“AI is a core topic, but usually not the solution.”
At Zukunftsnavigator #9, artificial intelligence, or AI for short, took centre stage. Viewers of the online event experienced two hours densely packed with insights into challenges and opportunities for applications of AI in the production environment and beyond.
From cloud connection to predictive maintenance algorithms
The keynote speech “AI for machine builders. From Cloud Connection to Predictive Maintenance Algorithm” was given jointly by Philipp Mayer, Managing Director of codestryke, and Felix Kraft, CFO and co-founder of ai-omatic. Codestryke is a young company specialising in the Internet of Things (IoT) for mechanical engineering, ai-omatic harnesses data via artificial intelligence to develop productive predictive maintenance applications for customers.
Predictive maintenance is about neither servicing machines too early and unnecessarily replacing parts, nor waiting until damage occurs, which often results in longer downtimes and thus higher costs. Predictive maintenance aims to use available data to predict when parts need to be replaced to ensure that machines are operating optimally and as efficiently as possible. Predictive maintenance requires data that is collected via IoT networks.
Scaling IoT
Since 2017, codestryke’s focus in its more than 50 projects has been to develop IoT connections in a scalable way so that all machines can be connected. In Mayer’s experience, connecting individual machines as an example case is not useful in practice.
At the beginning of an IoT project, Codestryke takes stock. What data is already available? What other data needs to be retrieved and how often? And how can it be accessed using hardware or sensors? The proof of concept evaluates the concept fit; after feedback from the customer, it is further developed and rolled out to all machines. Old machines are retrofitted with IoT capabilities, new ones are integrated. Once the connection is complete, it is optimised.
Ensuring long-term success
In order to successfully implement an IoT project, Mayer says, it is important to work towards collecting the right data from the very beginning in order to contribute to the efficiency of the operation. The technical feasibility must be considered, because a company that is to be networked rarely consists only of new machines that can be easily integrated. Last but not least, the choice of the AI application is relevant and also determines the success of a project.
Overcoming challenges
Mayer has experienced a number of challenges, specifically in the complexity of projects. The better complexity can be reduced, the sooner his company can ensure that data remains a source of information and does not become a problem. Implementing IoT is a huge change, he says, which requires appropriate support from the company—staff must be available, and responsibilities must be clear so that the project can move forward. Ideally, all machines that are to be connected should be managed centrally, as otherwise difficulties could arise in coordination. To keep the project successful in the long term, security and flexibility should be ensured by allowing over-the-air (OTA) updates from anywhere in the world.
As a solution to these challenges, codestryke has developed the software Vergelink. Vergelink compiles data in a third-party system, runs hardware-independently and can be used in many areas. The software automatically recognises machines in the system and data points are easily selectable. Mayer gave insight into an application example in which several hundred machines already in use at a customer’s were subsequently connected to the cloud in record time with the help of the software—without any downtime of the machines. Since the connection could be made remotely, travel costs in the six-figure range were avoided.
Data secured—and now?
Once the data flow is secured, companies like ai-omatic come into play. The software company processes the data using an algorithm, which according to Kraft is the heart of the company and independent of the hardware, as he emphasised.
The ai-omatic approach combines statistical evaluations with a neural network. A digital twin of the system to be monitored is created, from which the algorithm learns what the normal state looks like. New data is compared with the normal state. An alarm is triggered via the system if data deviates from the target values. The special feature of the ai-omatic solution is that no past data is necessary. The system does not learn from past mistakes but is directed towards the future.
Condition monitoring functions via a simple visualisation. It is clearly recognisable in which area of the sensor system the deviation occurs. The anomaly score, which is being developed for the digital twin, is able to detect deviations much earlier than conventional methods and visualises them for users. Using an example that juxtaposed both methods, Kraft showed that the AI solution could detect bearing damage two weeks in advance.
Ai-omatic offers its software under its own logo or as proprietary solutions. This is a big advantage for manufacturers, because they usually do not have the capacity to develop their own solutions—but if they can also offer predictive maintenance, this is often a competitive advantage.
Ten start-ups that can help you with AI
Dr Dominik Lausch, CEO, presented the Fraunhofer spin-off DENKweit. The vision of DENKweit: to make image-based artificial intelligence (vision-AI) easily accessible for customers from industry. This involves visual error detection via a Vision AI Hub. This can be used to classify objects with pixel precision, find objects in the image and detect anomalies, to name just a few examples. Users mark what they want to see, the rest runs in the background. This saves time and money.
Only a few images are needed to train the system, the software calculates fluctuations. DENKweit is characterised by a different approach to image-based artificial intelligence, Lausch explained. The underlying mathematics is adapted to each application and can be used widely – whether it is for tasks in production or object recognition in real life. How the AI works depends on the application. The customers provide the challenge, DENKweit the technological solution.
InnoSEP has taken up the cause of democratising artificial intelligence. According to CEO Kerim Galal, AI is often not used because companies lack the experience and data scientists to implement applications. His company overcomes this hurdle by offering an open-source platform that does not require code and can therefore be used by engineers themselves.
