DE202023103191U1 - Data processing system and system for monitoring a joining process - Google Patents

Abstract

Data processing system (620) for automatically monitoring a joining process for connecting a plurality of substrates arranged in an overlapping manner to form a composite product under pressure by a pressing device (605), the data processing system (620) having at least one processor platform and a memory coupled thereto, in which instructions are stored which, when executed on the processor platform, cause it to carry out a method (100) which has the following steps: acquiring (105) measurement data which, for various working positions assumed by the pressing device (605) as part of the application of pressure, contain respective measurement values of a represent a measured variable that specifies a pressing force acting on the substrates during the respective working position or a variable that is dependent on it;evaluating the recorded measurement data in order to extract a plurality of different features from them (115; 305,...,-320), each individually and/or together representing at least one characteristic property of a curve (210) of the measured variable represented by the measurement data as a function of the working positions of the pressing device (605) or a variable corresponding to the working positions ;Determining (120) an evaluation indicator (B) defined as a measure of a quality of the joining process as a function of the extracted features;Evaluating (130) the joining process based on a comparison of the determined evaluation indicator (B) with a defined evaluation reference, generating one from the Comparison of the resulting evaluation result; andcontrolling (135) the pressing device (605) and/or further treatment, in particular further processing, ejection or marking, of the composite product produced by means of the joining process depending on the evaluation result.

Description

The present invention relates to a data processing system for the automatic, in particular computer-implemented, monitoring of a joining process for connecting a plurality of overlappingly arranged, in particular stacked, substrates to form a composite product under pressure from a pressing device. The joining process can specifically be a sealing process for the production of packaging, such as blister packaging. Accordingly, the pressing device can in particular be a sealing machine, such as a plate sealing machine. The invention further relates to a system having the data processing system for carrying out and automatically monitoring a joining process.

In joining processes of the type mentioned at the outset, there is a risk that the quality of the composite products obtained will be impaired if a foreign body or a substance between the substrates, e.g. B. for the purpose of its packaging, product to be enclosed is located.

Such a case can occur in particular in the manufacture of blister packs, for example for food or medicinal or cosmetic products. Such blister packs often have a first substrate, which is designed as a film with bulges as courtyards for receiving the goods to be packaged, z. B. of one tablet per courtyard is formed. A second, also mostly film-like, substrate is applied to the first substrate by the joining process and connected under pressure by a pressing device, in particular positively or materially, that the two substrates are connected outside of the areas stressed by the courts, while the goods to be packaged lie in the courts and are surrounded on all sides by the interconnected substrates. Such a joining process is often also referred to as a "sealing process" and a device configured for its execution as a "sealing machine" or "sealing device". The quality problem mentioned above arises here in particular when the product to be packaged, for example one or more tablets, does not lie correctly only in its respective courts during the pressurization, but is wholly or partially located on substrate surfaces lying between the courts.

Since the occurrence of such quality problems cannot be ruled out with absolute certainty, the joining processes are usually monitored in order to be able to identify such problems.

For this purpose, it is known in particular to measure the pressing force that occurs on the pressing device during the pressurization of the substrates to be connected as part of the joining process and to carry out a threshold value comparison in this regard. If the pressing force is above a predetermined threshold, then an error in the joining process is concluded, while otherwise the joining process and the connection product produced in the process are evaluated as error-free.

It is an object of the invention to further improve the monitoring of joining processes of the type mentioned at the outset.

The solution to this problem is achieved according to the teaching of the independent claims. Various embodiments and developments of the solution are the subject matter of the dependent claims.

1. (i) Erfassen, insbesondere Empfangen, Einlesen oder messtechnisch Erfassen, von Messdaten, die für verschiedene von der Pressvorrichtung im Rahmen der Druckbeaufschlagung eingenommene Arbeitsstellungen jeweilige Messwerte einer, insbesondere skalaren oder vektoriellen, Messgröße repräsentieren, die eine während der jeweiligen Arbeitsstellung auf die Substrate einwirkende Presskraft oder eine in einem Abhängigkeitsverhältnis damit stehende Größe angibt;
2. (i) Auswerten der erfassten Messdaten, um daraus eine Mehrzahl verschiedener Merkmale zu extrahieren, insbesondere zu berechnen, die jeweils einzeln und/oder gemeinsam zumindest eine charakteristische Eigenschaft eines durch die Messdaten repräsentierten Verlaufs der Messgröße in Abhängigkeit von den Arbeitsstellungen der Pressvorrichtung oder einer zu den Arbeitsstellungen korrespondierenden Größe repräsentieren;
3. (iii) Ermitteln eines als ein Maß für eine Qualität des Fügeprozesses definierten, insbesondere numerischen, Bewertungsindikators in Abhängigkeit von den extrahierten Merkmalen;
4. (iv) Bewerten des Fügeprozesses anhand einer Gegenüberstellung, etwa in Form eines Vergleichs, des ermittelten Bewertungsindikators mit einer definierten, insbesondere numerischen, Bewertungsreferenz unter Erzeugung eines aus der Gegenüberstellung resultierenden, insbesondere numerischen, Bewertungsergebnisses (als Maß einer Qualität des Fügeprozesses oder des damit erzeugten Verbundprodukts); und
5. (v) Steuern der Pressvorrichtung und/oder Weiterbehandeln, insbesondere Weiterprozessieren, Ausschleusen oder Markieren, des mittels des Fügeprozesses erzeugten Verbundprodukts in Abhängigkeit von dem Bewertungsergebnis.

