Method for operating a labelling system
Patent Information
- Application Number
- EP2023701399
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2022-01-27
- Filing Date
- 2023-01-19
- Publication Date
- 2024-12-04
AI Technical Summary
Existing labeling systems face challenges in optimizing productivity by accurately predicting maintenance needs, leading to potential production downtime due to unforeseen failures of functional units.
A method using an evaluation arrangement with a prediction model based on operating values to forecast future maintenance times, allowing for early inclusion in operational planning and reducing downtime, which involves extrapolating time dependencies and using machine learning models for accurate prognosis.
This approach enables reliable prediction of maintenance needs, reducing the risk of production downtime by integrating forecasted maintenance into operational planning and ensuring timely resource availability.
Smart Images

Figure 1.1
Abstract
Description
[0001] Procedure for operating a labeling system
[0002] The invention relates to a method for operating a labeling system according to the preamble of claim 1, an evaluation arrangement for a labeling system according to the preamble of claim 12, a labeling system according to claim 14 and a computer program product according to claim 15.
[0003] The labeling system in question for labeling individual packages comprises at least one labeling device, which is designed in particular as a price marking device. The labeling device is equipped, among other things, with a weighing arrangement and a label dispensing arrangement as functional units, which are intended for labeling the individual packages. A printer arrangement is provided for printing the labels, whereby the printing can also be carried out depending on a weight value determined by the weighing arrangement.
[0004] To monitor operation, the functional units are equipped with sensors that determine operating values related to the labeling process. These operating values can be used for controlling the functional units and also for error detection. A known method (EP 3 616 932 A1) involves determining a wear indicator for a printer assembly. For example, if a threshold value for the wear indicator is reached, maintenance of the printer assembly is initiated.
[0005] Such a labeling system is managed, for example, in a production control system, which specifies further operation in a processing plan. Estimating resource availability plays a key role in optimizing the processing plan. A failure of functional units in the labeling device can lead to significant production losses if not properly planned.
[0006] The invention is based on the problem of providing a method for operating a labeling system that enables improved productivity through optimal use of available resources. The above problem is solved by the features of the characterizing part of claim 1.
[0007] A key consideration is that the operating values determined during operation can not only be used to detect faults and identify acute maintenance needs, but also allow for an early estimation of future maintenance requirements. It has been recognized that, particularly based on the temporal progression of operating values, it is possible to predict with sufficient accuracy when maintenance will be required, for example, due to wear and tear on individual functional units. Maintenance requirements can thus be incorporated into operational planning at an early stage, reducing the risk of production downtime.
[0008] In detail, it is proposed that the evaluation arrangement is used to forecast a future maintenance time for at least one of the functional units using a predetermined forecast model based on the operating values.
[0009] In the preferred embodiment according to claim 2, a determined time dependence of the operating values is used for extrapolation, whereby trends in the operating values can be used for a reliable forecast.
[0010] According to claim 3, threshold values for operating values or variables derived therefrom can be defined so that the forecast model can be easily parameterized.
[0011] Likewise, according to claim 4, a trained machine learning model can be used to create the forecast, so that in particular a complex time dependency of a large number of operating values can be incorporated into the forecast.
[0012] In the preferred embodiment according to claim 5, the model parameters of the forecast model are adapted to the respective labeling device in a configuration routine and thus individualized, so that the reliability of the forecast can be improved overall. Various variants of operating values that can be used for the forecast are the subject of claim 6. Preferably, the operating values are already parameters recorded during the labeling routine, so that additional sensors are not necessarily required to predict the maintenance time.
[0013] In the preferred embodiment according to claim 7, the evaluation arrangement is designed to indicate a confidence interval for the predicted maintenance time, which describes the forecast quality of the predicted maintenance time and thus enables a statement to be made about the reliability of the forecast.
[0014] Particularly preferred is the further embodiment according to claim 8, which provides for interaction with a production control system for creating a machining plan. On the one hand, the machining plan can take into account the predicted maintenance time in order to use the forecast for process optimization. On the other hand, the machining plan is preferably taken into account in the forecast, since, for example, the resulting wear can depend on the respective planned machining.
