Based on interviews in industry, this article describes a common understanding of the most important use cases. The results capture the current direction in the plastics industry.

16:9

Part 1 of the Series: Use Cases Based on Strategic Priorities in Plastics Processing

Strategie und Organisation

Wirtschaft

Spritzgießen

Kunststoffverarbeitung: Verfahren

Industrie 4.0 für die Kunststoffverarbeitung

Industrie 4.0

Compoundieren

Kunststoff-Aufbereitung

Implementation of Industry 4.0 in Injection Molding and Compounding

Under the motto “It‘s all Wittmann”, Wittmann Battenfeld is presenting its machines and systems in the new Wittmann design for the first time.

Automation cell with SmartPlus 90 for manufacturing a spirit level.

Schaumspritzgießen

Messe K-Kunststoffmesse

kunststoffe-international.com

kunststoffe.de

Spritzprägen

Biokunststoffe

Kunststoff Werkstoffe

Energieeffizienz

Spritzgießmaschinen

Kunststoffverarbeitung: Maschinen und Komponenten

Naturmaterialien

Verstärkungsstoffe

Kunststoff-Rezyklat

Green DC Current for the Injection Molding Machine

After the focus was on individual manufacturing and model-supported process set-up in recent years, the Institute for Plastics Processing (IKV) at RWTH Aachen University is linking the two aspects of digitalization and circular economy at K 2022.

The QR code on the PCR component provides project information and process data.

Werkzeuginnendrucksensoren

Messtechnik

Sensoren / Messwertaufnehmer

Digitale Transformation

Innovationen und neue Technologie

Kreislaufwirtschaft

Precise Process Control with Injectix

This year, the world’s leading trade show K has succeeded in presenting practical solutions for greater resource efficiency on a broad front. A first foray through the trade show grounds.

K 2022 gave numerous practical examples showing visitors how recyclates can be reliably processed with digital aids.

State-of-the-Art Injection Molding Solutions for Greater Resource Efficiency.

State-of-the-Art Injection Molding Solutions at K 2022

Doriat, Clemens, Dr.

Solar / PV

Energieerzeugung

Erneuerbare Energie

Temperiertechnik

Mehrkomponenten-Spritzgießen

Condition Monitoring / Prozessüberwachung

Instandhaltung

Spritzgießwerkzeuge

Werkzeuge für die Kunststoffverarbeitung

Handling, Handhabungstechnik

Automatisierungstechnik

Elastomer-Spritzgießen

Oberflächentechnik

Digitalisierung

Silikonkautschuk

Kautschuk / Elastomere

It Can Be Done!

Phase-unifying cavity pressure control reduces process fluctuations, as shown by the example of post-consumer recyclate processing.

The PCR storage box was very popular with visitors.

Phase-Unifying Cavity Pressure Control for PCR Processing

Laserbeschriftung

Laserbearbeitungen

Mess-, Steuer- und Regelgeräte

Qualitätssicherung

Qualitätssicherung Kunststoff

Präzisionswaagen

Mechanische Messtechnik

Precise Process Control with InjectiX

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

Software

Elektrische Antriebe für Spritzgießmaschinen

Antriebe

Elektrische Antriebe

How about a Little Bit Faster?

The road to the energy-optimized injection molding cell is often stony. A saving plan can be drawn up when there is transparency about the individual consumers.

The most varied measures help to save energy, but not all of them are equally profitable for every company.

Nachhaltigkeit

Umweltmanagement

Transparency as a Basis for  Energy Efficiency

The ComoNeoPredict process monitoring system is a proven option for ensuring the required quality in the injection molding production of medical devices.

In the medical technology industry, a high and validated product quality is inevitable.

Medizintechnik

When Validated Quality Is Not a Competitive Advantage

The algorithms for identifying faults and optimization possibilities stored in assistance systems of injection molding machines are continually being expanded.

Intelligent assistance systems in the injection molding machine control help the machine operator to perform the work more efficiently.

