Diagnosing for printer maintenance with AI
When exactly does a building or item of equipment require maintenance? Carrying out too much preventive maintenance can be costly. But if you leave it too long, the expense of an emergency repair can be much greater. And we all know that machines have a habit of breaking down at exactly the wrong time. So predictive maintenance is high on the list of priorities of the manufacturing industry. Here, too, artificial intelligence (AI) can make all the difference.
A customer is itching to receive the printed matter he has ordered. The printers are running flat out – as are all the other machines. It is not just tough quality requirements that the graphic industry has to meet, but in many cases tight deadlines as well.
That makes it an ideal sector for introducing predictive maintenance based on artificial intelligence. And that is exactly what TNO and Canon Production Printing (formerly Océ) are currently aiming to do. Together, they are carrying out research into an AI system that stands out in terms of reliable diagnoses and prognoses for professional printers.
AI that understands printers
A lot of different data is needed to be able to estimate the condition of a machine or machine components. But much of that data is incomplete or unreliable. To be able to extract the right conclusions from this mix of data, you need AI that is entirely at home in the world of printers.
This calls for 'hybrid AI' – a combination of data-learning AI and domain knowledge. The AI system is able to modify the likelihood of causal links in the domain model on the basis of a machine’s user data. It can also work out what problems could occur and in what kind of time frame.
Still essential: human expertise
And what about people? The part they play should not be underestimated. Machine learning, then, is just one part of the story. It is precisely the combination of artificial intelligence and human expertise that make this solution so powerful. The big challenge here is to develop an AI system that is capable of accurately combining the input from people and machines alike.
Christopher BrewsterFunctie:Senior scientist
Christopher Brewster is a Senior Scientist in the Data Science group and Professor of the Application of Emerging Tecnologies in the Institute of Data Science, Maastricht University. His research has focussed on the application of Semantic Technologies, Open and Linked Data, interoperability architectures and Data Governance, mostly to the food and agriculture domains.
Daniël WormFunctie:Senior consultant
Joris SijsFunction not known
Judith DijkFunctie:senior research scientist
Judith is specialised in extracting information from camera images. She now applies the subject of her PhD thesis in Physics, which she obtained 18 years ago, to her work as a research scientist at TNO, including in a research programme on camera systems for the Dutch Ministry of Defence.
Looking for another expert?View all experts
Responsible decision-making between people and machines
Bias in facial recognition and accidents with self-driving cars. AI must be developed further. The fastest way to do this is in close cooperation with people.
Knowledge representation and reasoning
Correct and unambiguous information is needed when making a decision. That is why we use AI technology called "knowledge representation & reasoning".
Natural language processing
What is natural language processing (NLP) and how do we use it intelligently? Find out how we use this AI technique to gather information from textual data.
Robotics and autonomous agents
Robotics brings a future-proof industry a big step closer. For example, we are working on automatic path planning with AI techniques.
Fair machine learning
Fair machine learning is relevant to all kinds of discrimination and bias arising from the use of biased data. Read more!