Developed from 2019, the platform has been in use since 2021. Specialising in mechanical engineering and IoT, the platform can be used to create custom applications for a variety of scenarios in industry, whether in demand forecasting or virtual product testing. The AI solution enjoys a high level of acceptance among employees and is also suitable for retaining skilled workers, as they can work with the AI themselves and master challenges they face.
Synthavo offers its customers the possibility to visually search for spare parts for mechanical engineering via automated parts recognition. Sebastian Stöcklmeier, co-founder of the company, impressively described what often happens when a machine is at a standstill. Technicians rummage through mountains of paper—the machine documentation—, identify the defective component and contact the machine manufacturer’s customer service. Then it takes time, the machine is standing still, and the costs increase. With the so-called Visual Self Service from Synthavo, parts can be scanned with the smartphone and availability is immediately displayed. The search for the spare part is no longer necessary and machine downtimes decrease.
Synthavo uses existing data for object recognition: The AI is trained via CAD data from the manufacturers, so a new component can be added quickly. Thanks to the AI, not only can spare parts orders be processed, but it also provides support in incoming goods, outgoing goods or in production—everywhere where automated parts recognition helps logistics.
Dr Günther Hoffmann, founder of LexaTexer, sees AI as a core issue, but says it is rarely the solution. In the laboratory environment, AI works very well, but in industrial operations there are often challenges. LexaTexer’s answer is an AI platform that solves standard questions about security, scalability, data connection and integration of the solution into existing processes. As an enterprise AI solution, it is either installed at the customer’s site or remotely.
In his experience, AI can be used profitably along the entire value chain, from the order book to the follow-up sale. Usually, the first order for LexaTexer comes from production in order to increase the overall equipment effectiveness (OEE). Predictive planning in particular offers opportunities for AI. Later, demand and sales planning would be added.
Country Manager Linus Grabher from KREATIZE reported on the production of spare parts on demand. The challenge behind this is that the procurement of customised, complex components is often just as time-consuming and expensive as in-house production.
Instead of buying halls in which parts are manufactured, KREATIZE offers to purchase components as a service via cloud manufacturing, i.e. they are manufactured wherever machine capacity is available in the world. Cloud manufacturing connects the physical and the digital world, ensures that components are priced automatically and selects the suppliers who currently have capacity.Companies often differentiate between A, B and C parts when it comes to infrequently needed parts. The procurement of B and C parts, which have a lower value than A parts, is often time-consuming and costly. KREATIZE enables companies to procure these parts without investing in a new supply chain and machinery. Since the company can procure a wide variety of parts as a single point of contact, time-consuming enquiry processes are eliminated. Despite greater influence on the parts themselves, the parts would be cheaper to purchase.
In his presentation of ai-omatic, Felix Kraft went beyond his keynote speech to provide background information on the company, which was founded in January 2020 and whose initiators come from the Airbus environment. Their original aim was to predict machine failures in good time, as it quickly became expensive at Airbus when spare parts were missing. Today, the company has 16 employees with its software-as-a-service model.
The founders of Trilleco, a provider of a programming-free IoT platform, have identified green transformation as a growth potential for digitalisation. Co-founder Miriam Janke presented the solution, which visualises data and works as an extended workbench for the IT team, enabling fast workflows and saving costs.
With Trilleco’s platform, a lot of data could be made usable that had previously been wasted potential, for example in energy management, for the creation of a digital twin or even predictive maintenance. It can be used in small and medium-sized enterprises as well as in large corporations.
According to Dr Jan-Marc Lischka, co-CEO of 5thindustry, anyone who really wants to make their production digital must overcome the last mile to the employees in production, because the lack of digitalisation and structured communication leads to reduced productivity. Digitalisation can only succeed if people are involved, and resistance is reduced—and if the solution is simple.
The fifth industry puts people at the centre. Therefore, employees have everything they need for their work at their fingertips digitally via smartphone apps. 5thindustry offers solutions that integrate into existing IT landscapes, for example from Microsoft or AWS, to reduce IT costs, increase productivity and lower quality costs. 5thindustry’s claim is to make AI usable off the shelf, so to speak.
Christoph Gielisch, co-founder of DETAGTO showed how individual parts can be traced in a forgery-proof way without marking them or applying stickers. Instead of serial numbers or barcodes, DETAGTO’s IRIS technology uses structures on components that are there anyway. IRIS stands for identification based on random and individual surface patterns. DETAGTO supplies the software and, if desired, also the camera.
The software offers security in case of product returns because copied products can be recognised as counterfeits and claims against the manufacturing company can be excluded. In addition, the software there is no need for information that has been applied or lasered onto the product, which on the one hand is not counterfeit-proof and on the other hand influences the product design.
Support project You fit!
At the end of the event, Lisa Rothfuß, Head of Network, Communication & Events at bwcon, presented the You fit! funding project, an online learning offer for SMEs that aims to provide personalised learning offers. It responds to the challenge that previous professions are disappearing or that different skills are required. You fit! is dedicated to artificial intelligence, software development, blockchain and quantum computing as well as teaching the basics for developing new business approaches and digital innovations. The platform is purely a self-learning programme through which interested parties can be assessed and develop individual learning content. BadenCampus is also involved in the funding programme.
About Zukunftsnavigator
Zukunftsnavigator is a series of events organised by BadenCampus, DigiHub Südbaden and EIT Manufacturing.