Changing Perspectives and Anticipating the Future Will Help Lower Operational Risk

For more than 15 years, companies in both the oil & gas and chemical industries have looked to XHQ operational intelligence software to help reduce costs and improve margins. With Siemens’ recent addition of both mobile access and BI Tool gateway capabilities, XHQ can now help users address the wider need for digital transformation. Significantly, XHQ fits into new advanced analytics technology stacks without requiring users to replace the systems already in place.

At the XHQ User Conference in Houston, Texas, ARC Advisory Group had an opportunity to meet with both Siemens executives and end users to discuss how these solutions are helping companies better manage operational risk and improve business performance. Key findings include:

• The new XHQ platform now provides support for mobile devices and modern browsers, providing decision makers with easy access to plant and operational data on any device, anytime, anywhere.

• Siemens has made it easier to integrate XHQ to business intelligence (BI) and other enterprise systems to leverage operational data across the supply chain and other management systems.

• Siemens’ MindSphere product now adds predictive analytics capabilities to the XHQ solution to further capitalize on the investments companies have already made to contextualize their data within XHQ.

   

IT/OT Convergence in the Oil & Gas and Chemicals Industries
Due to the complex, energy-intensive, and potentially hazardous and environmentally sensitive nature of most downstream petroleum refining, petrochemical, and chemical manufacturing processes and facilities, these sectors have traditionally been major users of automation and other operational technologies (OT). In recent decades, much of this investment has shifted to operation management software applications that reside above the control layer and to information technology (IT); with gradually increasing convergence between the OT and IT domains.

While current economic conditions and fuel efficiency initiatives have reduced global demand for hydrocarbon products to a certain degree, overall, the current depressed crude prices have not hurt downstream refiners as much as their upstream (exploration & production) counterparts. For integrated energy companies, downstream activity has helped reduce the pain felt by the upstream businesses to a certain degree. Many economists describe this oil price cycle as the “new normal,” leading downstream manufacturers to shift to optimize their operations; “sweating” existing assets and making better use of their data to reduce operational risk and improve business performance. This requires a full understanding of the true situation within an industrial plant or facility, including process, mechanical, and technical elements.

Disparate Sources for Operational Data
Operational data tends to be scattered throughout multiple disparate information sources, both real-time and transactional in nature. Typical systems of record include process historians, lab systems, work order management systems, asset information systems, inventory management systems, operator logs, and plant asset management systems. Increasingly, IIoT-connected smart devices and applications represent additional disparate data sources.

A clear understanding of operational risk requires insights into many of these systems with the underlying data in context. Workers and staff are too busy to establish and create this context using conventional historian tools. Organizing this data from multiple sources and providing context is complex, but essential. Industrial IoT adds more sources of information and more complexity to the data available to analyze different operational problems.

Managing Operational Risk with XHQ
There is a clear trend to provide plant personnel with better decision-support tools to improve plant performance and better manage operational risk. Industry leaders understand the need for operational information to be made available to authorized personnel in context, anywhere, on any device, anytime, and for any valid purpose.

As ARC learned, the new release of Siemens XHQ 5.0 provides the ability to collect and aggregate information from many different data sources (including across the all-too-typical plant functional silos), organize the data, and serve it up to users in ways that are appropriate for what they need to do. Version 5.0 provides organized and relevant visualizations on both mobile and desktop devices, all set up with a single tool; the XHQ Workbench.

XHQ Operations Intelligence aggregates and links plant data from the operational and business level, providing interactive views of the relevant plant data configured to address individual user requirements. The user now has the option to use this contextualized XHQ data to perform self-serve, ad hoc analyses within integrated third-party BI tools.

Impact of Mobility on the Industrial User
The rapid adoption of mobile technologies simplifies technology for end users and decouples plant data from plant-resident computer systems, putting data in the hands of people that can make a positive impact on the industrial supply chain.

As in many other industries today, the speed and complexity of many high-risk operations has increased exponentially, disrupting the way people work, creating stress, and increasing the need for effective decision-support tools. As far back as 2013, sales of commercial-off-the shelf smartphones were significantly higher than personal computers. Increasingly, the mobile device will be the main device people use to connect with their industrial information.