A first aspect of the solution presented here relates to a data processing system for automatically monitoring a joining process for connecting, in particular laminating, a plurality of overlapping substrates to form a composite product under pressure from a pressing device, in particular a sealing machine, e.g. B. Plate sealing machine. The data processing system has at least one processor platform and a memory coupled thereto, in which instructions are stored which, when executed on the processor platform, cause the processor platform to carry out a method which has the following steps:

1. (i) Acquiring, in particular receiving, reading in or metrologically acquiring measurement data which, for various working positions assumed by the pressing device as part of the pressurization, represent respective measured values of a measured variable, in particular scalar or vectorial, which indicates a pressing force acting on the substrates during the respective working position or a variable that is dependent on it;
2. (i) Evaluation of the recorded measurement data in order to extract from it, in particular to calculate, a plurality of different features which each individually and/or together represent at least one characteristic property of a profile of the measurement variable represented by the measurement data as a function of the working positions of the pressing device or a variable corresponding to the working positions;
3. (iii) determining an evaluation indicator defined as a measure of a quality of the joining process, in particular numerical, as a function of the extracted features;
4. (iv) Evaluation of the joining process based on a comparison, for example in the form of a comparison, of the determined evaluation indicator with a defined, in particular numerical, evaluation reference, generating an evaluation result, in particular numerical, resulting from the comparison (as a measure of a quality of the joining process or of the composite product produced with it); and
5. (v) Control of the pressing device and/or further treatment, in particular further processing, ejection or marking, of the composite product produced by means of the joining process depending on the evaluation result.

The term "substrate", as used herein, means a homogeneous or heterogeneous, in particular film or plate-shaped solid (i.e. with a solid state of aggregation at normal temperature 20 °C and normal pressure 1013 hPa) which is suitable to be joined together with one or more other such or similar solids under pressure to form a composite product. In particular, a substrate can be designed as a plastic or metal foil or even as a composite material. In particular, the various layers of a blister pack each fall under the term "substrate" as used herein.

The term "characteristic feature" or "feature" for short, as used herein, is to be understood as meaning a property of the progression of the measured variable that is basically suitable for distinguishing progressions of the measured variable that occur when the joining process is carried out correctly from other progressions of the measured variable that occur when the joining process is carried out with errors. Such erroneous designs can particularly affect cases in which the quality of the composite products obtained is impaired by the fact that one or more foreign objects or products to be packaged are located between the substrates to be connected as part of the joining process at a point where the substrates are to be brought into physical contact for their connection. A feature can optionally also have a direct physical meaning, but it can also only be a matter of a purely operand without direct meaning. What is crucial, however, is that it can be used alone or through its contribution in combination with other features to make an anomaly occurring during the joining process recognizable.

The term "quantity" as used herein means a physical or chemical quantity, i. H. to understand a quantitatively determinable property of a process or state of an object of physics or chemistry. In particular, pressures, forces, electrical or mechanical stresses, material compositions or structures, mass densities, lengths, etc. are all quantities in this sense.

The term "working position", as used herein, is to be understood as meaning a respective state of the pressing device, with different working positions corresponding to different working points, in particular strokes or distances from pressing tools that have a pressing effect on the material to be pressed (in this case substrates) during pressing, of the pressing device.

As used herein, the terms “comprises,” “includes,” “includes,” “has,” “has,” “having,” or any other variation thereof, as appropriate, are intended to cover non-exclusive inclusion. For example, a method or device that includes or has a list of elements is not necessarily limited to those elements, but may include other elements that are not expressly listed or that are inherent in such method or device.

Further, unless expressly stated to the contrary, "or" refers to an inclusive "or" and not to an exclusive "or". For example, a condition A or B is satisfied by one of the following conditions: A is true (or present) and B is false (or absent), A is false (or absent) and B is true (or present), and both A and B are true (or present).

As used herein, the terms "a" or "an" are defined to mean "one or more". The terms "another" and "another" and any other variant thereof shall be construed to mean "at least one other".

The term "plurality" as used herein, where appropriate, is to be understood as meaning "two or more".

The terms "first,""second,""third," and similar terms in the specification and claims are used to distinguish between similar or otherwise like-named elements and not necessarily to describe them in a sequential, spatial, or chronological order. It should be understood that the terms so used are interchangeable under appropriate circumstances, and that the solution embodiments described herein may operate in different orders than those described or illustrated herein.

The term "configured" or "set up" to perform a particular function (and any derivatives thereof), as used herein where appropriate, means that a related device or component thereof is already in a configuration or configuration in which it is capable of performing the function, or at least so adjustably - i.e. H. configurable - is that it can perform the function after appropriate setting. The configuration can take place, for example, via a corresponding setting of parameters of a process flow or of switches or the like for activating or deactivating functionalities or settings. In particular, the device can have a plurality of predetermined configurations or operating modes, so that the configuration can be carried out by selecting one of these configurations or operating modes.

The data processing system according to the first aspect is characterized in particular by the fact that a number of different characteristic features of the progression of the measured variable are used to evaluate the joining process as part of the method when it is carried out. On the one hand, this has the advantage that not only directly measurable characteristics, but also suitable characteristics that can only be indirectly derived from the course can be used for the evaluation, so that the available evaluation basis can be expanded.

Thus, the use of a plurality of features instead of a single feature as an assessment basis allows an increase in the achievable reliability (or equivalently: a reduction in the error rate) and/or the accuracy of the assessment. Thus, production can be better optimized and the process yield of the joining process can be increased while reducing composite products that are mistakenly classified as defective. In particular, the method is therefore not limited to the detection of very large overload situations, in contrast to a mere measurement of a maximum force with a subsequent comparison of a threshold value. In particular, the method is also less susceptible to any measurement-falsifying thermal expansions of components of the pressing device or of the material to be pressed.

Various exemplary embodiments of the data processing system are now first described below, which can be combined with one another as desired and with the other aspects of the present solution described below, unless this is expressly ruled out or is technically impossible.

