesive or the adhesive in the storage container in order to determine a state parameter (the corresponding temperature of the adhesive). Downstream of the labeling machine's application device that applies the label to the container, a camera can again be positioned as a sensor that records an image of the labeling container, such that the image information can be used substantially as a state parameter, which can be used, for example, later to detect whether the label is correctly positioned on the container 130.

[0054] The container processor 100 also includes a control unit 180 (e.g., a computer including a processor and allocated memory). According to the invention, the control unit 180 is configured to detect whether there is a deviation in the operation of the container processor and the cause of the deviation based on at least one state parameter and digital image of the container processor and at least one operating parameter of the processing unit, and to control the container processor 100 accordingly.

[0055] For this purpose, the control unit may include a prediction module 181, which includes, for example, a probabilistic model or a neural network, to detect whether a bias exists and the cause of the bias.

[0056] Therefore, the digital image of the container processor is preferably configured such that it can determine state parameters based on the operating parameters of the container processing unit, as described above. Thus, set state parameters are determined based on the current operating parameters using the digital image. These can be compared with state parameters measured or determined by sensors. Then, a probabilistic model, neural network, fuzzy logic, or time model can be used to detect the presence of a deviation and / or the cause of that deviation based on the deviation between the set state parameters and the state parameters determined by the sensors.

[0057] A time model describes the validity of statements and formulas over a specific time span. For example, a time model can represent the relationship between different events or states over time.

[0058] In this scenario, a comparison between the determined and set state parameters based on a digital image can be considered an indication of no deviation if the difference between the determined state parameter and the set state parameter does not exceed or falls below a certain limit value, or lies within a specific allowable parameter range defined by the lower and upper limits surrounding the set state parameter. If the deviation between the determined state parameter and the set state parameter exceeds the allowable deviation limit, the control unit can first detect the deviation. Then, the neural network, probabilistic model, or fuzzy logic of the prediction module can identify the possible causes of this deviation.

[0059] For example, if the detection shows that a specific state parameter assigned to a particular processing unit consistently deviates across multiple containers, the prediction module can identify this as the cause, thereby identifying the particular processing module as the cause of the deviation. For instance, processing unit 103, which sprays media onto containers, always sprays containers in groups, such that a group of 10 containers with 10 nozzles is applied media, where each nozzle applies media to exactly one container, and if every three containers in a subsequent group have been identified as insufficiently cleaned using measurements from sensor 144, the third nozzle of the processing unit could very likely be identified as the cause.

[0060] On the other hand, for example, if all containers passing through immersion bath 102 have sodium hydroxide residue exceeding a certain limit, this can be attributed to the composition of the immersion bath. This can be detected by a suitable probabilistic model or a neural network specifically trained for this purpose, for example by attempting to reproduce the determined state parameters by changing the operating parameters in a digital image.

[0061] The container processor 100 according to the invention is then controlled based on the detected deviation and the identified cause, wherein the control may include, for example, changing one or more operating parameters of the container processor based on the identified cause and / or outputting information indicating the deviation and / or cause to the operator via a graphical display, for example.

[0062] If the operating parameters are changed based on the detected bias and the identified cause, then only the operating parameters affecting the measurement bias can be changed. This can be achieved by changing the operating parameters related to the identified cause within the scope of digital imaging, to detect whether the specific change in operating parameters resolves the bias.

[0063] Additionally or alternatively, when providing information about the cause of the deviation, it may be possible to send the operator not only information about the cause and the deviation itself, but also, for example, possible solutions. In the application of the above example, for instance, in addition to information about a possible defect in the third nozzle of the nozzle row, instructions for maintaining or replacing the nozzle may also be shown to the operator.

[0064] Figure 2 The combination is shown Figure 1 The embodiments described herein are implementations of a method for controlling a container processor.

[0065] Method 200 can be derived from the verification corresponding to Figure 1 The process begins with an optional step involving the prediction module and / or digital images. For example, when the container processor is first put into use, such as after assembly at the customer's site, verification step 201 can be performed.

