Open Source Dataset Generator for Data Analytics, 23TAPPICon

Data analytics requires a dataset to provide the data that will be analyzed. The most common source of a dataset is from a real time connection to data historian or an exported file from a historian. When data analytics is used for training, testing, or demonstration purposes, the following challenges have to be overcome:

• Requiring an industrial process and a control system with a historian is prohibitive for schools, vendors, and other such users
• Obtaining a dataset from an industrial firm is difficult due to proprietary intellectual property
• Data from an industrial process may lack sufficient excitation in variables to perform accurate analysis.

The authors have developed a general-purpose industry wide dataset generator tool to generate a dataset. The specific application shown in this paper is for modeling paper final product quality (principally strength properties such as tensile, tear, burst, etc) with process data, quality control system (QCS) data, and pulp quality data as inputs and lab samples as the modeled properties. However, this tool can be customized and configured to generate simulated process data for any industrial process.

TAPPI conference proceedings and presentations, technical papers, and publication articles provide technical and management data and solutions on topics covering the Pulp, Paper, Tissue, Corrugated Packaging, Flexible Packaging, Nanotechnology and Converting Industries.

Simply select the quantity, add to your cart and your conference paper, presentation or article will be available for immediate download.