• - ein zu einer maximalen Presskraft korrespondierender Extremwert, insbesondere lokales oder globales Maximum, des Verlaufs der Messgröße;
• - ein Indikator, der eine Arbeitsstellung kennzeichnet, bei der der Extremwert auftrat;
• - eine, insbesondere konstante, Vorspannungskraft, der die Anordnung der überlappenden Substrate durch die Pressvorrichtung ausgesetzt war, bevor die zum Verbinden der Substrate mit einer demgegenüber, insbesondere sprunghaft, erhöhten Presskraft ausgeführte Druckbeaufschlagung einsetzte;
• - eine, insbesondere konstante, Nachspannungskraft, der die Anordnung der dann bereits verbundenen Substrate durch die Pressvorrichtung ausgesetzt wurde, nachdem die zum Verbinden der Substrate mit einem demgegenüber, insbesondere sprunghaft, erhöhten Presskraft ausgeführte Druckbeaufschlagung erfolgt war;
• - eine Differenz oder ein Verhältnis aus Vorspannungskraft und Nachspannungskraft;
• - ein Indikator, der eine Arbeitsstellung kennzeichnet, bei der ausgehend von der Vorspannungskraft die mit einer demgegenüber, insbesondere sprunghaft, erhöhten Presskraft ausgeführte Druckbeaufschlagung zum Verbinden der Substrate einsetzte oder ansteigend eine erste vorbestimmte Kraftschwelle überschritt;
• - ein Indikator, der eine Arbeitsstellung kennzeichnet, bei der nach der mit einer demgegenüber, insbesondere sprunghaft, erhöhten Presskraft ausgeführten Druckbeaufschlagung zum Verbinden der Substrate die Nachspannungskraft einsetzte oder die vorausgehende Druckbeaufschlagung abfallend eine zweite vorbestimmte Kraftschwelle überschritt;
• - eine über ihren Verlauf hinweg bestimmtes Integral der Messgröße.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, at least one of the features is selected from the following list of variables or is defined as a variable that is dependent on at least one variable from the list:

• - an extreme value corresponding to a maximum pressing force, in particular a local or global maximum, of the course of the measured variable;
• - an indicator identifying a working position at which the extreme value occurred;
• a, in particular constant, prestressing force to which the arrangement of the overlapping substrates was subjected by the pressing device before the application of pressure, which was carried out to connect the substrates with a comparatively, in particular abruptly, increased pressing force, began;
• an, in particular constant, post-tensioning force to which the arrangement of the then already connected substrates was subjected by the pressing device after the application of pressure carried out to connect the substrates with a pressure force that was increased, in particular suddenly, in comparison thereto, had taken place;
• - a difference or ratio of preload force and postload force;
• an indicator that characterizes a working position in which, starting from the prestressing force, the pressurization applied with a press force that is higher than this, in particular abruptly, for connecting the substrates, began or increasingly exceeded a first predetermined force threshold;
• an indicator that characterizes a working position in which, after the pressurization for connecting the substrates, which was carried out with a pressure that was increased, in particular abruptly, the post-tensioning force started or the previous pressurization fell and exceeded a second predetermined force threshold;
• - an integral of the measured variable determined over its course.

A (first) variable is “in a dependent relationship” with at least one (second) variable from the list if it can be determined in a predetermined manner, in particular in the sense of a (especially injective) mathematical function, from the at least one (second) variable from the list on which it depends. In particular, such a dependency relationship can also be defined using mathematical differentiation or integration.

The prestressing and/or the restressing can be effected in particular by means of a spring force or gas pressure acting on the substrates or the composite product, for example in order to secure the still unconnected substrates against slipping relative to one another (in the case of prestressing) or in both cases to secure the substrates or the composite product produced therefrom from slipping relative to a support. The means used to bring about the prestressing and/or post-stressing can differ in particular from the means used for pressurization. For example, the pretensioning and/or posttensioning can be effected solely by a spring force, while the pressurization is effected by a pressure piston or a motor-driven actuator.

The features mentioned in the list (and possibly the variables that are dependent on them) have proven to be particularly suitable variables for identifying faulty executions compared to fault-free executions of the joining process using a combination of two or more of these variables.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, sensor data is recorded as measurement data that was or is being recorded on the basis of measurements using at least one of the following sensor types: load cell, strain gauge, accelerometer. What these sensor types have in common is that they make it possible to directly or indirectly measure the pressing force exerted on the material to be pressed by the pressing device as a function of its respective working position.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, the measurement data are subjected to pre-processing to improve the data quality and at least one of the features is extracted from the measurement data prepared as part of the pre-processing. For this purpose, the pre-processing can in particular include filtering of the measurement data to reduce or eliminate high-frequency interference. In this way, the quality of the subsequent feature extraction can be increased and, as a result, the probability of incorrect assessments based thereon can be reduced.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, the pre-processing includes transforming the measurement data in such a way that the transformed measurement data still represent the measurement variable as a function of the working positions of the pressing device or the variable corresponding to the working positions, but they are independent of the speed of the pressurization exerted by the pressing device (i.e. of the mathematical derivation of the pressing pressure or the pressing force over time). The result of the preprocessing thus represents the measurement data, such as a force profile, with reference to a speed-independent variable, such as a position of a pressing tool of the pressing device that characterizes a working position. As a result, the speed plays no role in the subsequent determination of the features. Since small fluctuations in speed often cannot be avoided, the transformation serves in particular to make the method even more robust in relation to disturbances or in relation to process fluctuations that are difficult or impossible to control.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, the evaluation indicator is determined as a function of the extracted features and the features are weighted with respective assigned weight values. This can be done in particular by forming a weighted sum. In this case, the weighting of the features can be defined in particular on the basis of respective weighting factors individually assigned to the features. It is thus possible to use the various characteristics used to monitor the joining process to different extents in determining the evaluation indicator. If the weights can also be determined variably, the evaluation indicator can be achieved, especially iteratively, as a very good approximation of an "ideal" evaluation indicator.

