{{else if Image}}
{{else if Image}}
{{/if}}
{{/if}}
1/5/2024
Technology & Processes
Die casting process
Experts Know-how
Digitally enhanced die casting: from advanced monitoring to AI-perfected processes
Modern die casting complexity makes manual monitoring and improvement challenging. Troubleshooting is often guesswork and as more experienced staff retire, a skills gap appears, making it even harder to control casting quality, cut costs and lower emissions. Digital is now the most effective – often the only – way to achieve substantial gains.
Foundry digitalization – taking your first steps
Many die casters have standalone digital systems on individual machines that make live data available locally and may also store some data for reporting. But here, you still often need offline data integration to build a whole or partial process view. Manual integration like this is slow and error prone. Merged data and derived variables are also too old for spotting emerging problems. This means root cause analysis is slow and may never fully succeed due to time constraints. A single IIoT (Industrial Internet of Things) platform is the answer, an example of which is Monitizer®. With it, production data goes to a central database where it is stored and combined with other data. In real time.The essentials for effective data monitoring
As more machines are connected to the IIoT platform, it must be able to scale up on demand. Cloud-based modular systems are perfect for this in terms of flexibility and processing power. Whether cloud-based or on-site, the system must be able to extract data from any vendor’s equipment with no or a minimum of extra hardware.
Your IIoT system should collect, timestamp, transmit and standardize data, ensuring its secure storage in a reliable data repository. This approach makes real-time, automatic data integration, reliable reporting, and analysis possible. In a phased deployment, collect data from the most important sub-processes and equipment first to gain maximum value from the data and win further investment to connect other equipment.
Stored data should be available for comparison with live data, and for maximum effectiveness, non-technical users should be able to create and edit their own dashboards and Key Performance Indicators (KPIs) along with visualization tools like charting, tabular reporting, and color coding. Sophisticated notifications and alarms are also key.
Die casters can use their platform to clearly identify which process improvements work best – including those which aid scrap reduction. A big plus for emissions reduction. For instance, consider a foundry producing 50,000 tons of castings annually. It is calculated that if they reduce their scrap rate from five to three per cent, this equates to a saving of 604 tons of CO2 per year.
MAT Foundry Group collects, monitors and analyses data from several sites. Any user in any location can access the central cloud-based platform and monitor live KPIs within customized dashboards to manage daily operations. Senior management can view aggregated data such as casting tonnage or scrap levels per shift while production managers prefer site-specific productivity KPIs such as poured tons per hour, molds not poured and stop/wait times. Factory floor staff monitor live machine data which is color-coded to help them quickly recognize and fix any small technical issues. The system also automatically monitors dust filter pressures and alerts for possible blockages, avoiding production stops due to over-high facility emissions.
Energy monitoring and emissions reduction
Emissions reporting is now an essential – often compulsory – requirement. IIoT systems automatically gather energy consumption data which, combined with other inputs, can be translated into emissions. Access to reliable process data via IIoT makes scope 1 and 2 carbon reporting much more feasible, especially when multiple sites are involved.Die casters can use their platform to clearly identify which process improvements work best – including those which aid scrap reduction. A big plus for emissions reduction. For instance, consider a foundry producing 50,000 tons of castings annually. It is calculated that if they reduce their scrap rate from five to three per cent, this equates to a saving of 604 tons of CO2 per year.
Digitalization in the real world: two examples
Alupress Foundry, is using the Monitizer furnace monitoring system to optimize metal supply at its Hildburghausen site in Germany. The tool monitors dosing furnace fill levels against the metal consumption of the die casting process. Dashboards in the melt shop, the production hall and on forklifts show in real time when each furnace will need refilling, with which alloy, and the amount of metal required. Colour codes indicate priority levels. This replaces time-consuming manual fill level checks and reduces the risk of downtime and other downsides due to refilling with the wrong alloy, overfilling or underfilling. LENAAL is another aluminum die casting specialist benefiting from this technology.MAT Foundry Group collects, monitors and analyses data from several sites. Any user in any location can access the central cloud-based platform and monitor live KPIs within customized dashboards to manage daily operations. Senior management can view aggregated data such as casting tonnage or scrap levels per shift while production managers prefer site-specific productivity KPIs such as poured tons per hour, molds not poured and stop/wait times. Factory floor staff monitor live machine data which is color-coded to help them quickly recognize and fix any small technical issues. The system also automatically monitors dust filter pressures and alerts for possible blockages, avoiding production stops due to over-high facility emissions.
Leveraging the power of AI for scrap reduction
Use of Artificial Intelligence (AI) can make a significant difference to performance when built on top of a mature data platform as described above. An AI-driven Expert Execution System (EES) considers all the process parameters from an entire production line to maximize one target variable – casting quality.The AI examines historical data by creating a holistic process view and their effect on the final casting quality. It then builds the initial model that specifies the combination of machine settings and material properties will produce the best results for each pattern.
During production, instead of simply reacting to quality issues, the EES updates recommendations for the control plan every 30 minutes in response to AI predictions based on real-time data. That maintains stable, high-quality production, even as factors like air temperature vary. The base model is regularly updated with new parameter and final quality data, so optimization results continue to improve.
AI works. A global automotive OEM we supported with implemented an AI-driven Expert Execution System (EES) for low pressure diecasting reduced scrap by 29 per cent in its light-alloy wheel manufacturing process, resulting in a predicted gross annual saving of more than 0.5 million euros and a 2.4 per cent production volume increase. Japan’s Morikawa foundry started testing AI-driven optimization in 2022. The first tests on two different patterns cut scrap rates by 66.6 per cent and 86.9 per cent.
In conclusion, manual techniques don’t meet the needs of a modern foundry. Digital data and tools are the way to manage and further improve casting production – and an IIoT system that collects and sends data to a central database is the optimal solution, especially when paired with AI technology. With these tools, and the support of an expert implementation partner, die casters have a clear path to digital success.
During production, instead of simply reacting to quality issues, the EES updates recommendations for the control plan every 30 minutes in response to AI predictions based on real-time data. That maintains stable, high-quality production, even as factors like air temperature vary. The base model is regularly updated with new parameter and final quality data, so optimization results continue to improve.
AI works. A global automotive OEM we supported with implemented an AI-driven Expert Execution System (EES) for low pressure diecasting reduced scrap by 29 per cent in its light-alloy wheel manufacturing process, resulting in a predicted gross annual saving of more than 0.5 million euros and a 2.4 per cent production volume increase. Japan’s Morikawa foundry started testing AI-driven optimization in 2022. The first tests on two different patterns cut scrap rates by 66.6 per cent and 86.9 per cent.
In conclusion, manual techniques don’t meet the needs of a modern foundry. Digital data and tools are the way to manage and further improve casting production – and an IIoT system that collects and sends data to a central database is the optimal solution, especially when paired with AI technology. With these tools, and the support of an expert implementation partner, die casters have a clear path to digital success.