Steuerungen (Hardware und Software)

Intelligent Assistance Relieves the Strain on Production Staff

New process technologies, new machines – a selection of what will be on show at Fakuma 2023.

Making its debut at Fakuma 2023 is the next representative of the hybrid Hidrive series with new machine technology: an Allrounder 520 H in the “Premium” performance variant.

Solutions for Injection Molders

Arburg is working on the vision that, with the help of AI, every injection molding machine in the future will not only know the processes, but also the products it produces.

The problem with machine learning in injection molding: What has been learned at great expense only applies to that one, very specific process. In other words, the rules or algorithms that have been established cannot simply be transferred to other processes.

Industrie 4.0 für die Qualitätssicherung

Steuern, Regeln

Spritzgießsimulation

Simulation

Digitaler Zwilling

AI Models for Injection Molding Simulation

Whether it is the cycle time, energy consumption or process stability: the levers for greater efficiency and quality in the injection molding process are many and varied. With the new performance.boost Engel offer its customers an expertise as a service for process analysis and optimization.

With its expert knowledge, the company identifies process optimization potential and provides user support during their implementation. The results include shorter cycle times, superior part quality, greater process stability, lower energy consumption or a longer machine service life

Kunststoffverarbeitung

Dienstleistungen

Lohnfertigung

Instandhaltungssoftware

Optimize Processes Efficiently with Engel performance.boost

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

Werkzeug- und Formenbau

Werkzeug-, Formen- und Modellbau

Sensoren verschiedener Messverfahren

Fertigungsautomation

Sensorik / Aktorik

Fernwartung / Ferndiagnose

Machine Learning

Datenanalyse

Dienstleistungsqualität

Qualitätsmanagement

Instandhaltungsmanagement (TPM)

Vorbeugende Instandhaltung für die Qualitätssicherung

Werkzeugbau

Machine Learning für die Qualitätssicherung

Symbiosis of Toolmaking and  Serial Production

HiQ Flow is Wittmann Battenfeld’s answer to the challenge of fluctuating shot weights in injection-molded parts. The assistant system modifies the process parameters in the course of the same shot to counteract viscosity fluctuations caused by batch fluctuations in the material or by the use of regrind.

The HiQ Flow software corrects viscosity deviations during the injection and holding pressure phases within the same shot, based on the measurement values taken from the injection molding machine

Dynamic Adjustment of Switchover Pressure and Holding Pressure to Achieve a Constant Part Weight

No More Weight Problems

Part 2 of the series on the Plastics Innovation Center 4.0 (PIC 4.0) at RWTH Aachen describes the procedure by which industrial use cases of a Smart Factory are identified and converted into real testbeds within the PIC 4.0.

The PIC 4.0 extends the infrastructure of the Institute for Plastics Processing in Industry and Craft at RWTH Aachen University

PIC 4.0 Elaborates Holistic Solutions for Industrial Demands

Use Cases of Digitized Plastics Processing

On the Way to the Smart Injection Molding Factory

Part 2 of the Series: Integrated Data Acquisition for the Injection Molding Production

Everyone is talking about digitalization and Industry 4.0. In practice, however, implementation is often difficult. The data-driven operation of an injection molding production is often still a dream. Only if the exact actual condition of the machines and peripheral equipment is known, work on optimizing the processes can be done. The Eastern Switzerland University of Applied Sciences describes the challenges that have to be overcome and shows possible solutions based on a self-operated manufacturing cell.

There are two main challenges in implementing Industry 4.0 today [1].

On the one hand, there is often a lack of awareness in practice, both for possible applications and for the necessity of a concrete step-by-step implementation. We are talking about the actual target orientation or also use case definition for the smart factory. This concretization must be oriented to the following questions:

<ul><li>How can I increase my value creation by using data?</li><li>How can I use my data? What is the goal?</li><li>What data do I need to implement a specific use case?</li></ul>

The awareness for possible applications can be created by the use case framework presented in <a ext="tango:{f7174548-8ad9-4017-b06b-55b8e552a559}">the last article of this series (Kunststoffe international 7/21)</a>. This framework was systematized and developed on the basis of realized use cases in practice [2].