In some such embodiments, the instructions further configure the data processing system to: As part of the method, the characteristics are each quantified using at least one respective value from a predefined, limited set of values that is individual for each characteristic or the same for all characteristics, and these values are included in the determination of the evaluation indicator with the respectively assigned weight values. For example, the set of values can be defined by the numeric range [0; 1] to be given. Such a normalization facilitates the implementation and efficiency of the method. In particular, it is possible in this way to achieve the same accuracies or those that deviate only slightly from one another with regard to the quantification of the individual features.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, at least one of the weight values is derived on the basis of the respective evaluation results of one or more previous executions of the joining process, with these evaluation results each indicating a faulty joining process. Determining the weight values on the basis of faulty process executions allows a particularly effective and rapid convergence of the weight values towards a respective ideal value. Several process executions with different error causes are used as a basis in order to be able to correctly identify a large number of different errors later after the weight values have been determined.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, within the scope of the method, the evaluation indicator is determined using a trained machine learning model with the extracted features as input variables of the machine learning model. An artificial neural network (ANN) is particularly suitable as a machine learning model, the parameters (weights of its neurons) of which are optimized as part of training with suitable training data. The training data can in particular have a large number of different data sets, each of which has a possible value assignment for the features serving as input variables and a correct value for the evaluation indicator to be assigned to it. Compared to a weighting scheme that is defined once, the use of a machine learning model has the particular advantage that further continuous optimization of the method is available even after it has been put into operation for the first time and that very complex weighting functions that are otherwise difficult to determine can be determined or approximated very well.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, the comparison of the determined evaluation indicator with a defined evaluation reference includes a comparison of the determined evaluation indicator with at least one predetermined evaluation threshold serving as an evaluation reference. The evaluation indicator or the regulation, e.g. B. Weighting function, for its determination, can be or be defined in particular in such a way that the set of values for the evaluation indicator corresponds to a specific value range, limited in particular on both sides (e.g. [0; 1]), so that the evaluation threshold can only be determined in relation to this value range in a simplified manner.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, the method includes monitoring a multiple, in particular sequential or parallel, execution of the joining process to produce a corresponding number of composite products. In addition, the evaluation is carried out for each monitored joining process. For each joining process, the respective evaluation result is stored in a data structure, in particular in a shift register, or database in such a way that the evaluation results are assigned to the respective joining processes and the respective individual evaluation results of each of the joining processes can be inferred from the contents stored in the data structure or database. The method can thus be extended to a plurality, in particular a large number, of process executions in such a way that the respective evaluation results, in particular several at the same time, remain at least temporarily retrievable even after the respective execution of the joining process. In particular, in the case of a production line, the evaluation results can "run along with the composite products" along the further production process in this way, so that they can also be evaluated for any workstations arranged downstream of the pressing device in the process flow, e.g. a station for ejecting defective parts.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that the pressing device is controlled for each joining process as part of the method depending on the respective assigned evaluation result stored in the data structure or database. In particular, it is conceivable that the pressing process is stopped or carried out in a different way than in the error-free case, if based on of the saved evaluation result, an error is detected during process execution. This can be used in particular to prevent or reduce any avoidable damage or soiling of the pressing device, for example due to crushed foreign bodies or objects to be packaged.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that, as part of the method, the evaluation results are transmitted to a controller of the pressing device using communication based on the known OPC Unified Architecture (OPC-UA) information model, in particular according to its version 2 (e.g. version 2.0), in order to enable it to control the pressing device depending on the evaluation result and/or to cause it to do so. The evaluation results can thus be transmitted in a standardized and therefore manufacturer-independent and reliable manner.

In some embodiments, the data processing system is further configured on the basis of the instructions in such a way that a sealing machine, in particular a plate sealing machine, is used as the pressing device within the scope of the method in order to connect two or more of the substrates to form a blister pack. Such a blister pack can be configured in particular for the packaging of medicaments in tablet form, food supplements or cosmetic products. In the case of blister packaging in particular, there is always a risk that the objects to be packaged (e.g. tablets) will end up outside of the spaces intended for them and therefore disrupt the joining process and lead to defects in the resulting composite product. In addition, with such products, the requirements for the integrity of the products and their packaging are regularly particularly high, so that high-quality monitoring of their production and packaging is particularly relevant here.

A second aspect of the present solution relates to a system for executing and automatically monitoring a joining process for connecting a plurality of substrates arranged in an overlapping manner to form a composite product under pressure from a pressing device, in particular a plate sealing machine, the system having the pressing device including a controller for it and the data processing system according to the first aspect, which is set up to communicate certain evaluation results for the joining process to the controller according to the method (i.e. according to the method). The data processing system and the controller can in particular also coincide, so that the data processing system is then configured at the same time to take over the functions of the controller.

The instructions can in particular be in the form of a computer program or computer program product.

The computer program (or the instructions) can (or can) be stored in particular on a non-volatile data carrier. This is preferably a data carrier of the system according to the second aspect, for example a data carrier in the form of an optical or magnetic data carrier or a flash memory module or some other non-volatile semiconductor memory. In another implementation, the computer program can be present as a file on a system-external data processing unit, in particular on a server, and can be downloaded to the data processing system according to the first aspect via a data connection, such as the Internet or a dedicated data connection, such as a proprietary or local network. In addition, the computer program can have a plurality of interacting individual program modules. In particular, the modules can be configured or at least used in such a way that they are executed in the sense of distributed computing on different devices (computers or processor units that are geographically spaced apart and connected to one another via a data network.

The features and advantages explained in relation to the first aspect of the solution also apply accordingly to the second aspect of the solution.

Further advantages, features and application possibilities of the present solution result from the following detailed description in the context of the figures.

