Fixing problems before they arise in oil and gas
As part of its IoT kickstarter program, the SAP Co-innovation Lab in Silicon Valley partnered with Mtell and Rolta on a solution for predictive machine maintenance in oil and gas. Built on SAP HANA, the solution uses data from disparate sources to diagnose problems faster and better, and shows potential for extending machine life, avoiding failures, and saving money in a high-risk industry. In this interview, David Cruickshank, senior director SAP Co-innovation Lab, speaks about the co-innovation, its impact, and the technologies powering it.
Q. What is the problem that SAP, Mtell and Rolta seek to address?
A. Oil and gas companies struggle to converge information and operations technology to get real-time insight for decisions to innovate processes. The predictive maintenance solution we created brings together different data sources, including asset performance, external data sources, and input from field contractors. The solution automatically sends an alert on potential machine failure, expected time-to-failure, and provides prescriptive advice. This makes it possible to fix small problems before they become big ones. Ultimately, this solution enables early action to avoid or reduce the effects of machine degradation and failure.
Q. What capabilities did the three co-innovation partners bring to this solution?
A. Mtell created a machine learning and neural network that recognizes patterns associated with machine performance. Their software automatically generates notifications and sends them to SAP Plant Maintenance, which planners use to schedule machine repair and replacement. We improved their ability to analyze volumes of O&G asset data by integrating the solution with SAP HANA. The in-memory technology and analytics of SAP HANA enable real-time analysis to pinpoint potential machine failures.
This analysis is then delivered to Rolta’s OneView software solution, where it is displayed on one of the 30+ job-specific dashboards designed for O&G operations personnel. Rolta’s solution is available for SAP BusinessObjects, Business Intelligence, and the HANA platform, so customers can choose whatever environment is best for them. The synergy of the technologies from Mtell, SAP, and Rolta creates a solution that is greater than the sum of its parts.
Q. What outcomes are possible by running these solutions on SAP HANA?
A. In an analysis on IoT, InfoWorld wrote, “the primary value in an IoT system is in the ability to perform analytics on the acquired data and extract useful insights.” SAP HANA enables Mtell to simultaneously analyze the members of “pools” of connected equipment at different locations with great speed and improved accuracy.
The volumes of data are greater than can be managed in an SQL Server, so the closest comparison would be Hadoop. Hadoop excels as a cold storage technology, but when applications require repetitive, low latency access to large volumes of data, SAP HANA provides better performance. For example, 25,000 queries, each linking to 5 million sensor measurements, can be completed on SAP HANA in 1.5 days. The same would take Hadoop almost 3 weeks to complete.
Q. What has been the business value for SAP from this co-innovation project?
A. Fundamental to SAP’s IoT strategy is that we partner with suppliers of device hardware, data network, application software, and IoT service providers to build an extensive ecosystem to ensure we generate broad adoption. IoT is forecast to become a multi-million Euro software market by many analysts and there is a need for horizontal integration to leverage this opportunity.
SAP is working with a wide ecosystem, from leading tech companies to startups, to take on big business problems because a co-innovated solution can absorb the brunt of risk easier than a single company. The right combination of knowledge in a collaborative project accelerates the innovation and solution development. The SAP Co-innovation Lab knits together the technical business project objectives to industry-validated solutions, enabling a faster go-to-market track.
Q. Can you tell us where the project stands currently and plans for it?
A: This is the first IoT kickstarter project at SAP Co-innovation Lab in Silicon Valley. It was a pilot and was completed in just over 90 days. A whitepaper and new demo will be released soon. More news and collateral will grow as the go-to-market strategy and rollout plans for the solution are finalized between now and September. A follow-on project is underway for complete delivery of the solution on the SAP HANA Cloud Platform. If you’re interested in seeing this prescriptive maintenance solution for O&G, please visit us at the Co-innovation Lab at Palo Alto.