[0066] Within the scope of step 201, the container processor operates and processes the container under controlled conditions. Simultaneously, state parameters measured during this controlled operation are recorded, such that for a specific combination of operating parameters, the digital image can determine certain state parameters as set state parameters.

[0067] Subsequently, a series of limit values ​​can be defined or derived from this controlled operation, which can be used, for example, in the context of the prediction module.

[0068] Furthermore, step 201 may include, within the scope of controlled operation, intentionally inducing deviations such that the deviations have a defined cause by, for example, disabling a processing unit or blocking a valve. The resulting state parameters are then measured. Then, for example, a probabilistic model or neural network may be used to address the prediction module to identify the cause of the deviation.

[0069] This can be repeated as a regular learning process within the framework of a neural network, training the network to identify causes based on specific combinations of operating parameters and (i.e., measured by sensors) specific state parameters. Here, the probabilistic model, which can exist as a deterministic algorithm, can also be tuned by adjusting the parameters of the probabilistic model.

[0070] This ensures that the digital images are used as accurate digital images of the container processors actually put into use, and that the container processors are imaged or simulated with high precision. Meanwhile, the prediction module is configured to reliably detect deviations or their causes.

[0071] Then you can begin normal operation of the container processor.

[0072] In step 202, the container processor then operates with selected operating parameters, enabling it to process the container. Then, in step 203, state parameters can be determined for each container or at specific time intervals or combinations thereof. For example, state parameters assigned to each container can be determined for each container. State parameters indicating the operating state of the corresponding processing unit can also be determined in each processing step performed on the container, or they can be determined at specific time intervals (e.g., seconds, minutes, or hours).

[0073] For example, if the processing unit is an immersion bath that processes all containers passing through the immersion bath in the same or substantially the same manner, provided there is no deviation, it would be sufficient if, in step 203, the state parameters of the immersion bath were not determined for each container introduced into the immersion bath, but rather, for example, only once every 10 minutes. Instead, state parameters could be determined for each container passing through the immersion bath, which would be determined directly on the container after it leaves the immersion bath.

[0074] Subsequently, in step 204, the control unit uses the determined state parameters from step 203, the adjusted operating parameters from step 202, and a digital image of the container processor to determine whether a deviation exists. As previously described, this can be achieved, for example, by comparing the determined state parameters from step 203 with the set state parameters derived from the digital image using processing parameters, such as by detecting whether the measurement deviation between the set state parameters and the determined state parameters is within or exceeds a predetermined limit.

[0075] If no deviation 242 is detected in step 204, the normal operation of the container processor can continue in step 243. Then, after step 243, the state parameters corresponding to step 203 can be determined again so that possible deviations can be checked again.

[0076] On the other hand, if a deviation 244 is detected in step 204, the prediction module is attempted to detect the cause of the deviation in the next step 245. As mentioned earlier, this can be accomplished, for example, using a probabilistic model or a neural network, which can utilize the results of a digital image. For example, by repeatedly changing the operating parameters in the digital image, it can be checked whether the measurement deviation can be reproduced. As a result, it can be detected whether changes in one or more operating parameters lead to the measurement deviation.

[0077] Therefore, it is no longer necessary to provide a sensor for each set operating parameter to check whether the preset operating parameter has actually been reached. Thus, for example, in the example of the malfunctioning nozzle described above, providing a sensor capable of determining whether media is flowing from the nozzle is not absolutely necessary.

[0078] By changing the operating parameters to reduce the deviation (by altering the operating parameters in the digital image to achieve the measured state parameters), the cause of the deviation or its possible causes can then be detected. In this case, for several possible causes, probability values ​​can also be assigned to the corresponding causes, indicating how likely it is that the stated cause is the actual cause of the deviation.

[0079] If the cause (or multiple causes) assigned to the deviation is detected, the container processor can be controlled in the next step 246.