• 1 ein Flussdiagramm zur Veranschaulichung einer beispielhaften Ausführungsform des anhand der Anweisungen definierten Verfahrens zur automatischen Überwachung eines Fügeprozesses, .
• 2A einen beispielhaften zeitlichen Verlauf einer erfassten Messgröße;
• 2B einen beispielhaften zeitlichen Verlauf einer Positionskoordinate, deren Werte zu verschiedenen Arbeitsstellungen einer verfahrensgemäß verwendeten Pressvorrichtung korrespondieren;
• 2C schematisch ein Vorverarbeiten der Messgröße aus 2A und die Kombination von ihrem Verlauf mit dem Verlauf der Positionskoordinate aus 2B, um einen Verlauf der vorverarbeiteten Messgröße in Abhängigkeit von der Positionskoordinate zu erhalten;
• 3A ein Schema zur Illustration einer Extraktion verschiedener Merkmale aus dem Verlauf der Messgröße, insbesondere gemäß 2C;
• 3B-D verschiedene Diagramme zur Illustration der Merkmalsextraktion für drei verschiedene beispielhaft ausgewählte Merkmale;
• 4A ein Flussdiagramm zur Illustration eines Prozesses zur Bestimmung einer einem jeweiligen Merkmal zugeordneten quantifizierten Bewertung, hier am Beispiel des Merkmals „Maximalkraft“;
• 4B ein numerisches Beispiel für den Prozess aus 4A;
• 5A ein Flussdiagramm zur Illustration eines Prozesses zur Bestimmung eines Bewertungsindikators für den Fügeprozess mittels einer gewichteten Summe der jeweiligen Bewertungen der einzelnen Merkmale;
• 5B ein numerisches Beispiel für den Prozess aus 5A; und
• 6 schematisch eine beispielhafte Ausführungsform eines zur Durchführung des Verfahrens aus den vorausgehenden Figuren eingerichteten Systems zur automatischen Überwachung eines Fügeprozesses.

It shows:

• 1 a flowchart to illustrate an exemplary embodiment of the method defined using the instructions for automatically monitoring a joining process, .
• 2A an example of a measured variable over time;
• 2 B an exemplary time profile of a position coordinate whose values correspond to different working positions of a pressing device used according to the method;
• 2C schematically a pre-processing of the measured variable 2A and the combination of its history with the history of the position coordinate 2 B , in order to obtain a course of the pre-processed measured variable as a function of the position coordinate;
• 3A a scheme for illustrating an extraction of various features from the course of the measured variable, in particular according to 2C ;
• 3B-D various diagrams to illustrate the feature extraction for three different features selected as examples;
• 4A a flowchart to illustrate a process for determining a quantified evaluation assigned to a respective characteristic, here using the example of the “maximum force” characteristic;
• 4B a numerical example of the process 4A ;
• 5A a flowchart to illustrate a process for determining an evaluation indicator for the joining process using a weighted sum of the respective evaluations of the individual features;
• 5B a numerical example of the process 5A ; and
• 6 schematically shows an exemplary embodiment of a system for automatically monitoring a joining process that is set up to carry out the method from the preceding figures.

In the figures, the same reference numbers denote the same, similar or corresponding elements. Elements depicted in the figures are not necessarily drawn to scale. Rather, the various elements shown in the figures are presented in such a way that their function and general purpose can be understood by those skilled in the art. Unless expressly stated otherwise, connections and couplings between functional units and elements illustrated in the figures can also be implemented as indirect connections or couplings. Unless otherwise specified in detail or only technically possible in a specific way, functional units can be implemented in particular as hardware, software or a combination of hardware and software.

In 1 an exemplary embodiment 100 of the method defined on the basis of the instructions for automatically monitoring a joining process is shown as a flowchart. The method 100 can be used in particular by the in 6 illustrated system 600 are executed. The method 100 is therefore explained below with exemplary reference to the system 600, which is therefore described first.

The system 600 has a pressing device 605 for carrying out a joining process in which two or more substrates, for example plastic or metal foils, are pressed together under pressure by means of a pressing force in order to connect the substrates to form a composite product P in a materially bonded or form-fitting manner. The pressing device 605 can be, in particular, as in 6 illustrated to be a sealing machine, specifically a platen sealing machine, for the production of blister packs. Blister packs of this type can be used, for example, for packaging medicinal products, in particular tablets. Such a plate sealing machine can in particular, as shown, have two pressing tools 105a and 105b, between which the substrates to be connected are inserted overlapping, in particular stacked on top of one another, in order to then be subjected to pressure or the pressing force between the pressing tools 105a,b.

For its control by means of suitable control signals C, the pressing device 605 has a control unit 610, which is implemented in particular by means of a programmable logic controller (PLC).

Furthermore, the system 600 has a sensor system 615 for acquiring measurement data which, for various working positions assumed by the pressing device 605 during the application of pressure, represent respective measured values of a measured variable which indicates a pressing force exerted by the pressing tools 605a, b on the substrates during the respective working position or a variable that is dependent on it, such as a pressing pressure or an acceleration corresponding to the pressing force. In particular, load cells, strain gauges and accelerometers come into consideration as sensor types.

The system 600 also includes a data processing system 620 , such as a computer with a memory 625 . The other in 6 The components of the system 600 illustrated are introduced below in the explanation of the method 100 .

Now, the explanation of the method 100 is added to 1 referenced. The method 100 can be designed in particular as a computer-implemented method and can be run on the data processing system by means of a be implemented, for example, in the computer program stored in the memory 625.

As part of the method 100, the measurement data for the at least one measurement variable are first recorded in a process 105, for which purpose the measurement data are received by the sensor system 615.

