Materials, equipment, and methods have been endlessly refined to create today’s green sand process which produces high quality castings efficiently and inexpensively. But due to the complexity of the green sand process, it can be challenging to reduce defects, increase output or just consistently maintain production with high speed, uptime and quality.

Using digital tools to collect, visualise, monitor and analyse data from all parts of the foundry process is the most effective way to manage and further improve casting production. Even for complete newcomers to digital foundry technology, gaining easy access to a central trusted store of data offers significant opportunities.

A digital foundry system has other valuable applications like cutting costs and CO2 emissions and retaining the knowledge of experienced staff. The eventual goal can be dynamic, real-time process control across an entire line.

The proven route to success is to start digitalising the foundry processes using a single, central system that can be easily extended and upgraded to support a foundry’s digital growth. At every stage, new insights can be unlocked, and significant value gained.

In this presentation, we will outline this type of journey and discuss its challenges, possible solutions and, to ensure successful results, the need to find a partner that combines foundry experience with digital expertise. We will focus predominantly on the first two steps towards being data-driven: foundry digitalisation by connecting and establishing centralised data collection for each sub-process, then implementing access with reporting, monitoring, visualisation and alerting tools to understand the data and gain new insights.

Two case study examples of digitalisation are given. A natural next step is to apply Artificial Intelligence (AI) technology to obtain more new insights and improve further. Many AI solutions are available but a partner that knows the casting process is essential to ensure successful results.

Compactibility is the percentage of compressibility of the molding sand under impact of a predetermined weight (3 ram) under laboratory test standards and conditions. Also referred to as Lab Compactibility in foundry lexicon. A well compacted mould is an indicator of good sand process capability primarily in terms of GCS and Moisture control and predictive of good casting outcomes.

Compactibility may also be said to indicate the sand plasticity and flowability. Foundrymen have traditionally relied on experiential expertise in adjusting Compactibility set-point (CoSP) at the Compactibility controller or the mixer. However, arriving at optimal set points and dynamically varying the same factoring in several input variables that influence

Compactibility, such as relative humidity, ambient temperatures, return sand moisture, return sand temperature, GFN and sieve distribution of the return sand and sand additives, is a challenge for most foundrymen. Hence, more often than not,

Compactibility set point at the mixer is often kept constant over shifts or even longer periods of time. Since the green sand eco-system is in a state of perpetual dynamism, it stands to reason and logic that the system sand and its multifaceted control systems should also be pro-actively controlled, dynamically to maintain the moulding sand/Line Compactibility.

In this paper, we have used a data driven approach to predict Compactibility set point of mixer to maintain moulding sand Compactibility or Lab Compactibility. The developed module is tested in one of the leading Indian foundries. The results show benefits in term of casting weight reduction in majority of components and reduction in casting defects due to better Compactibility control of the moulding sand.

The amount of data available in the modern Electric Arc Furnace operation, even if only using standard instrumentation and automation, has proven to have enormous potential for process analysis and improvement using the latest Artificial Intelligence tools and algorithms, as they have been implemented on a dedicated software recently developed by AMI, the SmartKnB platform.

SmartKnB is a graphic programming interface making possible to develop solutions merging data acquisition, complex process logic and machine learning models, all in the same user-friendly environment. Several applications have been developed and deployed in the field of EAF using the SmartKnB, for instance, to follow the process from the raw material intake, analysing its characteristics in advance to optimize the melting and final steel composition. Also, capable of continuously evaluating correlations between the process and usage of consumables to find the most favourable operating point.

The possibility of adding image processing and using advanced cameras capable of withstanding the harsh environment of a steel plant, will give immediate feedback to the AMI platform, opening a vast field of opportunities to put eyes on the process closer than ever.

Hi-Performance Controllers play an essential role in modern Power Conversion (PC) Systems, increasing performance in PC devices used in the Steel Industry seeking more efficiency, reliability, and long-term maintainability. This article presents an Open Platform for High-Performance Power Electronics Controller skilled in precisely managing power conversion systems with high-speed control algorithms and short cycle times processor.