[0015] In the further embodiment according to claim 9, planned, for example regular, maintenance times are also provided, which are preferably compared with the predicted maintenance times in order to reduce downtime of the labeling device as much as possible.
[0016] Also preferred is the embodiment according to claim 10, in which, in order to avoid production downtimes, the availability of maintenance resources is checked for the predicted maintenance time and these can thus be requested in good time if necessary.
[0017] Preferably, an output of the predicted maintenance time is made, which is the subject of claim 11.
[0018] According to a further teaching according to claim 12, which has independent significance, an evaluation system for a labeling system is claimed. It is essential that the evaluation system predicts a future maintenance time for at least one of the functional units using a predefined forecast model based on the operating values. Reference is made to all explanations of the method.
[0019] In the preferred embodiment according to claim 13, the evaluation arrangement can be designed to carry out, in addition to generating the prognosis, also the control of the functional units in the context of labelling the packages.
[0020] According to a further teaching according to claim 14, which also has independent significance, a labeling system for implementing the proposed method is claimed. Reference may also be made to all explanations of the method.
[0021] According to a further teaching according to claim 15, which also has independent significance, a computer program product is claimed with instructions which, when executed on a computer of an evaluation device of a labeling system, cause the evaluation device to carry out the proposed method. Reference is also made to all statements regarding the method.
[0022] In the following, the invention is explained in more detail with reference to a drawing which merely represents exemplary embodiments. In the drawing,
[0023] Fig. 1 is a schematic representation of the proposed labeling system with a proposed evaluation arrangement for carrying out the proposed method and
[0024] Fig. 2 shows an example of a temporal progression of operating values.
[0025] The invention relates to a method for operating a labeling system. The labeling system is equipped with at least one labeling device 1 for labeling individual packages 2, which is designed in particular as a price labeling device. The labeling device 1 has, as functional units, at least one weighing arrangement 3 for determining a weight value of the package 2, a dispensing arrangement 4 for dispensing a label 5 from a material strip 6, and a printer arrangement 7 for printing the label 5. In addition to these functional units, further functional units can be provided. Likewise, the labeling system can also have a plurality of labeling devices 1, in particular as described here.
[0026] In a not-shown embodiment of the labeling system, the labeling device 1 is provided for partially manual labeling of the packages. For example, the operator manually places the package 2 onto the weighing arrangement 3, and a label 5 printed by the printer arrangement 7 is dispensed by the dispensing arrangement 4. The application of the label 5 to the package 2 is also performed manually, for example.
[0027] The weighing arrangement 3 serves to determine the weight values of the respective package 2. The weighing arrangement 3 has a load cell that determines representative, analog and / or digital weight values for the weight of the package 2. The weight values are determined in particular based on a deformation measurement of a support for the packages 2, for example via strain gauges, and / or based on electromagnetic force compensation of the weight of the respective package 2.
[0028] The dispensing arrangement 4 is provided for dispensing the label 5, which can be designed to be detachable from a material strip 6. A label 5 detachable from a material strip 6 refers in particular to a label 5 whose adhesive surface is detachably attached to a carrier strip that forms the material strip 6 and can consist, for example, of paper and / or plastic. It is also possible for the label 5 to be produced by separating a section from a printable or printed material strip 6, for example by cutting and / or tearing the material strip 6. In particular, labels 5 designed as adhesive labels are used, which already have an adhesive surface by means of which they are detachably attached to the material strip 6.It is also conceivable to use adhesive-free labels 5, which are only later provided with an adhesive surface or are applied to an adhesive surface on the respective package 2.
[0029] The printer assembly 7 is provided for printing the label 5, wherein the label 5 can be printed in principle on the material strip 6 and / or after the label 5 has been detached from the material strip 6, as well as before, after, or during the application of the label 5 to the respective package 2. Here, and preferably, a printer assembly 7 configured for thermal printing, in particular direct thermal printing or thermal transfer printing, is provided.
