Digitalization Drives Sustainability

Digitalization Drives Sustainability
Digitalization Drives Sustainability

The production of greenhouse gases, inefficient water and energy usage, and significant harmful emissions have given the manufacturing sector a negative reputation for its impact on the environment. For example, the oil and gas industry alone is responsible for 42% of the world’s greenhouse gas emissions.

As a result, manufacturing sector organizations have a moral, social, and economic obligation to address sustainability as a top corporate objective, and to make the necessary investments to ensure sustainable operation. Over recent years, sustainability has become a popular buzzword in many companies’ annual reports, and organizations often invest in personnel with a sole focus on sustainability.

Yet with all this focus, along with clear recognition of sustainability as an important topic, organizations struggle with exactly what to do or how to achieve their objectives. The result is often well-intentioned goals that fall short of objectives, with no measurable outcome or improvements.

Digitalization can be used to improve efficiency and thus sustainability, specifically by creating more value from data through the use of advanced analytics applications.


Implementation impediments

Although sustainability is clearly recognized as an area of significant importance in the process industries, companies are typically challenged to identify places to invest time and resources. Sustainability in the process industries is often synonymous with cutting-edge or newer technologies, such as carbon capture, alternative energy, and power storage. While these initiatives can be effective, they are expensive to implement and maintain. Companies interested in sustainable operation may lack the capital to invest, as it is difficult to quantify the return on investment.

These large capital projects are not only costly, but the benefits of sustainability are also not immediately realized. For example, wind energy is recognized as a green energy source, but there is a carbon footprint associated with the production of each wind turbine, which must be paid back through operation. When factoring in the time required to design, build, and implement a wind farm, the period to realize the sustainability benefits is much longer.

The same concept applies to many other technologies. And while innovations such as these are part of the solution, focusing solely on these new, niche technologies often makes companies overlook what they can do right now to optimize their environmental performance, with little to no capital investment required.

Frequently, companies do not have an accurate or easy method for presenting and tracking their current environmental performance. Without this insight into current operation, it becomes difficult, if not impossible, to make improvements and optimize. So, why aren’t companies doing more to track their environmental performance by optimizing use of their existing assets? Simply put, they do not have the right tools in their digitalization arsenal.

Without the right tools, designed specifically for analyzing time-series manufacturing data, performing any sort of metric calculations is difficult and time consuming. This often causes valuable engineering resources, typically subject-matter experts (SMEs), to invest significant amounts of time in menial data management activities. Without the right tools to give a company and its employees insight into their environmental key performance indicators (KPIs), there is little that can be done to drive improvements.


Advancing with analytics

Process manufacturers can use advanced analytics applications, a key component of digitalization, to gain more insight into their environmental process data. With the right tools, process manufacturers can leverage the expertise of their SMEs to define sustainability KPIs and track performance. Knowing the score enables the organization to identify areas for improvement, so it can optimize the environmental performance of existing assets.

Without the right tools and KPIs, organizations are at best reactive to their environmental performance, responding to events after the fact when they are identified in monthly or quarterly reports. Advanced analytics applications empower process manufacturers to move from this reactive approach to a proactive, or even a predictive, model.

For example, advanced analytics applications enable SMEs to identify relationships among environmental KPIs and process parameters. With these relationships understood, entire processes can be continuously monitored to identify and mitigate environmental excursions. This continuous monitoring ensures quick reaction to events, while facilitating root cause analysis by SMEs. Excursions are identified and acted upon quicker, and root causes and leading events can be quickly identified.

Advanced analytics applications not only provide monitoring and root cause investigation, but they also can be used to build models of a process to better understand how changes to the process or events will affect environmental performance. These models allow SMEs to perform “what if” analyses to gain a comprehensive understanding of any impacts to environmental KPIs. These models can further be applied to predict environmental performance, which can be used to prevent excursions entirely.

With the right advanced analytics application, insights can easily be shared and communicated with colleagues and the broader organization. SMEs can collaborate with their colleagues in real time, alleviating the siloed and error-prone analyses that exist when organizations are not equipped with the right tools and depend on spreadsheet applications. Analytics can quickly and easily be scaled to many assets across the entire fleet, with results communicated through auto-updating dashboards or reports.