[0080] This may include outputting the deviation and / or the identified cause of the deviation to the operator in step 247. This can be achieved, for example, through a graphical representation on the container processor's display, such as text or color indicators on a graphical image of the container processor in the area of ​​the identified cause. This allows the operator to easily identify the possible cause of the error and take appropriate steps if necessary.

[0081] Alternatively or additionally, the processing or operating parameters of the container processor may be changed in step 248 to eliminate the deviation.

[0082] In one implementation, the processing or operating parameters of the container processor can be automatically changed only when the cause of the deviation is clearly identified, in order to prevent the change in operating parameters from causing further deviation, but without eliminating the original cause of the deviation.

[0083] For example, if the cause is determined to be that the immersion bath temperature is too low, the temperature can be automatically adjusted, for example, by turning on the heating element or increasing its power. On the other hand, if a cause is identified with non-absolute certainty (e.g., only with an 80% probability), and another cause may be responsible for the deviation with a 20% probability, then in step 246, instead of changing the operating parameters, the corresponding information can be sent to the operator via output 247. For example, the latter can be instructed to check two different processing units to detect the actual location of the error.

[0084] While the aforementioned embodiments are primarily designed to address the fact that deviations lead to errors or operational malfunctions in the container handler, such as a nozzle that actually fails, the methods described above can also be used to predict impending operational errors in the operation of the container handler and, if necessary, to avoid such errors.

[0085] Taking a defective nozzle as an example, a state parameter could be the consumption of the medium discharged through the nozzle. Associated operating parameters could, for example, characterize the flow rate through each nozzle. If a decrease in detected medium consumption is detected, this could, for example, indicate that one or more nozzles are at least partially blocked. Alternatively, constant medium consumption and slightly different cleaning results (as a state parameter) might mean that the nozzle is partially blocked, while a leak exists in the supply line. This does not necessarily mean that the cleaning results of the container will be adversely affected, but it might indicate that one or more nozzles may fail or the pipeline may rupture in the near future. In this case, the possible blockage or partial blockage and / or leak of the nozzle can be identified as a cause of the deviation detected in the cleaning results or medium consumption, and can be detected as cause 245. In output 247, for example, at least partial blockage of one or more nozzles and a leak in the supply line can be specified as possible causes, and a signal can be issued to the operator that the nozzle needs to be cleaned or at least the nozzle and supply line inspected.

[0086] If the cause of the deviation is eliminated, normal operation can continue in step 202 using, for example, the processing parameters changed from step 248, or operation can continue using the original processing parameters after the cause of the deviation has been manually eliminated.

[0087] To better understand, some exemplary implementations are described below, which can be used to detect causes and subsequently control the container processor.

[0088] If a decrease in the transport speed of a container is detected while the torque of the drive unit of the transport equipment remains constant, this may indicate wear or contamination of the transport equipment. Alternatively, an increase in the torque of the drive unit of the transport equipment while the transport speed of the container remains constant may indicate wear or contamination of the transport equipment. For example, in the case of a cleaning machine, this could be due to blockage of components in the transport equipment. To address this issue, the container handling machine can be controlled in such a way that an increased carrying capacity of the cleaning medium is achieved, or post-treatment can be performed at elevated temperatures to eliminate blockages.

[0089] If increased power consumption or decreased transport speed is detected in the transport equipment, this could be due to a drive malfunction or general wear and tear on the transport chain. If this is considered a possible cause, the operator can be instructed to inspect the drive or moving parts, such as the transport equipment chain.

[0090] If the heating of the process medium over time is provided as a state parameter, then conclusions can be drawn about the heating elements and / or heat exchangers as possible causes of changes in these state parameters. Then, for example, the operator can be instructed to check the function of the heating elements, such as checking for possible calcification within the medium delivery line or impurities in the heat exchanger.

