Learn more about the use case:
Predictive Maintenance, Quality assurance
Predictive maintenance of printing presses in newspaper production
What drove the decision to develop an AI-based use case?
The print shop is in operation between 11 pm and 3 am. Our client therefore has just four hours to print millions of newspapers for the following day before they are distributed and delivered to customers in the morning hours. Given the time pressure, press breakdowns are fatal. Since repairs would be too time-consuming, the only solution in the event of a drive failure is to replace it, which nevertheless takes at least ten to 15 minutes and involves enormous costs.
In order to be able to quickly replace the relevant components in the event of a failure, our client had a very high stock of spare parts, which resulted in correspondingly high warehousing costs.
What were your expectations or requirements for the AI application?
The client's goal was to avoid unforeseen machine downtime and optimize maintenance planning.
Which partner did you rely on with which technology for the development?
The implementation of the project including data cleansing, anomaly detection, data labeling, data harmonization, the creation of predictive models and the visualization in dashboards for the client was done by our data science department using our custom developed modules and algorithms.
The use of AI solutions must also be accompanied by a change in competences. How have you dealt with this challenge in respect of your employees?
In addition to accurate and reliable classifications and predictions by our AI, the usability and comprehensibility of the outputs is of course of central importance. To ensure that our client can also use our solution effectively, we held two workshops with the decision-makers and employees involved. One workshop at the beginning of the project with the goal of concretely defining the use case and ensuring a clear understanding among all parties involved. A second workshop was held after the implementation of our solution to ensure that the users of our solution not only understand it, but can also use it to its full extent.
In what timeframe did they implement the AI solution in your company?
The implementation of the project took about four weeks. When this project was implemented, sufficient machine data was already available to train the model.
A conclusion to your AI solution:
The implementation of our AI solution for the client secured the company's brand name on one hand. Since a late delivery of newspapers would mean enormous damage to the company's image, the client was under enormous pressure with regard to the production volume to be delivered in the set time. By predicting potential machine failures, maintenance can be optimally planned and downtime during operating hours can be avoided. In the event of a predicted failure, the corresponding component can be replaced in advance. As a result, our client is able to distribute the newspapers reliably and on time, which in turn keeps the end customers - the readers of the newspapers - satisfied.
In addition, the more efficient inventory planning results in a considerable cost reduction.
For the users of our AI solution, there are also the following advantages:
- the production department can use our AI solution to plan maintenance in advance to avoid machine breakdowns
- the development department uses our system to verify and supplement their R&D results with regard to increasing the efficiency of the machines
- based on the more comprehensive insights into production, management can make informed business decisions.
One final piece of advice/tip to other entrepreneurs looking to apply AI:
Statistically, about 70% of all Data Science projects fail. To prevent this, we recommend working out and defining the concrete use case and business case in detail together with the partner before the actual kick-off of the project.
More info at: