Digitalisation in Plastics-Processing SMEs: Capabilities and Investment Priorities

Digital technologies can help plastics processors understand their processes, reduce technical uncertainty and retain information now scattered across records or held by a few experienced people. For an SME, the outcome depends on selecting applications suited to its machines, expertise and production challenges.

Practical starting points include long start-ups after mould changes, cycle-time differences between shifts, unallocated energy consumption, material batches with different processing behaviour or difficulties reconstructing the conditions under which a rejected part was made.

An industry shaped by interconnected engineering decisions

In plastics processing, a part results from the interaction of geometry, material, tooling, cooling, process conditions and operation. Changing one factor may simultaneously affect quality, productivity, energy consumption and stability. Digitalisation becomes especially valuable when it helps relate these effects.

The relevant information begins before production. Design revisions, material grades and mould versions can matter as much as pressure, temperature or cycle-time records. The entire value chain is worth examining: design, sourcing, industrialisation, processing, quality, logistics and, where relevant, take-back and recycling.

Five practical opportunities for an SME

1. Collect data from existing machines

Recording cycles, machine states, downtime, energy and selected critical variables provides an initial view of production losses. Signal selection should follow the engineering question: studying microstoppages requires sufficiently detailed events; comparing specific energy consumption also requires production quantity, product reference, material and measurement period.

Mixed machine fleets can combine available interfaces, discrete signals and additional sensors. Integration requires checks of data coverage, measurement accuracy, electrical safety and cybersecurity. Explore the KERN IoP monitoring platform y industrial data architecture.

2. Retain validated process conditions

A production recipe becomes valuable when its context is documented: machine, mould or die, material grade and batch, auxiliary equipment, parameters, relevant ambient conditions and quality outcome. Retaining process-window limits makes it possible to compare a new start-up against a trustworthy engineering reference.

This discipline supports repeatability across shifts, tooling transfers and personnel training. See how to document injection-moulding conditions.

3. Connect production, quality and energy

Power or temperature measurements alone offer only a partial picture. Linking data with orders, batches, product references and quality results provides a stronger basis for investigating process changes. For energy analysis, distinguishing the injection-moulding machine from cooling, drying, conveying and other auxiliaries is particularly important.

Explore KERN IoP | ENERGY: Cell and the energy measurement guide.

4. Use simulation where it reduces uncertainty

Thermal, rheological, mechanical or discrete-event models can be used to investigate alternatives before consuming material or machine time. Mould simulation may inform cooling changes; a capacity model may help evaluate sequences, product changeovers and shared resources. Value depends on boundary conditions, input data and validation against real operation.

For suitable applications, models can remain linked to operating data and support estimation, diagnostics and control. Explore digital twins in manufacturing e KERN IoP industrial engineering.

5. Include operators and technicians in improvement activities

Plant specialists recognise symptoms, sequences and operating conditions that may not yet be captured in databases. Visual instructions, intervention logs and process references reviewed with staff help make this experience accessible to new colleagues. Technology should deliver understandable information at the time and place of the decision.

How to prioritise the first project

Before purchasing sensors or software, define a testable hypothesis. For example: ‘The delay in stabilisation after a mould change is related to the initial thermal condition and start-up procedure.’ Then agree which variable to observe, what reference condition to use, who will act and how results will be assessed.

A practical sequence is: priority loss → baseline → adequate instrumentation → contextualised data → intervention → verification → standardisation. Comparisons must retain relevant production conditions, because different machines, moulds, materials and orders may account for part of the observed variability.

Total investment includes acquisition, installation, integration engineering, training, maintenance, calibration, licences and support. A pilot can assess both technical feasibility and the cost of sustaining the solution.

What the scientific evidence tells us

In a review of 229 real-world cases of digital technology adoption in manufacturing, Maretto, Faccio and Battini (2023) identified 94 with some performance evaluation and 30 including elements of economic assessment. These figures describe the reviewed studies. They highlight the importance of assessing outcomes but cannot, on their own, establish the return expected in a particular plant.

A study by López Almendros and Aguilar Pérez (2025) describes a modular architecture implemented at four plastics-processing SMEs through different interventions. The reported outcomes relate to those specific applications and conditions. The wider lesson is the value of incremental adaptation to defined needs while retaining usable production infrastructure.

KERN IoP’s research on the sector

PM Tec Engineering, through its Industry 4.0 division, KERN IoP, prepared the study State of the art of digitalisation in plastics-processing SMEs (August 2026). It brings together scientific literature, technical standards and regional evidence to identify opportunities across the circular plastics value chain.

The review identifies a research need in Colombia: assessing engineering, production, materials, quality, people and circularity capabilities jointly in plastics-processing companies. It provides a basis for developing a future methodology; its findings are a literature synthesis, not the results of a nationwide sector survey.

Further reading: industrial digitalisation in Colombia and Latin America, what Industry 4.0 means y technical resources.

References

• López Almendros, A., & Aguilar Pérez, T. (2025). Real-world validation of a modular digital architecture in plastic manufacturing SMEs. The International Journal of Advanced Manufacturing Technology, 141, 1905–1916. https://doi.org/10.1007/s00170-025-16792-1
• Maretto, L., Faccio, M., & Battini, D. (2023). The adoption of digital technologies in the manufacturing world and their evaluation: A systematic review of real-life case studies and future research agenda. Journal of Manufacturing Systems, 68, 576–600. https://doi.org/10.1016/j.jmsy.2023.05.009
• PM Tec Servicios de Ingeniería SAS, KERN IoP. (2026). State of the art of digitalisation in plastics-processing SMEs. Critical review of scientific literature, technical standards and institutional sources.