On the other hand, learning from data requires a complete database. Some questions arise here as well:

<ul><li>Which signals do I need? Which signals are available at all?</li><li>What quality of data do I need? Is the data available in this required quality?</li><li>How do I get the data out of my machine?</li><li>How do I synchronize data from different machines and devices?</li></ul>

The database is often a major hurdle, as the data is simply not available or not in sufficient quality. In the field of plastics processing, for example, there are no suitable, industry-wide standardized specifications and protocols that can be integrated with a variety of different data sources and database systems without any problems. This lack of standardization has resulted in each machine providing data differently today. Fortunately, many standards and specifications are currently in development (e. g. OPC UA), so interoperability will improve in the future.

Investigations showed that a step-by-step approach to implementing Industry 4.0 in plastics processing is target-oriented. We start with the definition of the use case. Based on this, an initial model for prediction can be developed with a focus on this use case. The validated model can then be integrated into the IT landscape, which is then rolled out in the factory or the entire production network. This is also reflected in the developed model for the implementation of Industry 4.0 in the factory (Fig. 1).

Many expert organizations are currently also dealing with this topic and specifically with the standardization of data. For example, there are also recommendations from the VDI group on which signals should be recorded in the field of injection molding [3].

Newer machines offer increasingly better data availability, i. e. they also enable more and more high-frequency recording of the individual signals and their storage as time series curves. This enables in-depth process analyses, which are essential depending on the use case. For the cyclic export of process parameters, the Euromap 63 and Euromap 77 (OPC UA) interfaces also play an important role here.

At the Institute of Materials Technology and Plastics Processing (IWK), it was possible to set up a data acquisition system to which five different injection molding machines from various manufacturers and various peripheral devices have now been integrated. The recorded data can be visualized and evaluated directly.

A number of challenges had to be overcome in order to set up this type of data acquisition for machine learning. It became clear that device-specific solutions often had to be implemented so that the data could be exported and recorded in the desired quality. This is a hurdle for smaller manufacturing companies in particular, as such interdisciplinary know-how is often not available.

Another difficulty is the synchronization of data from different machines and devices (e. g. injection molding machine, temperature control units, ambient conditions). Each device usually works with its own time stamp. This is a common problem, especially when working with time series of different devices. This can be avoided by setting up a live system in which all data is recorded synchronously. The time stamp is assigned by the data acquisition system. However, this requires that all machines and devices provide the data live. This means that curve data, which for example is made available via the OPC UA interface at the end of the cycle as time series histories, is not suitable for this purpose. A direct query of strongly time dependent signals (e. g. injection pressure or screw position) via OPC UA in high frequency is not suitable due to the limited publishing interval of the interface (usually max. 200 to 500 ms). However, it is possible to query pre-calculated parameters (such as maximum or average values) at the end of each cycle, and these data can also be combined with curve data. Nevertheless, aggregation already results in a loss of information. Depending on what is to be learned from the data, this can of course be critical. Older machines, which do not support such interfaces and do not store raw data at all due to limited storage capacities, present an additional difficulty.

In addition to synchronization, the allocation of data from different pre or post-processes is also an issue. On the one hand, data acquisition differs between continuous processes, e. g. material drying, in which continuous time series are recorded, and discontinuous processes such as injection molding and, for example, welding as a follow-up process, in which the data are recorded for each cycle and at a defined sampling rate. On the other hand, the data from the pre-process steps must then also be able to be clearly assigned to the later data of the part. For injection molding, this means which material batch was processed and how long was the material used, to manufacture the molded part, pre-dried? This is not a simple question, which is why it is currently still being worked on. For follow-up processes, this is much easier, since the part and the associated data already exist and only need to be expanded.

