In an online survey, representatives of the plastics industry formulated their expectations toward the Plastics Innovation Center 4.0 (PIC 4.0).

Wordcloud generated from the answers to the open question concerning the most important use cases for PIC 4.0

Part 5 of the Series: Practical Demonstrators for the Plastics Innovation Center 4.0

Spritzgießen

Kunststoffverarbeitung: Verfahren

Industrie 4.0 für die Qualitätssicherung

Industrie 4.0

Messdatenerfassung und -verarbeitung

Software

Steuern, Regeln

Digitale Transformation

Wirtschaft

Innovationen und neue Technologie

Prozessoptimierung

Prozessmanagement

Machine Learning

Datenanalyse

Industrie 4.0 für die Kunststoffverarbeitung

Automatisierungstechnik

Kunststoff-Rezyklat

Kunststoff Werkstoffe

Focus on the User Benefit

The Wilhelm Böllhoff GmbH & Co. KG employs Arburg’s ALS host computer system as a uniform MES at locations all over the world. Not only all their injection molding machines are networked with information technology via ALS, but hundreds of machines and turnkey systems for metalworking and assembly, as well. Some 3000 injection molds are also managed. This generates transparency in everything from order planning and process optimization to maintenance.

The process status of every machine can be viewed via the ALS terminal

Böllhoff Uses ALS as a Uniform Global MES for Injection Molding and Metalworking

Spritzgießmaschinen, allgemein

Kunststoffverarbeitung: Maschinen und Komponenten

Spritzgießmaschinen

Big Data für die Qualitätssicherung

Qualitätssicherung Kunststoff

Qualitätssicherung

Energiemanagement

Energieeffizienz

Completely Joined to the Host Computer System

The latest trend in digitization  is the Artificial Intelligence of Things. It amounts to “marrying” Artificial Intelligence with the Internet of Things. In the following interview, Martin Dimmler and Martin Rugfelt discuss how companies can profit from AIoT and what plastics manufacturers can learn from its pioneers in other industries.

Where Artificial Intelligence of Things (AIoT) is used, value-adding opportunities for more efficiency, quality, and thus higher sales can be realized in every industry

Artificial Intelligence of Things: Trends and Models for the Plastics Industry

Künstliche Intelligenz für die Qualitätssicherung

Vernetzung / Cloudlösung für die Kunststoffverarbeitung

IoT-Plattformen für die Qualitätssicherung

Fernwartung / Ferndiagnose

Instandhaltung

Produkt- / anbieterspezifische Automatisierung

Automatisierungszellen

Fertigungsautomation

IoT-Plattformen für die Kunststoffverarbeitung

“Intelligent Automation Brings Systems Closer to their Optimum”

Unforeseen downtimes in serial production are always accompanied by high costs, making it essential for machines to be serviced in time. Because sensor, transmission and data storage technology have taken a big leap forward in recent years, predictive maintenance has already been realized in some industries, demonstrating a tangible benefit of Industry 4.0. The WZL and the WBA have developed a guideline for this.

Fig. 1. The guideline for the development of predictive maintenance solutions is divided into three phases: analysis, design and implementation

Guideline to the Development of Predictive Maintenance Systems for Serial Producers and Toolmaking Companies

Condition Monitoring / Prozessüberwachung

Werkzeug- und Formenbau

Dienstleistungen

Werkzeug-, Formen- und Modellbau

Sensoren verschiedener Messverfahren

Sensorik / Aktorik

Dienstleistungsqualität

Qualitätsmanagement

Instandhaltungsmanagement (TPM)

Vorbeugende Instandhaltung für die Qualitätssicherung

Werkzeugbau

Machine Learning für die Qualitätssicherung

Symbiosis of Toolmaking and  Serial Production

A consistent flow of data and information is essential for digital solutions and meaningful analytics. The introduction of potential solutions is therefore often associated with high costs for data preparation.

Exemplary information flow across several steps of the value creation process in injection molding(Work-Center-Layer)

Standardization Guarantees High Data Quality for Future Applications

To Get the Information Flow in a Row

The cluster of excellence “Internet of Production” at the RWTH Aachen University conducts research on structures to realize a “Google of Production”. The Plastics Innovation Center 4.0 serves as demonstration platform to present real-world solutions to the industry already today.