Estimates show that by 2020 there will be six billion smartphones worldwide. As the cost to deploy these types of wireless devices decreases, this number is expected to increase by 15 percent annually. Enterprise IT groups are now embracing deployment models such as “bring-your-own-device (BYOD)” for back office and industrial use. With cost pressures and the need for agility, the market has developed low-cost zippered pouches that allow a commercial mobile device to meet the specifications of harsh/hazardous environments. According to several industry research reports, nearly 50 percent of large enterprises now support BYOD.

Decision support does not end with the operator shift. Operational risk management requirements now decouple the decision maker from the office or industrial setting. Operations typically run 24/7, and managers and supervisors must have instant access to the decision-support tools they need to prevent the next incident or catastrophe at any time, from anywhere.

Taking XHQ to More Advanced (Predictive) Analytics
Much of the currently unused archival data in industrial operations can also be mined to create new value. Massive amounts of unstructured data such as video, audio, work logs, manuals, and paper work order documents can be integrated into analytics. While many industrial businesses have been employing historic performance monitoring and describe/discover analysis (also known as “business intelligence”) for some time, analytics are quickly evolving beyond their BI roots.

Many predictive analytics solutions are available, including those using machine learning and other cognitive approaches. Many industrial sectors lag in the learning curve for newer, predictive analytics. Companies are still trying to understand how to best employ these advanced types of analytics. Despite the challenges, executive expectations remain that analytics can be used to deliver transformational business value. Executives expect that by integrating and analyzing multiple data sources to enhance decision support, they will be able to improve operational efficiency, asset performance, and, in some cases, deliver new, value-based services.

Siemens has built a platform for digitalization as a scalable, cloud-based open IoT operating system in which applications and digital services can be developed and deployed. The platform provides data analytics and connectivity capabilities, plus developer tools for a wide range of applications and services. This offering, branded as “MindSphere, the open, cloud-based system for the IoT,” is designed to help companies improve efficiency. It does so by ingesting and analyzing large volumes of operational data and providing a foundation for applications and data-based services from Siemens and third-party providers. Typical applications include predictive maintenance and process optimization.

Siemens XHQ MindSphere Predictive Analytics Ecosystem

MindSphere can collect large amounts of raw data, analyze it through a range of apps, transform it into knowledge and information, and leverage that newly created knowledge and information to help industrial organizations optimize their production assets and improve business KPIs. This knowledge and information impacts decisions regarding resource usage, predictive maintenance, process and product design, and system performance and availability. Through an “analytic gateway,” XHQ can upload exploratory data to train the algorithms in MindSphere. The creation of the MindSphere product for predictive analytics adds to the XHQ ecosystem, enabling users to capitalize on predictive analytics solutions while protecting the previous investments made in XHQ to contextualize their disparate data.

Conclusion
Digital transformation, Industrie 4.0, and Industrial IoT have brought forth a plethora of business performance improvements and opportunities. How quickly companies can capitalize on this largely depends on how quickly they can scale up. Many companies realize that there is significant value in the data they are already collecting. They also want to protect the investments they have made in systems that contextualize and organize their data.

Analyzing large data sets of structured, historical time-series and unstructured information will become a key basis of competitive advantage, underpinning new waves of productivity growth and safety for the process industries. The companies that invest in making this easy for the average engineer will prevail. Big Data and analytics will unlock significant value by making information more usable or by exposing problems that have been previously unknown. It is not always about using a tool to solve known problems, but instead, identifying and solving of a problem that was mostly unknown. A more sophisticated approach to using data can improve decision making well beyond traditional means.

Over the years, Siemens helped change conventional perspectives in process automation. Today, the company is also helping change perspectives on what is possible for energy and chemicals companies to accomplish with data and analytics. The company has invested to make XHQ a more ubiquitous solution and provided a path to help customers retain their investment and transition to advanced analytics to help reduce operational risk and anticipate events before they occur.

An essential ingredient for this industrial transformation is providing domain experts (as opposed to data scientists) with capabilities to apply machine learning and predictive analytics to help improve plant performance, asset reliability, and reduce risk. To this end, ARC sees value in the emerging advanced analytics such as machine learning, deep learning, and cognitive analytics, along with simply having access to more complete information. This includes the ability for individual plants to compare performance between shifts, and for industrial enterprises to compare performance between plants.

ARC Advisory Group clients can view the complete report at ARC Client Portal on Office 365 or Box.com or New Client Portal on this website

If you would like to buy this report or obtain information about how to become a client, please Contact Us

Keywords: Operational Analytics, Oil & Gas, Chemicals, Siemens XHQ, MindSphere, Operations Intelligence, ARC Advisory Group.