Fully Automated and Self-Learning Manufacturing Cell

One implementation of this connected factory is a manufacturing cell for the production of a floorball (Title figure and Fig. 2). The ball halves are manufactured on an injection molding machine, laser marked, completely measured in three dimensions and then stored in an interim storage system sorted by color. A collaborative robot is used for automated handling.

For customer orders, this robot takes the ball halves in the desired color from the storage system and transfers them to the welding machine, where the halves are welded into a ball fully automatically. This is a fully connected and automated production cell, the process data of all production steps as well as the quality characteristics are stored in the cloud and can be clearly assigned to each ball. On the one hand, this ensures complete traceability and, on the other, the entire production process can be optimized by using artificial intelligence and advancing towards zero-defect production. This manufacturing cell serves as a training object for students of the OST –Eastern Switzerland University of Applied Sciences and shows companies the possibilities of digitalization.

Use of Data Acquisition for  Research Projects

The data acquisition system also serves as the basis for the use of artificial intelligence in a wide range of projects in the field of injection molding. A central topic is the early detection of process anomalies on the basis of process data. When an anomaly occurs, the machine operator should also be given a recommendation for a suitable countermeasure. This topic is being investigated in a three-year publicly funded research project with five industrial partners.

The process anomalies can be reliably detected and first appropriate countermeasures can be suggested. With the use of a support vector machine and an autoencoder an anomaly score (Fig. 3, top left) can be calculated based on various features. This indicates how stable the current process is running. When this score increases, a recommendation for action is suggested to the operator (Fig. 3, bottom right), which can be used to correct the process.

Other use cases include the prediction of the quality characteristics of the manufactured parts on the basis of process data and predictive maintenance or detection of wear on tool or machine components.

[1] Hopmann, C. & Schmitz, M. (2021). Plastics industry 4.0: Potentials and applications in plastics technology. Hanser Publishers; Hanser Publications.

[2] Budde, Lukas, Hänggi, Roman and Friedli, Thomas. „Digitalisierung à la carte: Individuelle Auswahl von Use Cases nach strategischen Prioritäten“ Zeitschrift für wirtschaftlichen Fabrikbetrieb, vol. 113, no. 12, 2018, pp. 850–854. <a href="https://doi.org/10.3139/104.112016" target="_blank">https://doi.org/10.3139/104.112016</a>

[3] VDI-Gesellschaft Materials Engineering (2019). VDI-Statusreport Industrie 4.0 in Spritzgiessunternehmen.

OST Ostschweizer Fachhochschule Inst. f. Werkstofftechnik u. Kunststoffverarbeitung (IWK)

https://www.iwk.hsr.ch

Ausgabenartikel

Fully automated manufacturing cell for the production of a floorball at IWK’s technical laboratory in Rapperswil, Switzerland

Fig. 1. Model for the implementation of machine learning in the factory

Fig. 2. Production flow of fully automated manufacturing cell

Fig. 3. GUI (Graphical User Interface) for anomaly detection and countermeasure proposal 

Ostschweizer FH - Hauptartikel

Curdin Wick, M.Sc., is head of the injection molding department at the Institute of Materials Technology and Plastics Processing (IWK) at Eastern Switzerland University of Applied Sciences (OST).

Prof. Dr.-Ing. Frank Ehrig heads the Institute for Materials Technology and Plastics Processing (IWK) at OST.

Prof. Daniel Schwendemann is head of the compounding and extrusion department at the Institute of Materials Engineering and Plastics Processing (IWK) at OST.

Prof. Dr. Roman Hänggi is a partner at the Institute for Product Design, Development and Construction (IPEK) and Professor for Production Management at OST.

Adrian Rüedy, M.Sc., is project manager at the Institute for Product Design, Development and Construction (IPEK) at OST.

The last article in this series takes a look at the challenges involved in implementing specific use cases and learning from data with the help of artificial intelligence in the field of compounding production technology.