The Plastics Innovation Center 4.0 as part of  a network of research facilities at the Campus Melaten, Aachen, focused to production technology

IKV Offers an Application-Oriented Demonstration Platform for Excellent Research

The PIC 4.0 as Part of the Internet  of Production

iQ process observer, the new process monitoring platform from Engel monitors hundreds of parameters from the injection molding cell in the background.

The injection molder is truly not a friend of changes – if they occur in the running process. The iQ process observer helps him to keep an eye on the process and thus keep a handle on the quality

A Process Monitoring Platform Monitors Several Hundred Parameters Simultaneously

Steuerungen (Hardware und Software)

Prozessvisualisierung

Spritzgießsimulation

Simulation

An Eye on the Process –  a Handle on Quality

With the completion of the Plastics Innovation Center 4.0, the research infrastructure of the IKV in Aachen, Germany, has been significantly expanded. I

Optical measurement and CAD export of the real component geometry allow deviations from the original and simulation geometry to be compared node by node.

16:9

With the completion of the Plastics Innovation Center 4.0, the research infrastructure of the IKV in Aachen, Germany, has been significantly expanded.

Part 10 and Conclusion: The Digitalization of Plastics Processing Gets a Home

Everything under One Roof

Many properties of plastic sheet and film can be effectively modeled and predicted by means of a structured methodology, and precisely controlled thanks to model-based multivariable control. Rejects are minimized and production costs considerably reduced.

Fig. 1. Twin-screw extruder, slit die and roll with atline permeability measurement for acquiring the test data

Predicting and Controlling Barrier Properties with Data Analysis

Prozesssimulation

Flachfolien- und Plattenextrusion

Extrusion

Extruder

Extrusionsanlagen

Big Data

Big Data Surmounts the Barrier

Cost risks and the loss of knowledge threatened by demographic change, form a scenario for the toolmaking industry for which automated tool design could be a conceivable way out.

Partial automation of the demolding system represents an important step towards complete automation of injection mold design.

Automated Design of the Demolding Systems of Injection Molds

Werkzeugkonstruktion

Spritzgießwerkzeuge

Werkzeuge für die Kunststoffverarbeitung

Analysetools, FEM

Digitaler Zwilling

Anticipation of a Larger  System Landscape

Maintaining competitiveness while producing in Germany requires not only cost-efficient production, but also high-quality products. Vorwerk Elektrowerke is accepting this challenge. In collaboration with the Institute of Product Engineering at the University of Duisburg-Essen, Germany, the company is testing a 100 % inline quality monitoring system as well as a quality prediction using machine learning.

Customers who choose the Kobold VK 200 vacuum cleaner expect top quality. To ensure this, efforts for the introduction of Industry 4.0 measures are taken in the production plant in Wuppertal, Germany

Successfully Managing Digital Transformation with Automation and Artificial Intelligence

Mehrkomponenten-Spritzgießen

Kameras, intelligente

Bildverarbeitung

Machine Learning / Künstliche Intelligenz für die spanende Fertigung

Industrie 4.0 für die spanende Fertigung

Inline- / Online-Messsysteme

Inline Quality Monitoring and  Data-Based Quality Prediction

The iQ product family from Engel will gain a new member at K 2022. iQ hold control automatically determines the optimum holding pressure time for the particular mold with no input from the operator.

 The optimum holding pressure time is often lower than that established at the beginning. In these cases, the cycle time is shortened.

iQ hold control Determines the Optimum Holding Pressure Time

Smart Factory

Energiedatenmanagement

Holding out for Higher Quality

The iQ motion control assistance system from Engel optimizes the acceleration phases of mold movements and thus shortens cycle times.

The pressure to work efficiently is huge, especially in the packaging industry. The production of thin-wall containers clearly shows the potential of  iQ motion control to shorten cycle times.

iQ motion control Shortens Cycle Times in High-Performance Injection Molding

Elektrische Antriebe für Spritzgießmaschinen

Antriebe

Elektrische Antriebe

How about a Little Bit Faster?