[0091] If a sensor capable of determining the chemical composition of a process medium is provided, and a deviation occurs in this case, it can indicate, for example, a defect or impending defect in the supply lines for the individual components of the process medium. This can be used to instruct the operator to inspect these supply lines or valves.

[0092] Choosing the temperature of the container after it has passed through the container washer as a state parameter allows for conclusions about the transport speed or medium temperature within the individual processing units of the container washer (e.g., the already mentioned immersion bath or nozzle). To eliminate this possibility, for example, the operator can be instructed to measure certain medium temperatures in a specific manner.

[0093] For example, the flow rate or temperature of the process medium before or after treatment can also be provided as a status parameter. If a deviation is detected here, this may indicate that energy loss or leakage is occurring. This can then be displayed to the operator to check for possible pipeline ruptures.

[0094] For example, the number of containers supplied to and removed from the machine can also be used as further status parameters. Discrepancies here could indicate container loss, such as a broken container, and can be output to the operator as a possible cause. Alternatively or additionally, the operator can be advised to clean the container washer.

[0095] Furthermore, for example, the alkalinity of the process medium and / or its change over time can also be used as a state parameter, wherein alkalinity at a given time is determined, for example, by measuring conductivity and / or pH. If a change occurs here, this can indicate an increase in deposit formation in the machine and can be output to the operator as a possible cause, and, if necessary, can also indicate appropriate measures for manual and / or automated cleaning processes.

Claims

1. A container processor for processing containers, the container processor comprising at least two processing units for processing containers, at least one sensor for determining state parameters, and a control unit, the state parameters indicating the state of the container after and / or during processing and / or the operational state of at least one processing unit, wherein, The control unit is configured to detect whether there are deviations in the operation of the container processor and the cause of the deviations based on the status parameters and digital images of the container processor and at least one operating parameter of the processing unit, and to control the container processor accordingly.

2. The container processing machine according to claim 1, wherein, The control of the container handler includes changing at least one operating parameter and / or providing the operator with an output indicating the detected deviation.

3. The container handling machine according to claim 1 or 2, wherein, The control unit is configured to use a prediction module, including a probabilistic model, a neural network, or fuzzy logic, to detect the presence of a bias and the cause of the bias.

4. The container processing machine according to claim 3, wherein, The prediction module is configured to learn based on deviations detected during the operation of the container processor.

5. The container handling machine according to any one of claims 1 to 4, wherein, The deviation indicates an operational error or an impending operational error.

6. The container handling machine according to any one of claims 1 to 5, wherein, The container handling machine is a cleaning machine or includes a cleaning machine.

7. A method for controlling a container processor, the container processor comprising at least two processing units for processing containers, at least one sensor for determining state parameters, and a control unit, the state parameters indicating the state of the container after or during processing, or the operational state of at least one processing unit, wherein, The control unit detects whether there is a deviation in the operation of the container processor and the cause of the deviation based on the status parameters and digital images of the container processor and at least one operating parameter of the processing unit, and controls the container processor accordingly.

8. The method according to claim 7, wherein, The control of the container handler includes changing at least one operating parameter and / or providing the operator with an output indicating the detected deviation.

9. The method of claim 8, a second alternative, wherein, The output includes the output of at least two possible causes of the deviation.

10. The method according to any one of claims 7 to 9, wherein, The control unit uses a prediction module, including probabilistic models, neural networks, or fuzzy logic, to detect whether a deviation exists and the cause of the deviation.

11. The method according to claim 10, wherein, The prediction module learns based on deviations detected during the operation of the container processor.

12. The method according to claim 10 or 11, wherein, The prediction module and / or the digital image are verified when the container processor starts up.

13. The method according to any one of claims 7 to 12, wherein, The deviation indicates an operational error or an impending operational error.

14. The method according to any one of claims 7 to 13, wherein, The container handling machine is a cleaning machine or includes a cleaning machine.

15. The method according to any one of claims 7 to 14, wherein, The method includes detecting deviations for each processed container or at predetermined time intervals during operation of the container processor.

Images