Philips Drachten is situated in Drachten, Netherlands since 1950 and is one of the largest Philips development and production centers in Europe. More than 2000 employees work in this facility and develop Personal Health products such as electric shavers, beard trimmers, wake-up lights, and parts for electric toothbrushes (Philips).
The manufacturing of electric shavers in the production center has a large suite of highly automated processes. Injection moulding is of particular importance as it is used in manufacturing plastic components for electric shavers. Injection moulding is a competitive market. i.e., no single entrant dominates the single market. This makes it important for Philips Drachten to continuously improve injection moulding on quality, production performance, and costs. This case is based on the referenced study (Lázaro, 2022).
The plastic parts manufactured on-site at Drachten require approximately 80-90 moulding machines from multiple vendors, models, and generations. It is not feasible to develop a specialized solution for each machine in the machine park because the time investment required to build a customized solution is too high compared to potential savings. However, financial gains are significant while focusing on the fall-off rate of the entire plastic-part-making department.
If the amount of time required to enable analytic capabilities is lowered it results in predictive maintenance and process control solutions that are cloud-enabled and thus easily scalable. Another issue that has been tackled is the interaction of data-driven digital processes with the current manufacturing processes and how data-driven decisions are translated into actionable insights in production.
Shopfloor automation value for injection moulding
Philips Drachten over the years had employed data-driven solutions within the production however they never have been successful in scaling up or maintaining those data-driven solutions. These special solutions focused on unique cases and thus failed.
Thus, they started focusing on generic automated solutions and developed a failure prediction model which can be applied to multiple machines. This results in a reduction of the fall-off rate and machines’ downtime. The application of Big-Data and fact-based decision-making, coupled with seamless connectivity in the manufacturing process, results in efficient ramp-up times between different moulds. It also leads to full traceability along the process chain until the customer. To execute the Big Data-driven applications, they installed a new data collection and storage infrastructure to effectively integrate various types of data into a single common repository. The results of the data monitoring and machine learning were shared with process engineering, assembly line operators, and data scientists.
Shopfloor quality automation results
The implementation of Big Data-driven solutions has resulted in significant shopfloor performance improvements in terms of flexibility, efficiency, quality, and time to market. This was achieved by the implementation of advanced decision support dashboards which reduce decision-making time and allow anticipating unplanned events. A real-time dashboard was developed for the visualization of machine data, including pre-processing and machine-learning models deployed as services.
Figure – Shopfloor dashboards experience and advanced data processing tools.
Following are the results of the efficiency improvements:
1. 10% reduction in fall-off rate.
2. 9% reduction in downtime.
3. Increased availability of process parameters data was available from every 20 minutes to real-time information and increase the number of parameters from 10 to ~80 per machine per cycle.
4. Collected over 400k of individual shots in 5 months of injection moulding data which provides an opportunity to develop advanced models.
5. Reduction of 70% in the amount of (non) valuable and unnecessary control actions by operators.
It also resulted in:
1. Providing technicians with a more efficient tool for solving production issues and a better method for troubleshooting.
2. Taking fact-based informed decisions like avoiding acquiring new machines by using the current machine park more efficiently.
3. A better understanding of the time-related behavior of the injection moulding process.
Conclusion
The successful implementation of Big Data-driven processes and advanced analytics at Philips Drachten paves the way for Mittelstands to implement these systems. The technologies developed using Big Data-driven processes can further be developed into new autonomous modes of manufacturing. This would further drive productivity, increase quality, and cost savings in manufacturing companies. The “Made-in-Germany” brand would only be emboldened by the implementation of these technologies.
References
Edward Curry, S. A. (2022). Technologies and Applications for Big Data Value. Springer. doi:https://doi.org/10.1007/978-3-030-78307-5_1
Lázaro, O. e. (2022). Next-Generation Big Data-Driven Factory 4.0 Operations and Optimization: The Boost 4.0 Experience. In E. A. Curry, Technologies and Applications for Big Data Value. Springer, Cham. doi:https://doi.org/10.1007/978-3-030-78307-5_16
Philips. (n.d.). Retrieved from Innovatiecluster- High tech systems Drachten: https://www.icdrachten.nl/en/bedrijven/philips/
Comments