Innovation management affects many areas, which now increasingly include digital services in addition to classic product and process innovation. Beyond the continuous reassessment of technical setups, a platform is being established for the consistent provision and further development of software services and dedicated analysis algorithms. Thereby, services are being provided to generate new ideas from the application and to facilitate the transfer of technology into industrial practice.

The outer skin of the PIC 4.0 is closing, inside the design of the demonstration cells is in full swing.

Part 8 of the PIC 4.0 Series: Flexible Infrastructures Facilitate Access to Innovative Services

Innovationsmanagement

Produktentwicklung (F+E)

Smart Services

Internet der Dinge

Messdatenerfassung, Software

Softwarearchitektur

Adaptable Structures for  More Innovation

Injection molding of optical components is subject to strict requirements, including freedom from internal defects. Tomography analysis methods can identify even microdefects in the order of 20 µm. The main cause of these very small defects are gases that enter the melt either from the material or the environment. With new software, Engel intends to reduce gas inclusions during the processing of transparent plastics and ensures a consistent high melt quality.

The quality of photos taken with the smartphone increases with each new generation of devices. As a consequence thereof, the requirements for plastic optical lenses are increased.

New “optimelt sequence” Software Reduces Microdefects in Optical Components

Technische Optik

Ingenieurwissenschaften

Schnecken und Plastifiziersysteme

Freedom from Internal Defects  for Brilliant Images

Part 9: Consistent Data Structures for Sustainable Access to Secure Knowledge

In production and research, process data and previously defined quality values are tracked to determine optimization models and pursue consistent quality management. In contrast, data that is not relevant to the specific application is rarely recorded.

In production and research, process data and previously defined quality values are tracked to determine optimization models and pursue consistent quality management. In contrast, data that is not relevant to the specific application is rarely recorded. To ensure long-term access to complete and contextualized trial data, research data management in conjunction with process data acquisition is required and initialized at the IKV as part of the Plastics Innovation Center 4.0.

Statistical design and analysis of experiments are central tools in the engineering sciences. In research as well as in industrial setup-procedures, the influence of specific machine-settings on process and quality variables can be investigated with little experimental and measurement effort. Based on research questions and hypotheses, monitoring variables are defined, such as characteristic values for injection pressure or the machine-side screw-acceleration-curves. Real or simulated trials then evaluate the hypothesis.

Although valid results are generated concerning the parameter space that allow a statement to be made about the initial hypothesis, the data collected also allow a large number of other correlations and dependencies to be analyzed that are usually not the focus of concern in the actual case. The research infrastructure of the Plastics Innovation Center 4.0 (PIC 4.0) now shows how the consistency of process-data can be ensured with the aid of structured data-acquisition and digital services in trial and production planning.

The importance of consistent data and reliable data-formats usually raises after a process has been completed. On the one hand, data such as the sensor-signal of a cavity-pressure-sensor, the screw-position of an injection unit or the simulated course of a flow-front-velocity are available, which must first be synchronized and correlated [1]. Different cycle-counters or timestamps may be available in the respective systems. On the other hand, there is also master data on the machine, the mold and the material, a current configuration of the system-technology as well as notes recorded with paper and pen, which are relevant for the significance or the reconstruction of the test series.

If this information gets lost completely or just partially, the results can only be reused to a limited extent outside the specific research-question of concern. Trials with the same mold and the same material even on the same machine must be repeated in case of doubt because, for example, the screw movement was not relevant in previous investigations and was therefore not recorded or there is uncertainty about individual setting values. Data acquisition in PIC 4.0 prevents this by defining a standard dataset that is stored in parallel with focused trials.

Aimless Data-Acquisition,  Unused Data-Graveyards

Consistent data are also important for machine learning methods. Incomplete datasets or those that cannot be unambiguously assigned often limit the direct applicability in industrial production or result in inaccuracy of the derived models [2]. Aimless data-acquisition, on the other hand, leads to unused data graveyards. Setup-procedures open up a good analogy to the experimental trial plans used in research.