[0030] The design of the labeling device 1 shown in Fig. 1 comprises, in addition to the functional units already mentioned, further functional units which implement a largely automated and continuous labeling of the packages 2.
[0031] A feed arrangement 8 is provided as a further functional unit for transporting the respective packages 2. The feed arrangement 8 is preferably a belt conveyor or a roller conveyor, optionally also at least one robot arm, for moving the respective packages 2. The feed arrangement 8, here the belt conveyor, preferably has at least one conveyor belt, via which the respective packages 2 are transported along a transport direction.
[0032] Preferably, the weighing arrangement 3 is designed as a dynamic weighing arrangement, which determines the weight values of moving packages 2 and thus enables the continuous operation of the labeling device 1. In Fig. 1, the weighing arrangement 3 is provided accordingly on the feed arrangement 8. Likewise, the printer arrangement 7 and / or an additional printer arrangement (not shown here) can be provided on the feed arrangement 8 and, for example, print the moving package 2, in particular the label 5 applied to the package 2.
[0033] In addition, the labeling device 1, here in a common housing with the dispensing arrangement 4, has an application arrangement 9 as a further functional unit for applying the dispensed label 5 to the respective package 2. Preferably, the dispensed label 5 is picked up by a stamp, which here is preferably designed as a pendulum stamp 10, and applied to the respective package 2. In particular, the stamp has a blow head 11 for sucking on and blowing off the label 5. During application, the pendulum stamp 10 performs a movement along the transport direction in order to enable labeling of the package 2 moved by the feed arrangement 8. With the application arrangement 9, the label 5 can be applied to the package 2 in a contact-like manner by pressing the label 5 onto it.Additionally or alternatively, it is conceivable that the label 5 is applied without contact, for example by the blow head 11 of the stamp blowing the label 5 onto the package 2 by generating a blast of compressed air directed towards the package 2.
[0034] The labeling device 1 further comprises an operating controller 12. In a labeling routine, the functional units are controlled by the operating controller 12 for labeling the individual packages 2. During the labeling routine, respective packages 2 are transported by means of the feed arrangement 8, wherein a label 5 dispensed from a material strip 6 by the dispensing arrangement 4 is applied to the respective package 2 by means of the application arrangement 9, and the label 5 is printed by means of the printer arrangement 7. For this purpose, the operating controller 12 preferably comprises control electronics for implementing the control tasks arising during the labeling routine. The operating controller 12 can, as also shown in simplified form in Fig. 1, be a central operating controller 12 of the labeling system and / or the labeling device 1, which controls all or at least some of the functional units.It is also possible for the operating control 12 to have a plurality of decentralized, mutually communicating control units, wherein preferably each functional unit is assigned a control unit.
[0035] The labeling device 1 has a sensor arrangement 13, by means of which operating values assigned to the functional units are determined. Here, the term "sensor arrangement 13" refers to the sensor units assigned to the functional units. The sensor data determined by the respective sensor units are processed and transmitted as operating values to the operating control 12 and are used, in particular, to monitor and control the functional units in the labeling routine.
[0036] The sensor units here comprise at least one sensor and preferably a plurality of sensors, which determine operating values based, for example, on optical, acoustic, mechanical, and / or electronic measured variables. An operating value can be understood as an operating state, such as the temperature, speed, or acceleration of a component. It is also conceivable for the sensor arrangement 13 to determine, for example, the operating time of a component as operating values.
[0037] The labeling system also has an evaluation device 14, to which the operating values are transmitted. As shown in Fig. 1, the evaluation device 14 can, for example, be a server for the labeling system that is higher-level than the operating controller 12 and performs an evaluation of the operating values, as described below. In this case, the evaluation device 14 is connected to the operating controller 12 and / or the sensor device 13 via a local communications network. However, it is also possible for the operating controller 12 to be a component of the evaluation device 14.
