The Challenge
The client had many steel coordinators on the mill floor making decisions via heuristic knowledge and spreadsheet-based modeling. Operators leveraged simple averages to understand possible dwell and transit times, often overlooking many available details. The overarching goal was to keep the casting units running constantly and at maximum capacity. To do this, the plant floor operators needed optimal production schedules to maximize output.
Our Approach
The Aimpoint Digital team worked within the client’s Hadoop environment, leveraging Python, Spark, Pyspark, Dash, Docker, and FastAPI to use edge computing nodes to implement a Discrete Event Simulation that scaled to compute thousands of probability densities efficiently and quickly. This allowed the team to run a “what-if” style analysis to determine optimal schedules given production requirements. The Aimpoint team also included additional functionality for the client, allowing them to push files detailing scheduled machine downtimes to understand the effect of machine maintenance on production schedules.
Results
1. Ease of Run:
The client is now able to query their data lake via API to easily return optimized schedules.
2. Dynamic Production Schedules:
Schedules can be quickly adapted based on the changing facility status.
3. Scenario Building:
Thanks to the queries available, the client can run various “what if” scenarios to find the best solution.
Key Takeaways
In a production environment, optimizing output is crucial for efficiency. While manual processes work, they lead to wasted time and resources.
The Aimpoint Difference
At Aimpoint Digital, our mission is to transform intricate data into actionable insights. We achieve this by blending innovative technology with a comprehensive grasp of business needs, resulting in solutions that empower our clients.
Our proficiency in data analysis, attention to detail, and talent for crafting strategies that yield quantifiable outcomes set us apart.
Contact us through the form below to get started today.
