Cracking the Code
Digital technology is revolutionising industries around the world, with even traditionally conservative sectors such as plant and chemicals embracing its potential.
Chemicals companies are turning to digital technology to gain a competitive advantage as competition increases and margins continue to be squeezed. A recent survey of key decision makers within the chemicals industry found that 92% of those interviewed believe they will be left behind competition if they don’t adopt digital technologies.
Some chemical organisations such as Eastman Chemicals Company, a global organization, headquartered in the US and Russian firm NIIK are already reaping the rewards of more efficient operating processes. Eastman, for example is confident of achieving industry benchmarks savings of 30% reduction in engineering and design costs and 3% Total Installed Cost after implementing intelligent data management software while Russia’s NIIK has introduced laser scanning and 3D modeling to execute projects faster and save significant costs. Some of the improvements have been dramatic: pipeline specifications have been reduced from three days’ work to one hour. Changes are managed 15% faster, and corrections for collisions and clashes specifically are 50% faster.
Many chemical companies recognise that the future is digital and are actively implementing intelligent information management systems to create a single source of accurate and trust-worthy data throughout an asset’s lifecycle. However, there remains a lack of understanding of both the full benefits of digital transformation and how best to implement successful programmes. This confusion is preventing the sector from fully cracking the digital transformation code.
Industrial Internet of Things (IIoT) and Industry 4.0 technologies promise to tackle these problems by promoting operational efficiency and sharing of consistent data. But while it is easy to be dazzled by a piece of “cool” technology, for industry the primary driver must always be business value. In this context, there are two particular technologies that have huge potential to deliver value on investment in the chemical industry.
The first is augmented reality (AR). This has the potential to transform plant engineering, operations and maintenance – enabling engineers and operators to be able to point a tablet at plant equipment and have it overlaid with the relevant logs, diagrams and performance curves.
Second is predictive maintenance. An ARC Advisory Group reliability study showed that 82% of all assets have a random failure pattern. That means that even with the best preventive maintenance practices, the very best people can’t account for the random failures that no one sees coming. But what if they could?
Predictive maintenance solutions use advanced analytical methods to capture problems before they occur, helping to improve reliability and performance. Leading chemical companies have already incorporated this approach into their operating practices; indeed, a predictive maintenance solution enabled a large industrial gas company to detect a slight vibration anomaly, leading to the discovery of a cracked impeller inside an air compressor. This single catch saved the company over $500,000 in maintenance costs avoidance and unplanned downtime. By adopting AR and predictive maintenance, chemical companies can empower their operators with digital insights to improve their operations and their bottom line.
Augmented Reality (AR)
While every trade show contains highly produced demos of so-called digital twin and AR technology, a lot of what’s being demonstrated fails to deliver on the tangible value that customers need to see to justify investment in new technology. But AR technology does merit investment because it can empower users in the field with actionable insights. One of the leading chemical companies in the world, BASF implemented AR as part of the company’s Industry 4.0 initiative. The company is using it to achieve operator-driven reliability, improving asset performance, reliability and utilisation while increasing production efficiency.
Talking to our clients, their overarching concern is how to operate their enterprise more efficiently and profitably. Yet much AR technology was developed without understanding the specifics of an industrial use case. With that in mind, let’s turn to how AR technology is starting to change industrial operating practices.
Building Augmented Reality on Mobile Technology
Asking users to completely modify the operational tasks they’re familiar with overnight is a recipe for failure. Yet, drawing on workers’ increasing use of technology in their private lives, companies are learning the benefits of tech that can draw together useful information from diverse sources into a single interface that teams can work with easily. As the industrial workforce shifts, this kind of intelligent data management is increasingly important.
As companies adopt digital technologies, they are learning to build on existing foundations which can help them to drive efficiency. One key area is mobile technology that teams already use in their daily routine. Rather than trying to transition users and operators to an entirely new way of performing their job duties through AR goggles, start small. Begin by enabling operators in chemical manufacturing plants to perform maintenance rounds using mobile technology, like smartphones and tablets.
Applications in Chemical Manufacturing
This immediately delivers value in traditional chemical manufacturing applications. For instance, mobile operator rounds enable operators to capture key operational data in digital form to immediately give the entire organisation real-time operations visibility. This also drives enterprise wide KPI management by providing all functional units with complete manufacturing situational awareness.
These solutions accelerate the speed and accuracy of operator rounds by delivering important KPIs directly to their device and automating task management. Operators can also capture pictures and videos of the assets directly for further documentation purposes and can collaborate in real-time with reliability engineers and operators performing maintenance rounds. When Ascend Performance Materials implemented mobile operator rounds, the company saved over $1 million in maintenance costs and $2 million in avoided plant shutdowns.
Typical maintenance strategies start with preventive maintenance based on calendar time or usage. But how does one account for things like manufacturing defects in equipment or simple human error in maintenance procedures? Shadow sensing technology, machine learning, big data and predictive maintenance are allowing companies to shift to a new, IIoT-enabled proactive maintenance solution. These solutions replace conventional reactive maintenance strategies with the ability to see what’s going to fail weeks or months before it does. That means you can perform maintenance at the optimal time, instead of replacing equipment that still has a useful operational life ahead of it or scrambling after a failure occurs.
More accurate and efficient automated data collection enabled through IIoT sensor and information technology drastically expands the number and variety of environmental and operational parameters that maintenance and operations technicians can use to keep their systems running. The downside is that this big data can be cumbersome to actually sort through and manage. Predictive maintenance solutions use analytic techniques such as advanced pattern recognition (APR) and machine learning to tackle this big data, parsing actionable insights from the volume of data to detect the smallest operational anomalies. This provides users with the insights they need to take corrective action.
User-Friendly Predictive Maintenance
When implementing predictive maintenance, one common hidden cost is the complexity of the solutions. Many solutions require in-depth coding knowledge to use and configure properly. Some of the more complex solutions may require a dedicated data scientist to properly deploy and adjust the solution. In the long run, this level of staff investment can add up to a substantial cost. Therefore, selecting a user-friendly predictive maintenance solution can make all the difference for chemical companies. These solutions are easy to use and can be configured without any programming experience. This makes it possible for chemical companies to adjust these solutions without substantial (and expensive) support from the original vendor or outside consultants.
By implementing predictive maintenance, chemical companies can benefit from higher uptime, better reliability and reduced maintenance costs. Being able to predict and schedule maintenance properly also leads to reduced inventory costs. In addition, preventing unexpected equipment failures in a chemical manufacturing plant with many volatile agents has a huge positive impact on employee safety and regulatory compliance.
It is clear that the chemicals sector is now fully aware of the advantages of digital transformation and they are actively investing in technologies. While AR and predictive maintenance can immediately deliver value, the results they deliver will only ever be as good as the data they are working with. Therefore, in their quest to cracking the digital code, the first step must be an intelligent data management. The success of these solutions can them help justify the business case for further technology adoption, enabling your company to take the next step on its digital transformation.
To learn more about AR, predictive maintenance and the benefits of digital transformation, visit our stand at the ACHEMA Conference in Frankfurt, Germany from 11-15 June 2018.
Kim Custeau has 30+ years of experience in industrial asset management software and services. She is currently responsible for the strategic direction, commercialization and development of Schneider Electric Software’s Asset Performance software portfolio globally, delivering solutions that help customers improve asset reliability and performance to maximize return on capital investments and increase profitability.