[0038] Furthermore, the connection of the evaluation arrangement 14 to a cloud 15, which has at least one cloud server 16, is provided here and preferably. It is conceivable that at least some of the tasks occurring at the evaluation arrangement 14 are performed by the cloud server 16. In the illustrated embodiment, however, an evaluation of the operating values is carried out, for example, locally at the labeling device 1 by means of the evaluation arrangement 14.
[0039] What is essential now is that, by means of the evaluation arrangement 14, a future maintenance time is forecast for at least one of the functional units using a predefined forecast model based on the operating values. A forecast model is defined here as a model that enables the prediction of an output variable in the future as a function of at least one functional variable. Such a forecast model uses, in particular, the temporal progression of at least one functional variable in the past and forecasts the output variable from this temporal progression. The future maintenance time serves, in particular, as the output variable. The operating values or variables derived therefrom serve as the functional variables here.
[0040] The predicted maintenance time can be specified for individual components of the labeling device 1 or for a module consisting of multiple components. The maintenance time can serve either to prevent wear-related failure of one of the components or a part of a component, but can also be provided to prevent a reduction in the performance or quality of the labeling routine induced by wear or other effects.
[0041] Furthermore, it is preferably provided here that the predetermined forecast model is based on a time dependence of the operating values, preferably on an extrapolation of the time dependence of the operating values.
[0042] In particular, various regression methods can be used, such as linear regression, non- or semi-parametric regression such as multivariate adaptive regression splines or robust regression methods such as least squares estimation or maximum likelihood estimation.
[0043] Fig. 2 shows example curves of a first operating value (shown as diamonds) and a second operating value (shown as rectangles) as a function of time t. Up to time t = 0, the operating values were recorded and their time dependence was stored using the evaluation arrangement 14 (filled symbols in Fig. 2). From the time dependencies, for example, a further temporal curve of the first and second operating value is forecast here, which is represented by the open symbols. In addition to discrete, forecast values for the operating values, the forecast can also be given as a continuous function. The forecast for one of the operating values does not necessarily have to be created exclusively from the same operating value. In Fig. 2, a third operating value is shown with circles, whereby, for example, the first and / or second operating value is related to the third operating value.The forecast for the first and / or second operating value can be determined here depending on the temporal course of the third operating value.
[0044] Furthermore, it is preferably provided here that the forecast model contains at least one threshold value for an operating value or for a variable derived from the operating values as a model parameter, and that the forecast maintenance time is determined on the basis of the threshold value being reached as forecast from the operating values.
[0045] The threshold can represent both an upper and a lower limit for an operating value or a variable derived from the operating values, as well as a threshold corridor. Likewise, multiple thresholds with different significance can exist for an operating value or a derived variable. For example, it is conceivable that if a first threshold for the electrical power consumption of a drive component is exceeded, a maintenance time further in the future is predicted, and if a second, higher threshold is exceeded, a maintenance time closer in the future is predicted.
[0046] In Fig. 2, threshold values for the first and second operating values are indicated as examples, which are used to predict the maintenance times twi and tw2.
[0047] Multiple operating values can be combined to form a single, higher-level variable, or a further variable can be derived from one or more operating values. Combining multiple operating values can be achieved, for example, by individually weighting the various operating values. For example, the increase in the electrical power consumption of an actuator is assigned a higher weighting than the measured value of a vibration sensor, which is also used to generate the combined variable. The combined variable can also be generated from derived values of one or more operating values.
[0048] Machine learning methods, such as artificial neural networks or least-square support vector machines, can be used in particular for regression analysis and forecasting. In a preferred embodiment, the specified forecast model contains a machine learning model trained to generate the forecast maintenance time from operating values.
[0049] A machine learning model is an algorithm capable of generating a probable output dataset for an unknown input dataset from a given set of input and corresponding output data. The given input dataset, also known as the training dataset, serves to train the machine learning model. This training can take place as supervised or unsupervised learning. Here, and preferably, the machine learning model is trained using a supervised learning concept. In this case, the assignment of an input dataset to the corresponding output dataset is known, so that the learning result is the recognition of a functional or regressive relationship between the input and output data.
