Process Predictive Analysis in Pulp and Paper Mill

Qsee

Process Predictive Analysis in Pulp and Paper Mill
Qsee Qsee
View Full Case Study
Contact Vendor
Feature New Record
OVERVIEW

Common paper breaks consequently lead up to 60 minutes of downtime, delaying a potential $10K per hour of production value process. Thus, defective products cause financial and damage company's reputation. Improving quality and reducing defect rates can generate millions of dollars of revenue per year for your company.

Manufacturing plants

Qsee is able to predict and optimize quality test during the production letting the operator save time and get the right insights for all the produced products.

IT
Cutting Edge (technology has been on the market for < 2 years)
OPERATIONAL IMPACT

The predictive quality AI technology analyzes and generates predictions during the production and alerts the operator the quality of the paper based on the parameters collected at that moment.

It is able to create an automated independent tool to predict the CMT and other tests results during the production with 99% accuracy. Resulting also in 4 times more tests done than the quality control lab. False positives and negatives from the lab's results can be detected with 97% accuracy.

Qsee predicts and explains (at least 40 minutes on average) paper strength and prevents paper web breaks to help manufacturers improve productivity and product quality before problems occur.

Within a one month window, data was analyzed and predicted over 80% of the events. The predictive quality AI technology alerted (on average) 2 times and 40 minutes in advance per event.

QUANTITATIVE BENEFIT

Reduction in downtime by predicting and preventing tears. Enabling the operators to proactively take action and reduce 50% of the web breaks. Automate ongoing Quality tests and reduce depreciation online in production. Optimize raw materials to reduce waste and returns due to bad quality and provide optimum and peak quality. It instills greater confidence with the increase in productivity and peak quality, resulting in significant yield improvement.

Continuous failure prediction and root cause analysis, secured and backed up, improves process stability


Fatal error: Call to a member function getLabel() on null in /efs/iotone.com/module/Application/view/application/common/IoTSnapshot_view.phtml on line 9