Valuable insights into how the setting variables on the production machines depend on each other enable model-based setup-support for consistent quality-assurance. However, the initial challenge is to set up data-acquisition in a targeted manner and to make data available for statistical or data-driven models from the field of artificial intelligence for model-validation long after the original trials. For this purpose, completeness, and the unambiguous assignment of quality variables to setting variables must be ensured.

Increased Efficiency through Standardized Test Planning

Research-data-management covers a broad range of topics. It ranges from the efficient data-acquisition of heterogeneous systems to the fast and simple processing of data into information to the long-term access of generated knowledge while simultaneously linking the relevant data (Title figure) [3]. For the data and information management of a research infrastructure such as that of PIC 4.0, this means specifically keeping track of data from trials consistently and being able to access it beyond the initial research project, for example for model validation in other projects.

The challenge is to keep track of all the process-settings required for reliable reconstruction of the trial data and to assign all the trials to specific trial plans and projects. Two scenarios must be distinguished in the functional sequence for this purpose (Fig. 1). On the one hand, a proactive definition must be made based on the project-specific trial planning, and on the other hand, a retrospective database-query must be made from historical data.

A service platform based on open-source-technologies (ikv-services) developed within the project already supports users in generating statistical experimental designs (Design of Experiments, DoE) in a standardized way [4]. Another module allows the data-acquisition-client (Connector) to be configured by selecting the monitoring variables desired for the particular series of trials (Fig. 2). The Connector queries the monitored quantities and sends the numerical values to an internal broker-network, where they are, among others, stored in a database.

In addition to the individually specifiable target-variables, the set of monitoring variables is expanded by a basic selection that includes all relevant process-settings and helpful measurement-diagrams for screw-movement, even if these are not the focus of the investigations in the specific project. Finally, when the Connector is started, a process-ID is generated that allows data-traces from different devices to be retrospectively assigned to a project. Analog and unstructured data-packages, for example handwritten test-notes or error-logs, can also be attributed to the trials retrospectively.

The second application-scenario concerns the database-query on processes carried out in the past. For this purpose, the database can be searched for the measured variables; however, it is more purposeful to compile the data-traces to the setting-combinations searched for. The concept of the digital shadow developed in the “Internet of Production” cluster of excellence can be implemented and demonstrated close to the application for contextualizing the data within PIC 4.0 [5]. In the form of a further service for the available platform, a functionality is currently being developed that determines and outputs the data-traces of the process-history based on setting-combinations of the process to be defined (digital shadow caster).

With reference to the metadata generated for the processes, as well as the process-ID, corresponding devices and plants can initially be selected as data sources (assets). From these, a user is to define the data sources to be included. Subsequently, the available parameters are to be displayed; the basic configuration is ensured by the trial-planning-scenario. Subsequently, a relevant subset of the data-sets suitable for the intended analysis or model-validation can be exported via an automated database-filter-command.

The need for intelligent filtering techniques arises from the various databases and database-structures that are operated when setting up data-acquisition and for the semantic correlation of individual data-traces. While cycle-related numerical values or character strings can be written into a relational database, metadata (for example master data) on the machine and further equipment used or on the process-configuration are stored in non-relational databases. Since each production system generates its own data traces as a data source, these can each be stored in separate tables in relational databases, while the associated master data can be stored in collections in the non-relational database. The correlation of data traces and metadata can then only take place via unique identifiers such as an order number in an industrial production or the process-ID introduced here.

While the basic collection, storage and archiving of even large volumes of data is no longer a technical problem, it is often still a long way to go before the data can be processed in a targeted manner and any monetary benefit can be generated. The scenarios presented for setting up project-related data-acquisition and retrospective correlation of historical data are intended to generate long-term added value. In addition to the increased transparency and retrievability, this is also expressed in a guaranteed consistency and completeness of the data – for this purpose, further software-services are being developed in addition to the existing ones. In this way, data will also be made usable for answering further questions, such as the transferability of research approaches to different machines and equipment or the processing of other materials.