[0050] The machine learning model can, for example, be an artificial neural network, but decision trees, support vector machines, Bayesian networks or other well-known machine learning methods can also serve as the basis for the forecasting model.
[0051] For example, the trained machine learning model generates a forecast of the future temporal progression of individual operating values, from which the future maintenance time is determined, in particular by comparing it with at least one threshold value. The future maintenance time can also be a starting point for the trained machine learning model.
[0052] The machine learning model can be trained before the labeling system is put into operation, and the model resulting from the training can be stored in the evaluation system 14. However, it is also conceivable for the machine learning model to be trained or further developed in a learning routine during operation of the labeling system. For example, a forecast for the operating values generated using the machine learning model is compared with the subsequent temporal progression of the recorded operating values. Consequently, the data on the operating values collected during ongoing operation can be used for further training of the machine learning model, thereby adapting the machine learning model, in particular, to the individual requirements of the respective labeling device 1.
[0053] Furthermore, it is preferably provided here that the forecast model contains model parameters which are determined by means of the evaluation arrangement 14 in a configuration routine on the basis of the operating values.
[0054] In an advantageous embodiment, the forecast model can contain model parameters that establish a functional relationship between the operating values and the output variables, for example, in the form of coefficients or the like. Model parameters can also be understood as weights, thresholds, or activation function specifications used in artificial neural networks, for example.
[0055] Since such model parameters depend on the physical conditions of the individual labeling system, the values of the model parameters can differ for two different labeling devices 1 of the same type depending on the environment or specific configuration. Therefore, the values of the model parameters are determined by the evaluation arrangement 14 in a configuration routine based on the operating values. This can be achieved, for example, by operating the labeling system in different, predefined operating modes and / or for different labeling processes, and by recording and evaluating the operating values.
[0056] Preferably, the configuration routine is performed during commissioning, so that the labeling device 1 is set up with an optimized initial configuration for the forecast model. Furthermore, the configuration routine can generally be performed during operation, in particular in a time-controlled manner and, for example, at regular intervals. In particular, the time-controlled execution of the configuration routine makes it possible to adapt the forecast model to changing conditions, such as changes in material specifications, environmental conditions, or minor geometric changes to the structural components of the labeling system, even over a longer operating period of the labeling system of several years.
[0057] In principle, the operating values can be all measurable and estimable variables that arise during the operation of the labeling system. Particularly advantageous operating values are representative of at least one of the following values: the operating time of at least one functional unit; a speed assigned to the functional unit, in particular the feed speed, application speed and / or printing speed; temperature, pressure, humidity and / or air speed; the number of processed packs 2, start-up processes, labels 5 and / or material strips 6 used; the pack weight 2 of the processed packs 2; the number of detected collisions between a functional arrangement, in particular the dispensing arrangement 4, and packs 2 and / or step losses; and / or drive values of electrical actuators of the functional units.
[0058] The operating time is understood to mean a usage time accumulated over the operation of the functional unit, in particular a time period in which the functional unit is switched on and / or a time period in which the functional unit is active and, for example, processes a pack 2.
[0059] The feed speed can be specified, for example, via the speed of the belt of the feed arrangement 8 or also via an angular velocity of a roller or the like. The application speed is in particular the speed of a component of the application arrangement 9 when applying the label 5 and preferably the angular velocity of the pendulum stamp 10. The printing speed is to be understood in particular as the speed of the label 5 on the printer arrangement 7. In addition to the speed, the distance covered by the respective components can also be used as operating values. The temperature, pressure, air humidity and air speed are in particular parameters of the air conditions at the location of the labeling device 1 and specifically at individual functional units, which can influence the labeling routine.The temperature of a component, for example, an actuator, the print head of the printer assembly 7, or the like, can also be used as an operating value. The pressure at pneumatic or hydraulic components, here, for example, at the blowing head 11 and / or the associated compressed air system, can also serve as an operating value.