An example of a time course 200 of the measured variable “press force” represented by recorded measurement data is in 2A illustrated. The time course covers a pressing process in which the substrates to be connected are first prestressed against each other ("prestressing", VSP), then are connected to each other with increased pressing force (pressing stress, PSP) and finally remain tensioned against each other again with a comparatively lower pressing force ("post-stressing", NSP). The prestressing can be carried out in particular (solely) by means of a spring force at a first level of pressing force that is not yet sufficient for connecting the substrates, with the overlapping substrates that are then not yet connected being clamped between the tools 605a, b in order to secure them against slipping, to eliminate any air pockets between surface sections to be connected, and/or to eliminate undesired deformations of the substrates. The connection under pressure with a higher pressing force can be carried out with a dedicated pressing mechanism, for example hydraulically or using a motor to generate the pressing force. Like the pre-tensioning, the post-tensioning can again be provided alone or at least to a large extent by a spring force, although other designs are also conceivable.

The recorded measurement data also represent an exemplary in 2 B illustrated time course 205 of the working position of the pressing device, in particular the relative position of the tools 605a and 605b to one another. In this case, the range of the working positions assumed one after the other during the execution of the joining process can expediently be normalized, for example to a degree range [0°; 360°] for a complete process execution, which in particular can be periodically repeatable. The term "position" is used below to indicate the respective working position in relation to this degree range. Of course, other ways of quantifying different jobs are possible instead.

After being recorded in process 105, the recorded measurement data are pre-processed in a further process 110, in particular as in 2C illustrated. The pre-processing can in particular include filtering 215 (in particular low-pass filtering) the time profile 200 of the measured variable(s) represented by the measurement data in order to remove any interference (in particular high-frequency interference, as in 2A recognizable) in it to be removed or at least reduced.

During the pre-processing, the (possibly filtered) curve 200 and the curve 205 are also linked (typically mathematically) as part of a transformation 220 in order to obtain a curve of the measured variable(s) as a function of the working position (position). In the example chart 210 off 2C two different curves of the measured variable are already shown as a function of the position, with the curve with the lower maximum corresponding to error-free process execution, while the other curve corresponds to error-prone process execution.

In particular, imagine the case of a blister pack, during the production of which two substrates are to be joined together in such a way that tablets to be packed are ideally only ever stored in one of the courtyards formed by the substrate. The error-free curve in diagram 210 characterizes the joining process. Initially, only the essentially constant preload is applied, before the force then increases significantly at a position of around 80° and ends in a maximum. Here the two pressing tools 605a, b are thus pressed together to the maximum extent in order to connect the substrates, while the tablets lying in the pockets are not subjected to the pressing force. During the subsequent pressure reduction, a step occurs in the force curve before the force then falls continuously to the post-tension.

In the event of an error, on the other hand, at least one of the tablets comes to rest at least partially outside of its assigned area, so that when the pressing tools 605a, b are brought together earlier (approximately at 70°) than in the error-free process, an increase in the pressing force acting on the substrates is recorded because the mentioned tablet(s) act as resistance. The maximum power is also correspondingly higher than in the error-free course and even the post-tensioning can set in later. The area or the integral under the curves is therefore different. These and possibly other differences in the curves can be used in the following to accomplish a quality assessment of the joining process.

An advantage of the representation according to diagram 210 is that the course of the measured variable is available here independently of the speed of the process run, so that speed fluctuations in the further course of the proceedings does not matter. The curve progression can thus be analyzed independently of the speed.

As part of the method 100, there follows a further process 115, in which the pre-processed measurement data (cf. 2C ) various features characteristic of the course 210 are extracted. this is in 3A 1, where a scheme 300 for extracting four different features in respective extraction processes 305 to 320 is shown by way of example.

3B illustrates the extraction process 305 in more detail, in which a first feature “maximum force” is extracted, which characterizes the maximum pressing force that occurs in the course of the measurement. In 3B is here for two different product types each according to the type 2C Corresponding course of the pressing force is shown, including the position of the respective maxima (extreme values) E1 and E2 occurring during the pressing phase following the prestressing. If required, their position can be calculated and calculated in a known manner, in particular using differential calculus. The maxima represent the values sought for the first characteristic.

3C Figure 12 illustrates in more detail the extraction processes 310 and 315 extracting the second feature, "threshold crossing in rise" and the third feature, "threshold crossing in decay". These are the positions S1 and S2, in which the force progression, starting from the pretension, exceeds a defined rise force threshold F1 on the rise (second feature) or exceeds a defined fall force threshold F2 on the fall before the posttension is reached. The distance between these two positions determined in this way is also suitable as a feature.

3D 320 illustrates the extraction process 320 in more detail, in which a fourth feature "area integral" is extracted, which characterizes an integral under the history of the pressing force, where (as shown) the position areas of the prestress VSP and the poststress NSP can be disregarded in order to achieve a higher sensitivity of the feature. In 3D this is illustrated by way of example for two different curves, with the integrals A1 and A2 being determined as areas under the curves (in this example, the area A1 also contains the area A2 as a partial area). In particular, this can be done in a known manner using methods of numerical integration.

up again 1 Referring to this, a further process 120 follows in the method 100, in which an evaluation indicator for the quality of the joining process is determined from the extracted features in a number of stages.

A first stage of this process 120 is in 4A and as a suitable concrete numerical example 401 in 4B illustrated. In this first stage, it is a matter of carrying out an individual assessment as part of a process 400 for each of the extracted features. In the 4A and 4B this is done as an example for the first characteristic "maximum force" (F _max ), but the same methodology can be adopted accordingly for the other characteristics.

