Uptake Solves Dirty Data Problem with AI Data Integrity Capability for Maintenance Optimization

Uptake Asset IO Repairs Work Order Data to Provide Insights for up to 20 Percent O&M Savings

Industrial artificial intelligence (AI) leader, Uptake, announced it is solving critical problems for the Energy, Industrial and Utilities sectors by providing comprehensive data integrity capabilities for operations and maintenance (O&M) that allows work order cost analysis overcoming the industry challenge of incorrect, dirty work order data.

Companies worldwide are using advanced analytics and machine learning for predictive maintenance strategy optimization as a driving force to reduce operational costs. However, the lack of clean data is a major impediment to achieve those cost savings. Industrial companies are particularly susceptible to dirty data due to wildly disparate, legacy systems, frequently missing, or miswritten, data and the prevalence of proprietary systems that have their own data language. Uptake has solved this problem.

Read More: Bithumb to Strengthen Its Cooperation with a Blockchain Firm to Dominate the Security Tokens Market

“Operational and maintenance data in the Industrial, Energy and Utilities sector is often inaccurate or missing critical pieces and AI-driven insights are only as good as your data,” said Jay Allardyce, Uptake’s Chief Product Officer. “This Uptake APM capability for data integrity is a first for the industry allowing companies to successfully implement predictive maintenance strategies that increase revenues with better insights and reduce annual O&M costs by up to 20 percent.”

Asset IO, Uptake’s Asset Performance Management (APM) application, includes a new module capability to ingest years of work order data – from existing computerized maintenance management systems (CMMS) and enterprise asset management (EAM) systems that leverage artificial intelligence and natural language processing to complete missing data, suggest asset labels and create an asset category schema where none exists. The result is a clean dataset for work order cost analysis that can be used to inform critical preventive and predictive maintenance strategies to de-risk operations and reduce annual O&M costs significantly.

Read More: Twenty Interesting AI Symbiotic Events To Look Forward To In 2019

“There is a major barrier for industrial plants when it comes to leveraging the value of their assets using current EAM/CMMS software. These systems are not designed to deal with many of the data challenges common in work orders, such as incorrect or incomplete information, role and location-based variations in word meaning, and the heavy use of slang and shorthand, which can change over time,” said Mike Guilfoyle, Director of Research at ARC Advisory. “So much organizational knowledge is locked within these work orders, unable to be leveraged as the key intellectual property it is. By overcoming this barrier, industrial plants can use this knowledge to reduce their O&M expenditures without raising production risk and better execute maintenance strategies aligned with operational excellence goals.”

The Uptake Asset IO application also leverages Uptake’s Asset Strategy Library, which has records of over 58,000 machine failures and over 800 critical asset types and has been trained on over 2.1 billion hours of operational machine data that allows customers to leverage the largest library of asset types, machine failures and preventive maintenance strategies data in the world. By deploying Asset IO, industries can unlock new operational efficiencies by making proactive maintenance decisions based on predictive insights. Our industrial AI and machine learning engines understand over 10 million different components to help predict and prevent problems before they happen.

Read More: Lockheed Martin and Drone Racing League Announce 2019 AlphaPilot Teams