[0060] The number of packages 2 processed, start-up processes, labels 5, and / or material strips 6 used can also have a significant impact on component wear and are preferably recorded as operating values. A start-up process is understood to mean the start-up of the labeling device 1, which, in particular, resumes continuous labeling after a stop. A high number of material strips 6 used corresponds to the fact that material strips 6 in the dispensing arrangement 4 have been replaced frequently, which may result in a need for maintenance.
[0061] The package weight of the processed packages 2 is determined by means of the weighing system 3. The cumulative package weight 2 of the packages 2 can be used as the operating value. Threshold values such as maximum values can also be specified for the package weight 2, with the overweight of the packages 2, weight classes of the packages 2, or the like being determined as operating values.
[0062] Errors can include collisions between dispensing assembly 4 and packs 2, and lost steps during labeling. Such events can be recorded, and their number, in particular, can be incorporated into operating values.
[0063] Drive values of electrical actuators of the functional units include, for example, a drive current, a drive voltage, speeds of electric motors, or the like. An operating value can also be representative of an actuator overcurrent, for example, the duration or number of times a maximum drive current is exceeded. Examples of electrical actuators are the drive motors of the feed arrangement 8 and the drive motors for moving the material strip 6 in the dispensing arrangement 4.
[0064] Operating values for electronic control components can also be recorded, in particular the operating control 12, the evaluation arrangement 14 or also the sensor arrangement 13. For example, the voltage, current, temperature and / or cooling capacity of electronic components are recorded.
[0065] Also conceivable are operating values relating to the verification and / or calibration of the weighing arrangement 3.
[0066] Since forecast models are always subject to uncertainty, a time interval with an earliest maintenance time and a latest maintenance time can be determined for the forecasted maintenance time, whereby the earliest maintenance time and the latest maintenance time describe the boundaries of a confidence interval with a predetermined confidence. The time interval can correspond to the p-confidence interval of the true value of the maintenance time. The interval boundaries are then described as the earliest and latest maintenance times, so that the period between the earliest and latest maintenance times contains the true maintenance time with a probability of p. The parameter p is at least 0.5, but preferably at least 0.8 and more preferably 0.95.
[0067] In order to optimally integrate downtimes of the labeling system caused by maintenance work into the operating sequence and to optimally adapt the operating sequence to maintenance work, it is preferably provided here that the predicted maintenance time is transmitted by means of the evaluation arrangement 14 to a production control system of the labeling system, which then creates a processing plan for the operation of the labeling system. The production control system can create the processing plan for the operation of the labeling system depending on the predicted maintenance time. For example, the production control system can be configured to chronologically relate various processing blocks to the predicted maintenance time in such a way that the maintenance coincides with a setup process resulting from the changeover from one processing block to another.
[0068] It can also be provided that the processing plan is transmitted to the evaluation system 14 via the production control system, and the forecast model is defined depending on the processing plan. Accordingly, the forecast of the maintenance period can take into account the processing blocks planned for the future, for example, in order to predict an earlier maintenance time in the case of a high number of intensive processing steps.
[0069] It is also conceivable that deterministically specified maintenance intervals are also taken into account in the forecast, for example, if these are prescribed by law. Here, and preferably, it is provided that specified maintenance times are stored, which are output by the evaluation system 14 in addition to the forecast maintenance times. Preferably, the processing plan is created by the production control system in such a way that a predicted maintenance time coincides with one of the specified maintenance times.
[0070] In this way, it is possible to incorporate legally prescribed maintenance times or limited service lives of wear components due to warranty rights into the planning of maintenance times, thus enabling a further reduction in downtime and thus an increase in efficiency.
[0071] Furthermore, it is preferably provided here that at least one maintenance resource, in particular a spare part or tool, is assigned to the predicted maintenance time on the basis of a maintenance specification by means of the evaluation arrangement 14.