For this purpose, it is assumed that the joining process is carried out repeatedly, in particular in cycles, as is customary in particular in the production of blister packs. First, in a current cycle n, a mean value ∅F _max is calculated in step 410 from several, in the specific example four, measured values 405 of the immediately preceding cycles n-4 to n-1, i.e. the individual measured values F _max,n-4 to F _max,n-1 . In a further step 415, a deviation (specifically a difference here) X between this mean value φF _max and a measured value F _max,n taken from the measurement data for the current cycle is determined. This deviation X is then compared in a step 420 with an evaluation threshold TH ₁ defined for the first feature. If the deviation is above this evaluation threshold TH ₁ , the feature is evaluated in a further step 435 with a first value (here with B ₁ ="1"), otherwise with a different second value (eg B ₁ ="0"). In particular, a binary value assignment is therefore possible here. All other features are evaluated in a corresponding manner, in particular using feature-specific individual evaluation thresholds TH _i , in order to obtain respective evaluations B ₂ to B ₄ .

A second stage of the process 120 is in the left part of an in 5A illustrated process 500 and as a concrete numerical example 501 in 5B illustrated. In this second stage, the values B ₁ to B ₄ of the extracted features determined in the first stage are each weighted and combined with an individual weight value, in particular a respective weighting factor W ₁ to W ₄ , which can be done in particular by forming a sum of the weighted values (W _i · B _i ) of the features. The weighting factors W ₁ to W ₄ are expediently normalized in accordance with the value range of the values B ₁ to B ₄ in such a way that their sum results in the value 1. The result of the weighted sum is an evaluation indicator Y, whose value is in the value interval [0; 1] lies. Optimum values for the weight values or present weighting factors, W ₁ to W ₄ can be determined in advance, especially in the context of test series. Alternatively, the evaluation indicator Y can be determined using a trained machine learning model with the values B ₁ to B ₄ of the extracted features as input variables of the machine learning model, with the weighting factors W ₁ to W ₄ being determined automatically as part of the training. An artificial neural network as a machine learning model is particularly suitable for this purpose.

Based on the evaluation indicator Y determined in this way, the joining process can now be evaluated in a further process 130 as part of the method 100 by comparing the evaluation indicator Y with a predetermined evaluation reference, in particular an evaluation threshold TH, in particular directly comparing it, with a corresponding evaluation result B being generated as the result of the comparison, which can be used as a quality evaluation for the joining process.

Finally, the pressing device 605 or, more generally, the system 600 and thus the further course of the process for treating the composite product P produced in the current cycle in the pressing device can be controlled as a function of the evaluation result B within the scope of a process 135 . Such a control 135 can in particular also include a (re)calibration of the pressing device. Another possibility, which can also be used cumulatively for this purpose, is to carry out a separation of good parts and defective parts depending on the evaluation results B per cycle.

This is also in 6 illustrated, where in the system 600 there is also an ejection device 630 downstream of the pressing device 605 in the process flow, which can be controlled by the data processing device 620 depending on the evaluation result B of the current cycle in such a way that if the evaluation result B indicates a faulty joining process, the composite product P produced is treated as a defective part and is ejected from the process by the ejection device 630 and, for example, into a collection depot 635 is transferred for defective parts. Otherwise, if the evaluation result B characterizes an error-free joining process, the composite product P produced is treated as a good part and is fed to the further process flow 640 for good parts.

In the case of the already mentioned repeated, in particular clocked, execution of the method 100, the evaluation results per execution can be stored in particular in a data structure or database in such a way that the evaluation results B are assigned to the respective executions of the joining process, so that the respective individual evaluation results of each of the joining processes can be inferred from the contents stored in the data structure or database. A shift register is particularly suitable as the data structure. The data structure or database can be stored in particular in the memory 625 of the system 600 and can be configured to be accessible for the ejection device 630 and/or for further workstations in the system 600 that are used along the further course of the process 640 . In this way, the evaluation results can "wander through the process" with the composite products P that are produced, ie remain continuously available. In particular, the evaluation results B can be communicated within the system 600 according to the OPC UA information model (e.g. according to its version V. 2.0).

Reference List

100

Method for monitoring a joining process

105 - 135

Process steps of the process 100

200

chronological progression of the "pressing force" measured variable

205

Time course of the working position of the pressing device

210

Courses of the "pressing force" measured variable as a function of the working position

215

Pre-processing, in particular (low-pass) filtering

220

Transformation of the curves 200 (after pre-processing) and 205 to determine the curve 210

300

Feature Extraction Scheme

305

Extraction of a first characteristic "maximum force"

310

Extraction of a second characteristic "threshold exceeded in increase"

315

Extraction of a third characteristic "threshold exceeded in the waste"

320

Extraction of a fourth feature "area integral"

400

Process for the individual evaluation of characteristics, using the example of the first characteristic

401

numerical example for process 400

405

Measured values for the (first) characteristic for previous work cycles

410

Averaging over the measured values 405

415

subtraction

420

Comparison with feature-related threshold

425

individual evaluation of the (first) feature

500

Process for determining an evaluation indicator for the joining process

501

numerical example for process 500

600

Systems for executing and automatically monitoring a joining process

605

Press device, in particular sealing machine for blister packs

605a, b

pressing tools

610

Control unit of the pressing device, in particular SPS

615

Sensor technology for recording measured values for measured variable(s)

620

data processing system

625

Memory, in particular program memory and/or data memory

630

rejection device

635

Collection depot for ejected defective parts

640

further process flow for good parts

B

Evaluation indicator for joining process

Bi

Value of the i-th feature

C

control signals

D

Data

E1, E2

maximum force values

Fmax,j

Measured values for the first characteristic "maximum force" with j = n-4,..., n-1

∅Fmax

Mean value of the measured values F _max,j

Fmax,n

current measured values for the first characteristic "maximum force"

F1

climb force threshold

F2

waste power threshold

NSP

post-tension or post-tension force

P

connection product

psp

press tension

th

Rating threshold as rating reference for rating indicator

THi

individual evaluation threshold for the i-th characteristic

VSP

Preload or preload force

Wi

Weight of the i-th feature

X

Deviation from the mean

Y

weighted sum of the values of the characteristics

Claims (16)

