AI-Driven Autonomous Control Reduces Paper Machine Dry End Test Variability

GoalReduce wet tensile variation and improving wet tensile quality adherence.

<h6>Customer Challenge</h6> <p>A large North American Liquid Packaging mill was interested in reducing wet tensile variation and improving wet tensile quality adherence. This mill employed a typical wet end chemical dosage strategy practiced throughout the industry of waiting for dry end quality lab tests to be completed or validated by re-testing before chemical setpoints are changed. These delays typically force operations to run higher chemical feed rates as insurance to ensure no off-quality board is produced.</p> <h6>Recommended Solution</h6> <p>Solenis recommended OPTIX&trade; Applied Intelligence &ndash; a machinelearning, predictive analytics platform with autonomous control capabilities. OPTIX&trade; generates a real-time virtual measure of wet tensile quality using machine learning capabilities.</p> <h6>Results Achieved</h6> <ol> <li>Reduced lag time for wet strength adjustments. Smaller, quicker incremental dosage changes in real time replaced the previous control strategy of waiting for dry end quality tests.</li> <li>Mill management drove wet strength targets closer to the lower control limits with predictable quality target adherence.</li> <li>Optimized wet strength dosage quicker during grade changes</li> <li>Reduced variation in wet strength usage from operator to operator and from shift to shift.</li> </ol> <p><img style="max-width: 100%; width: auto; height: auto;" src="/link/e97f60e6853e41e594deb772a7c1620a.aspx" alt="" width="1100" height="641" /></p> <p><img style="max-width: 50%; width: auto; height: auto; display: block; margin-left: auto; margin-right: auto;" src="/link/0d30e3ebd0b5498cbcaed5de21c347fb.aspx" alt="" width="550" height="588" /></p>