[0072] The maintenance resource can be a replacement part, in particular a wearing part such as a bearing, a filter or a clutch, but also a spare part for a defective component or a component for which the risk of imminent failure is high based on the data from the forecast model. However, the maintenance resource is not limited to replacement parts. The maintenance resource can also be a tool necessary for maintenance, such as a special measuring device or a joining tool. It is also conceivable that the maintenance part is a component of the labeling system for which a decision is only made during the maintenance process as to whether the component needs to be replaced. In addition to the maintenance resources, maintenance personnel can also be assigned to the forecast maintenance time.
[0073] Assigning a maintenance resource is particularly advantageous if the evaluation system 14 requests the availability of the maintenance resource at the predicted maintenance time in a warehouse management system. This ensures that all maintenance resources required for maintenance are available at the scheduled maintenance time and that no delays occur. The evaluation system 14 can also be configured to register the requirement in the warehouse management system, so that if, for example, a spare part is unavailable, an order process is triggered.
[0074] Furthermore, it is preferably provided here that the evaluation arrangement 14 causes an output of the predicted maintenance time and at least some of the current operating values and / or variables dependent on the operating values via a display device 17, 18, 19.
[0075] The display device 17, 18, 19 can be a graphical output unit, such as a display 17 on the labeling device 1 or a display 18, 19 of a terminal device, for example a mobile device, which is in communication with the evaluation arrangement 14 or with the cloud server 16. Likewise, the display device 17, 18, 19 can be a mechanical output unit in the form of a pointer or the like. In addition to the predicted maintenance time, the display device 17, 18, 19 preferably also outputs operating values or variables derived from them. For example, temperatures, power consumption or pressures, but also dimensionless key figures such as relative changes to base values of an operating value can be output. This enables the operator to obtain a more detailed assessment of the current operating situation.
[0076] Also claimed according to a further teaching which is of independent significance is an evaluation arrangement 14 for a labelling system with at least one labelling device 1 for labelling, in particular for pricing, individual packages 2, wherein the labelling device 1 has as functional units at least one weighing arrangement 3 for determining a weight value of the package 2, a dispensing arrangement 4 for dispensing a label 5 from a material strip 6 and a printer arrangement 7 for printing the label 5, wherein the evaluation arrangement 14 receives operating values assigned to the functional units from a sensor arrangement 13 of the labelling device 1.
[0077] What is essential here is that the evaluation system 14 uses a predefined forecast model based on the operating values to predict a future maintenance time for at least one of the functional units. Reference is made to the explanations regarding the method.
[0078] Preferably, the evaluation arrangement 14 is also configured to control the functional units for labeling the individual packages 2 in a labeling routine. In this respect, the evaluation arrangement 14 can contain the previously described operating control 12.
[0079] According to another teaching of independent significance, a labelling system for carrying out the proposed method is also claimed.
[0080] Also claimed, according to a further teaching of independent significance, is a computer program product with instructions which, when executed on a computer of an evaluation arrangement 14 of a labeling system, cause the evaluation arrangement to carry out the proposed method. The computer program product is preferably stored in an electronic memory. Particularly preferably, the evaluation arrangement 14 has a memory in which the instructions of the computer program product are stored, and at least one processor for executing the program instructions, wherein the memory and the instructions are configured, together with the processor, to control the labeling system to carry out the proposed method.
[0081] The memory preferably comprises a non-volatile memory for the program instructions, for example a flash memory, an EEPROM memory, a magnetic memory, and / or an optical memory. The memory may further be equipped with a working memory, preferably a random access memory (RAM) or the like. The processor preferably comprises a microprocessor, a digital signal processor, and / or an application-specific integrated circuit.
Claims
Claims 1. A method for operating a labeling system with at least one labeling device (1) for labeling, in particular for price marking, individual packages (2), wherein the labeling device (1) comprises as functional units at least a weighing arrangement (3) for determining a weight value of the package (2), a dispensing arrangement (4) for dispensing a label (5) from a strip of material (6), and a printer arrangement (7) for printing the label (5), wherein the labeling device (1) comprises a sensor arrangement (13) by means of which operating values assigned to the functional units are determined and transmitted to an evaluation arrangement (14) of the labeling system, characterized in that, by means of the evaluation arrangement (14), a future maintenance time for at least one of the functional units is predicted based on the operating values using a predetermined forecasting model.
