To address this, the team at Tredence developed an analytically robust approach with the following specifications:

                              • Identified primary drivers among the selected machine variables using ML variable reduction techniques
                              • Driver models to understand key influential variables and determine the energy consumption profile
                              • Identified the right combination of drivers under the given production constraints – time, quantity and quality
                              • Optimization engine to provide the machine settings for a given production plan

                              KEY BENEFITS

                              • The learnings will be used across similar machines to create operational guidelines for reducing energy consumption


                              • We were able to achieve a ~5% reduction in energy consumption across major machines