- Register


Home>IIot & Smart Technology>Industry 4.0>Entering the next stage with artificial intelligence

Entering the next stage with artificial intelligence

10 August 2020

New technologies like Artificial Intelligence [AI] generate unprecedented market opportunities. This applies particularly to digitalisation in the machinery construction sector. Steve Sands, head of Product Management at Festo GB looks at how Festo is committed to supporting customers and partners into the digital age as part of this transformation process

With the acquisition of the industrial intelligence company Resolto, Festo has strengthened its capacity for entering the next stage in automation technology: the use of artificial intelligence.

We can see how fast the shift from hardware to software is taking place by looking back only to the year 2000 when the owners of the classic Nokia 3310 were so proud of their sturdy mobile phone. Nokia's turnover figures were in the billions thanks to the number of units sold, relying almost entirely on the value of the hardware itself. Only 20 years later, the hardware of Apple’s iPhone is not only a lot more expensive, but, thanks to digitalisation, it created its own boom for new business models and new markets. More than 100,000 apps are available in the Apple Store, creating a market of €9.5 billion for software, entertainment and media. And the software trend is clearly on the up.

Much more than fit & forget

For many decades Festo industrial automation products have always followed the motto 'fit and forget'. This guiding principle still strongly applies today, but nowadays the products are installed and are able to continuously generate additional added value – thanks to digitalisation.

Following the acquisition of Resolto, a leading innovator and expert in industrial intelligence, Festo is now offering solutions with artificial intelligence for real-time applications. Data is the key, making it possible to save energy, shorten cycle times, and reduce machine failures and production errors.

Data is the key, making it possible to save energy, shorten cycle times, and reduce machine failures

The SCRAITEC software solution from Resolto, for example, learns the healthy condition of a system and detects every anomaly with the real-time analysis of the system's existing sensor data. SCRAITEC supplies early and precise prognoses, makes diagnoses and can supply recommendations for action. AI algorithms can be integrated both in the cloud, on Edge and directly in Festo components and it is clear to see the enormous impact this can have, on added values for customers.

With the Festo IoT Gateway [CPX-IOT] local control interface hardware, customers can have their machine and plants directly monitored at field level. Within the SCRAITEC package, field level support is provided with the ScraiField software component. This runs within the smaller controller constantly in close proximity to the machine.  Analysing the data is a pretrained algorithm model with minimal hardware requirements, reliably monitoring and locally interpreting data streams. Local analysis means even large amounts of data can be analysed in real-time. Minimising data transfers to the cloud saves time and money.  Separating the time sensitive machine control and data intelligence ensures uninterrupted performance. 

The key AI component of SCRAITEC is the cloud based ScraiBrain. This module monitors in turn the local ScraField modules, optimising the performance of the algorithm. For example, the sensitivity of an AI anomaly based detection system can become damped due to historical data. Creating disturbances, equivalent to engineers inducing a flutter into a mechanical system, increases the dynamic response and sensitivity of the AI system.

The IoT gateway connects to the cloud, where outputs can be channelled to the Festo dashboards or triggering as necessary, actions via smart maintenance tools such as Smartenance providing a massive increase in the effectiveness of field based maintenance teams. The ScraiBrain is embedded in the cloud with access to a host of preconfigured application models.

Human-in-the-loop principle

The platform continuously learns from the machine or system’s operation, integrating the knowledge of the engineers and the customer’s technical experts, called the ‘human-in-the-loop’ principle. The machine learning and AI product, interprets information predictively to actively optimise parameters or to send concrete instructions for action to “its” people (e.g. via smartphone).

The machine learning and AI product, interprets information predictively to actively optimise parameters

New business models

Combining Scraitec with plants and machines to transform them into digital tools is opening new business models for machine and plant manufacturers. New maintenance service concepts offer substantial added value through the automated, early coordination of in-house maintenance teams.

Scraitec helps end customers to optimise the utilisation of their plants. The costs for maintenance can be substantially reduced, since maintenance schedules are adapted by predicting events and making recommendations for action for known fault patterns.

AI application examples

Household appliance manufacturer Miele noticed fluctuating product quality in one of its production processes, but was unable to account for the causes. Operating complex production lines, where products are sequentially manufactured, it is not enough to look at individual problem stations in isolation.

Production managers at Miele applied the Scraitec system for automatically detecting anomalies in complex manufacturing flows. Deep Learning was the right approach, what was needed was an integrated database that brought together different measurement systems. Additional measuring points also had to be configured for this. The Scraitec platform modelled the production lines as an integrated system, and by doing so, increased throughput by 1.5%.

An automobile manufacturer application is another example. Pneumatic clamps are a relatively low-cost component deployed in their thousands within body-in-white plants where car bodies are assembled. However, unforeseen production stoppages can cost several hundred thousand pounds at a time. An early warning system for wear and slowing down of cycle times was therefore an ideal AI application. A learning system was deployed for the predictive maintenance of all types of clamping systems. The solution monitored the existing sensors, inputs and outputs and with Scraitec real-time data analytics can predict potential failures in good time, enabling planned maintenance without critical line stoppages.

The power of AI

Artificial Intelligence is an extremely powerful component within the digitalisation tool kit alongside many new digital technologies and products.  The Industry 4.0 strategy provides a unifying set of standards that will make it easier to combine these elements creating an exciting ‘whole’ considerably greater than the ‘sum of the parts’.  Artificial Intelligence is the jewel in the crown providing actionable insights from the Big Data that is becoming so widespread and accessible.