2. Method according to claim 1, characterized in that the specified forecasting model is based on a time dependency of the operating values, preferably on an extrapolation of the time dependency of the operating values.
3. Method according to claim 1 or 2, characterized in that the forecasting model includes at least one threshold value for an operating value or for a quantity derived from the operating values as a model parameter, and that the predicted maintenance time is determined on the basis of a threshold being reached as predicted from the operating values.
4. Method according to one of the preceding claims, characterized in that the specified forecasting model includes a machine learning model trained to generate the predicted maintenance time from the operating values.
5. Method according to one of the preceding claims, characterized in that the forecasting model contains model parameters which are determined by means of the evaluation arrangement (14) in a configuration routine based on the operating values, preferably that the configuration routine with The labeling device (1) is commissioned and / or time-controlled.
6. Method according to one of the preceding claims, characterized in that the operating values are representative of at least one of: the operating time of at least one functional unit; a speed assigned to the functional unit, in particular the feed rate, application rate and / or printing rate; temperature, pressure and / or humidity; the number of processed packages (2), start-up operations, labels (5) used and / or material strips (6); the package weight (2) of the processed packages (2); the number of detected collisions between dispensing arrangement (4) and packages (2) and / or step losses; and / or drive values of electrical actuators of the functional units.
7. Method according to one of the preceding claims, characterized in that a time interval with an earliest maintenance time and a latest maintenance time is determined for the predicted maintenance time, wherein the earliest maintenance time and the latest maintenance time describe the limits of a confidence interval with a predetermined confidence.
8. Method according to one of the preceding claims, characterized in that the predicted maintenance time is transmitted to a production control system of the labeling system by means of the evaluation arrangement (14), which creates a processing plan for the operation of the labeling system, preferably depending on the predicted maintenance time, and / or that the processing plan is transmitted to the evaluation arrangement (14) by means of the production control system and that the forecast model is defined depending on the processing plan.
9. Method according to one of the preceding claims, characterized in that predetermined maintenance times are stored, which are output by means of the evaluation arrangement (14) in addition to the predicted maintenance times, preferably that the processing plan is created by means of the production control system in such a way that a predicted The maintenance time coincides with one of the specified maintenance times.
10. Method according to one of the preceding claims, characterized in that, by means of the evaluation arrangement (14), at least one maintenance resource, in particular a spare part or tool, is assigned to the predicted maintenance time based on a maintenance specification, preferably, that, by means of the evaluation arrangement (14), the availability of the maintenance resource in a warehouse management system is requested at the predicted maintenance time.
11. Method according to one of the preceding claims, characterized in that the evaluation arrangement (14) is used to output the predicted maintenance time and at least part of the current operating values and / or quantities dependent on the operating values via a display device (17, 18, 19).
12. Evaluation arrangement for a labeling system with at least one labeling device (1) for labeling, in particular for price marking, individual packages (2), wherein the labeling device (1) comprises as functional units at least a weighing arrangement (3) for determining a weight value of the package (2), a dispensing arrangement (4) for dispensing a label (5) from a strip of material (6) and a printer arrangement (7) for printing the label (5), wherein the evaluation arrangement (14) receives operating values assigned to the functional units from a sensor arrangement (13) of the labeling device (1), characterized in that the evaluation arrangement (14) uses a predetermined forecasting model based on the operating values to predict a future maintenance time for at least one of the functional units.
13. Evaluation arrangement according to claim 12, characterized in that the evaluation arrangement (14) is configured to control the functional units for labeling the individual packages (2) in a labeling routine.
14. Labeling system for carrying out a method according to any one of claims 1 to 11.
15. Computer program product comprising instructions which, when executed on a computer of an evaluation arrangement (14) of a labeling system, cause the evaluation arrangement (14) to perform the method according to one of claims 1 to 11.