[1] Hopmann, C.; Bibow, P.: Out of the Shadow into the Light. How the Digital Shadow Enlightens Real Processes in the PIC 4.0. Kunststoffe international 23 (2022) 1, pp. 8–10.

[2] Boureanu, L.: Erfolgreiches Machine Learning dank Datenkonsistenz. Digitale Welt 4 (2021) 3, pp. 68–70

[3] Schmitt, R. H.; Anthofer, V.; Auer, S.; Baskaya, S.; Bischof, C.; Bronger, T.; Claus, F.; Cordes, F.; Demandt, E. I.; Eifert, T.; Flemisch, B.; Fuchs, M.; Fuhrmans, M.; Gerike, R.; Gerstner, E.-M.; Hanke, V.; Heine, I.; Huebser, L.; Iglezakis, D.; Jagusch, G.; Klinger, A.; Krafczyk, M.; Kraft, A.; Kuckertz, P.; Küsters, U.; Lachmayer, R.; Langenbach, C.; Mozgova, I.; Müller, M. S.; Nestler, B.; Pelz, P.; Politze, M.; Preuss, N.; Przybylski-Freund, M.-D.; Rissler-Pipka, N.; Robinius, M.; Schachtner, J.; Schlenz, H.; Schwarz, A.; Schwibs, J.; Selzer, M.; Sens, I.; Stäcker, T.; Stemmer, C.; Stille, W.; Stolten, D.; Stotzka, R.; Streit, A.; Strötgen, R.; Wang, W. M.: NFDI4Ing the National Research Data Infrastructure for Engineering Sciences. Zenodo research shared 2020 (2020), pp. 1–116

[4] Hopmann, C.; Bibow, P.; Seifert, L.; Liu, B.: Adaptable Structures for More Innovation. Flexible Infrastructures Facilitate Access to Innovative Services. Kunststoffe international 23 (2022) 3, pp. 8–10.

[5] Hopmann, C.; Schmitz, M.; Bibow, P.: The PIC 4.0 as Part of the Internet of Production. Kunststoffe international 22 (2021) 2, pp. 7–9.

Institut für Kunststoffverarbeitung IKV in Industrie und Handwerk an der RWTH Aachen

https://www.ikv-aachen.de

Ausgabenartikel

Structure and interconnection along the information-pyramid subsequently generate knowledge from sensorsignals.

Fig. 1. The two scenarios of targeted data assignment: perspective from experimental design (left) or retrospective via database query (right).

Fig. 2. In the user interface for manual Connector configuration (excerpt), project-specific monitoring variables can be individually compiled.

Name - Hauptartikel

The digital shadow is the core-concept of the Cluster of Excellence “Internet of Production”. It describes a semantic aggregation of relevant data traces from different sources to enable a data-based mapping of an object’s (asset’s) behavior in production.

 Univ.-Prof. Dr.-Ing. Christian Hopmann has held the Chair of Plastics Processing as Head of the Institute for Plastics Processing (IVK) in Industry and Craft at RWTH Aachen University, Germany, since 2011.

Pascal Bibow, M.Sc. RWTH, has been working since September 2016 on intelligent production systems at IKV. Since January 2020, he has been Managing Director of the Plastics Innovation Center 4.0;

<a href="mailto:pascal.bibow@ikv.rwth-aachen.de">pascal.bibow@ikv.rwth-aachen.de</a>

Dipl.-Ing. Mauritius Schmitz has been Scientific Director for Digitization and Industry 4.0 since January 2019 at the IKV and has been responsible coordinator of the institute’s research activities in the cluster of excellence Internet of Production.

The construction of the Plastics Innovation Center 4.0 is funded by the State of North Rhine-Westphalia and by the European Regional Development Fund (ERDF).

Das PIC 4.0 is close to completion and the implementation of machine and plant technology is scheduled. In the last article of the series, read about the installed possibilities offered by the PIC 4.0 and its research fields in the future. It appears in one of the next issues.

Read the German version of the article in our magazine Kunststoffe or at <a href="https://www.kunststoffe.de/a/fachartikel/vollstaendige-daten-ohne-wenn-und-aber-2738182" target="_blank">www.kunststoffe.de</a>