Data processing system (620) for automatically monitoring a joining process for connecting a plurality of substrates arranged in an overlapping manner to form a composite product under pressure by a pressing device (605), the data processing system (620) having at least one processor platform and a memory coupled thereto, in which instructions are stored which, when they are executed on the processor platform, cause the latter to carry out a method (100) which has the following steps: recording (105) measurement data which are 605) working positions taken within the framework of the pressurization represent respective measured values of a measured variable which specifies a pressing force acting on the substrates during the respective working position or a variable which is dependent on it; Evaluating the recorded measurement data in order to extract from it a plurality of different features (115; 305,...,-320), which individually and/or together represent at least one characteristic property of a profile (210) of the measurement variable represented by the measurement data as a function of the working positions of the pressing device (605) or of a variable corresponding to the working positions; determining (120) an evaluation indicator (B) defined as a measure for a quality of the joining process as a function of the extracted features; Evaluation (130) of the joining process based on a comparison of the determined evaluation index kators (B) with a defined evaluation reference, generating an evaluation result resulting from the comparison; and controlling (135) the pressing device (605) and/or further treatment, in particular further processing, ejection or marking, of the composite product produced by means of the joining process depending on the evaluation result. data processing system (620). claim 1 , wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope _of the method at least one of the features is selected from the following list of variables or is defined as a variable that is dependent on at least one variable from the list: - an indicator identifying a working position at which the extreme value occurred; - a prestressing force (VSP) to which the arrangement of the overlapping substrates was subjected by the pressing device (605) before the pressing effected to bond the substrates with a pressing force which was increased compared thereto; - a post-tensioning force (NSP) to which the assembly of the then already bonded substrates has been subjected by the pressing device (605) after the pressurization carried out to bond the substrates with a press force which is increased in relation thereto; - a difference or ratio of preload force (VSP) and postload force (NSP); - an indicator that characterizes a working position in which, starting from the pretensioning force (VSP), the pressurization, which is carried out with a press force which is increased in comparison, for connecting the substrates, begins or increasingly exceeds a first predetermined force threshold (F1); - an indicator that characterizes a working position in which, after the pressurization for connecting the substrates, which was carried out with an increased pressing force, the post-tensioning force (NSP) started or the previous pressurization fell and exceeded a second predetermined force threshold (F2); - an integral of the measured variable determined over its course (210). Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope of the method (100) sensor data are recorded as measurement data which were or are recorded on the basis of measurements with at least one of the following sensor types: load cell, strain gauge, accelerometer. Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that as part of the method (100) the measurement data are subjected to pre-processing (110, 215) to improve the data quality, and at least one of the features is extracted from the measurement data prepared as part of the pre-processing (110; 215). data processing system (620). claim 4 , wherein the data processing system (620) is further configured on the basis of the instructions such that as part of the method (100), the preprocessing (110; 215) includes filtering (215) the measurement data to reduce or eliminate high-frequency interference. data processing system (620). claim 4 or 5 , wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope of the method (100) the pre-processing (110; 215) includes a transformation of the measurement data in such a way that the transformed measurement data still represent the measurement variable as a function of the working positions of the pressing device (605) or as a variable corresponding to the working positions, but they are independent of the speed of the pressurization exerted by the pressing device (605). Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope of the method (100) the determination of the evaluation indicator (B) depending on the extracted features is weighted for the features with respective assigned weight values (W _i ). data processing system (620). claim 7 , wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the framework of the method (100) the characteristics are each quantified on the basis of at least one respective value from a predefined limited set of values that is individual for each characteristic or is the same for all characteristics, and these values with the respectively assigned weight values (W _i ) flow into the determination of the evaluation indicator (B). data processing system (620). claim 7 or 8th , where the data processing system (620) is further configured on the basis of the instructions in such a way that, as part of the method (100), at least one of the weight values (W _i ) is derived on the basis of the respective evaluation results of one or more previous executions of the joining process, with these evaluation results each indicating a faulty joining process. Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope of the method (100) the evaluation indicator (B) is determined using a trained machine learning model with the extracted features as input variables of the machine learning model. Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope of the method (100) the comparison of the determined evaluation indicator (B) with a defined evaluation reference comprises a comparison of the determined evaluation indicator (B) with at least one predetermined evaluation threshold serving as an evaluation reference. The data processing system (620) of any preceding claim, wherein the instructions further configure the data processing system (620) to perform, as part of the method (100): a multiple execution of the joining process is monitored to produce a corresponding number of composite products; and the evaluation is carried out for each monitored joining process, with the respective evaluation result for each joining process being stored in a data structure or database in such a way that the evaluation results are assigned to the respective joining processes, so that the contents stored in the data structure or database can be used to draw conclusions about the respective individual evaluation results of each of the joining processes. Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is also configured on the basis of the instructions in such a way that within the scope of the method (100) the pressing device (605) is controlled for each joining process depending on the respective assigned evaluation result stored in the data structure or database. Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that as part of the method (100) the evaluation results are transmitted to a controller (610) of the pressing device (605) using communication based on the OPC-UA information model in order to enable it to control the pressing device (605) depending on the evaluation result and/or to cause it to do so. Data processing system (620) according to one of the preceding claims, wherein the data processing system (620) is further configured on the basis of the instructions in such a way that within the scope of the method (100) a sealing machine is used as the pressing device (605) in order to connect two or more of the substrates to form a blister pack. System (600) for carrying out and automatically monitoring a joining process for joining a plurality of substrates arranged in an overlapping manner to form a composite product with the application of pressure by a pressing device (605), the system (600) having the pressing device (605) including a controller (610) for it and the data processing system (620) according to one of the preceding claims, which is set up to transmit evaluation results for the joining process determined by it according to the method (100) to the controller (61 0) to communicate.

Images