Workpad Industrial Data Solutions IoT
Visit Workpad at NDTMA to Learn About Cloud Storage for UT Data
Workpad LLC will be demonstrating its cloud NDT data platform at NDTMA in Las Vegas, NV USA Feb. 11-13, 2019. Come visit our booth to see a live demonstration of how to use Workpad to connect any inspection device to the cloud and automate the storage, analysis, and reporting of any type of inspection data including high resolution video and image data, UT and phased array data, and x-ray imaging.

The following case study illustrates how Workpad can automate data collection and apply artificial intelligence to aid in making inspection data useful for customers.

In August of 2018, TechKnowServ approached Workpad LLC to investigate possible solutions for an automated pipe wall thickness data collection and analysis system. TechKnowServ has a number of customers who utilize a diverse selection of pipe components in the field, including elbows, tees, and connectors used to pump drilling fluid at elevated pressures. These components have a limited working life, and are inspected both when new and at regular intervals for wall thickness, corrosion, and defects.

The current method of using ultrasonic thickness gauges in the field resulted in many inefficiencies and inaccuracies in the data generated by the field inspectors. Transferring data manually with memory cards to a stand-alone computer was slow, and offered no ability to securely store data and analyze at scale.

TechKnowServ endeavored to build an integrated inspection, data collection, and analysis system which could improve the efficiency of this process and create a repository of useful data which could provide not only a history of individual parts, but also predict expected service life of components. The goal was to enable customers to predict the service life of parts and assemblies segmented by manufacturer, part geometry, operating environment, and other factors.

Download the case study and learn how Workpad implemented an automated system with machine learning capabilities to improve the process and accurately predict in-service lifetimes of piping components.