Viking Analytics, a Swedish provider of advanced analytics solutions for predictive operations, and Bharat Forge Kilsta, a Sweden-based supplier of forged components, began collaborating in a data-driven production quality project. In the coming months, Viking Analytics will prepare an assessment of the data collected by sensors installed in the oven that heats steel rods used in the production of crankshafts and front axle beams for heavy-duty vehicles. In Bharat Forge Kilsta’s Karlskoga plant, the forged steel is first heated in an induction oven, whose temperature varies according to different steel grades and products. If a disruption occurs, the oven must be adjusted to keep the metal at a constant temperature. This process is currently performed manually, which sometimes causes human-related deviations in the proper temperature-level records.

Based on large amounts of sensor data from the oven, artificial intelligence (AI) should be able to control the system so that adjustments can be made automatically, eliminating human error. To achieve that, data scientists at Viking Analytics developed a digital twin that simulates the production stage and tests if adding more sensors or changing certain parameters can influence the quality of the data that will be used in machine learning.