Access Official Technical PDF

Share Summary:LinkedInEmail

Industrial automation innovation is not limited to new robots or production machinery. A review of European SME Instrument Phase 1 project entries from the November 2018 and February 2019 cut-off dates shows a broader range of ideas: machine vision for inspection, sensors for equipment monitoring, software for industrial data, and tools for more responsive process control. These entries describe proposed feasibility-stage projects, rather than evidence of completed deployments or verified performance.

For automation engineers, integrators, and plant leaders, the proposals offer a useful snapshot of the problems smaller technology companies were trying to address. Their common thread is the effort to make operational information more accessible and useful, whether it comes from a production line, a machine, or a wider industrial environment.

Industrial automation innovation extends beyond robotics

Robotics is an important part of automation, but the project list points to several complementary layers. A system may need to capture reliable data, interpret it, and present a useful signal to an operator or control process. Some proposals addressed sensing and inspection; others focused on analytics, monitoring, or process-specific control.

That distinction matters when evaluating new automation technologies. A sensing device may provide measurements, while a software platform may help organize or interpret data. Neither necessarily replaces a control system or makes decisions autonomously. The value depends on the application, the available data, and how the technology connects to existing operations.

Machine vision brings inspection into the digital workflow

Several entries focused on computer vision and image-based analysis. Austria’s MoonVision 2.0 proposal described the use of AI computer vision for visual inspection in industry. Spain’s UniMind was presented as a platform applying artificial intelligence and collaborative learning to the automation of machine-vision-based manufacturing processes.

These concepts address a familiar industrial challenge: turning visual information into a repeatable digital input. In a production context, that may support inspection workflows or help automate parts of an existing machine-vision process. However, the project descriptions do not specify supported defect types, line speeds, accuracy levels, or integration methods. Those details would need to be established before assessing fit for a particular plant.

For engineering teams considering machine vision, practical evaluation should include the conditions under which images are captured, the consistency of lighting and product presentation, and how inspection results will be handled. The technology is only one component of a dependable inspection process.

Monitoring proposals target equipment and industrial environments

Equipment monitoring and predictive maintenance were also represented. Israel’s FeelIT Technologies proposed a nanotechnology sensor-based platform for predictive maintenance of industrial equipment. Norway’s Foresight was described as an autonomous machine monitoring and prognostics system for the oil and gas and maritime sectors. Czechia’s AxleRing focused on a self-charging remote monitoring device for rail freight wagons.

These proposals illustrate different monitoring contexts: industrial equipment, machines in sector-specific environments, and mobile rail assets. Across them, the underlying automation question is similar: what information can be collected remotely, and how can it help users understand asset condition or operation?

Monitoring should not be confused with maintenance action. A monitoring system can provide information, but the project descriptions do not establish how alerts are generated, how they connect to maintenance planning, or whether they trigger any automatic response. Plant teams assessing a system should clarify data availability, communications requirements, alert handling, and the responsibilities of operators and maintenance staff.

Process control and industrial data analytics

Some proposals focused on process-specific control and analysis. Denmark’s Specshell ENZEYE project aimed to bring automated, real-time process control into the starch-based industry. Germany’s DatenBerg entry described a feasibility study for implementing data-analysis software at a manufacturing site in the rubber-processing industry. France’s HIBOO was presented as a data platform for visualizing and predicting the industrial world.

Together, these examples show that digitalization can operate at different levels. A process-control project is tied to a particular industrial operation, while a data platform or analytics tool may address information from a broader environment. The project descriptions do not establish how these systems exchange data with existing automation infrastructure, so interoperability and deployment scope should be treated as open questions.

For decision-makers, a useful first step is to define the operational problem precisely. Is the objective to improve visibility, detect changes, support an operator, or automate a process step? A clear use case makes it easier to determine what data is required and how a proposed tool should fit alongside existing sensors, control systems, and maintenance workflows.

What engineers and plant leaders can take from the proposals

The entries suggest several practical considerations for assessing emerging automation technologies:

  • Start with the use case. Identify the asset, process, or inspection task the technology is intended to support.
  • Check the data pathway. Understand what is measured or captured, how it is transmitted, and how users access the resulting information.
  • Define the operational response. Establish who reviews alerts or analysis and what actions are expected to follow.
  • Assess integration requirements. Confirm how a proposed solution would coexist with current equipment and software; the project summaries do not provide detailed interface specifications.
  • Separate proposal aims from validated results. These entries describe project concepts and objectives, not demonstrated plant outcomes.

These questions help keep evaluations grounded in operating requirements rather than broad claims about artificial intelligence, connectivity, or automation.

Conclusion: connect digital tools to operational needs

The 2018 and 2019 SME Instrument Phase 1 entries capture a varied set of industrial automation innovation priorities: machine vision, remote monitoring, predictive maintenance, process control, and industrial data analysis. They show how automation concepts can begin with a focused problem—inspecting products, monitoring an asset, or making process information easier to use.

For industrial organizations, the practical implication is to evaluate each technology in context. A promising concept must be matched to a defined task, suitable data, integration needs, and a clear operational response. That disciplined approach helps engineers and decision-makers distinguish an interesting proposal from a solution that is ready for their facility.

Access Official Technical PDF

About The Author