Analytics in action

Improving environmental performance can mean many different things and often varies by company, industry, and objectives. Many oil and gas companies are focused primarily on decreasing emissions, while other companies may be more interested in minimizing water and energy consumption, while others work on progress toward the circular economy. Whatever the focus, advanced analytics can play a role in achieving an organization’s objectives for more sustainable operation.

Reducing emissions: With the world’s current focus on climate change, emissions are a huge area of concern for oil and gas companies, and other heavy industries as well. Yet, when typical process engineers at a refinery think about emissions, they are likely focused on compliance. When SMEs are not armed with the right tools, a typical workflow requires downloading historical operating data to a spreadsheet application, and then spending days each month cleansing, aggregating, and contextualizing the data to identify excursions.

And while compliance is important, companies need to do more than just comply to go net zero. Focusing solely on compliance results in reacting to environmental excursions after the fact. To shift from this approach, organizations need to empower their SMEs with advanced analytics applications so they can contextualize data, and then provide key insights, or perform root cause analysis in real time.

At one super-major oil and gas company, SMEs used an advanced analytics application to automate their regulatory compliance reporting. The application pulls data from the process historian and applies calculations defined by process engineers to report emissions levels accurately and efficiently, ensuring regulatory compliance.

Figure 1: Organizations can use advanced analytics applications to monitor emissions KPIs across an entire fleet of refineries.

As new data becomes available in the data historian, the calculations and reports are automatically updated with the latest information (Figure 1). By using an advanced analytics application, the company has saved a significant amount of time in generating these reports.

But more importantly, having emissions performance information readily available with the latest data empowers the company to shift from a reactive to a proactive approach to identify issues quicker, instead of just reporting after the fact.

In another example, a super-major oil and gas company leveraged an advanced analytics application and its flexible architecture to operationalize the work of a centralized data science team, which built a proprietary neural network algorithm to estimate NOx emissions based on the current operation of the site. This algorithm was then deployed as a custom add-on tool in the advanced analytics application, providing wider availability to the site teams, along with seamless integration to their application.

The team of engineers at the site now uses this custom tool to gain near-real-time insight and monitoring into their environmental performance, enabling them to make proactive decisions and adjustments to reduce greenhouse gas emissions.

Cutting energy and water consumption: At a specialty chemical manufacturer, SMEs used an advanced analytics application to build a multivariate model of the chemical manufacturer’s process energy consumption. This model was used to compare expected (modeled) and actual energy consumption (figure 2).

Figure 2: Using an advanced analytics application, SMEs working for a chemical manufacturer compare modeled to actual energy consumption. If a high deviation from the model is identified, SMEs perform a root cause analysis.

These comparisons and subsequent investigations have identified process issues, such as a nonfunctioning valve or a poorly tuned controller, causing significant energy waste. Identifying the root cause of these deviations enabled the engineers to perform corrective actions and mitigate energy waste. Before developing these energy models, such issues typically went undetected.

Progress to a more circular economy: Advanced analytic applications can be applied to help process manufacturers as they continue to promote the circular economy. Manufacturers are being pushed, now more than ever, to produce the required goods using methods that ensure efficient use of raw materials, less waste, and more recycling. As with other sustainability focus areas, these objectives can be achieved with the help of advanced analytics.

With the right advanced analytic application, SMEs can monitor their plant, process, or equipment mass balance in near real time. While organizations may already have methods for performing mass balance calculations, these traditional methods are often difficult to maintain and update as new data becomes available.

However, with an advanced analytic application, SMEs can run their mass balance calculations continuously to track changes over time and efficiently identify deviations. In this case, deviations may indicate a loss or waste of material, and identifying these issues in near real time allows proactive mitigation.


Final thoughts

Process manufacturers have a moral obligation to be world leaders in sustainability efforts, but they are faced with the daunting task of determining the best approach to address concerns. They should not overlook the optimization opportunities already available at their fingertips to use existing assets and resources more efficiently, with low to no capital investment.

As part of a larger digitalization effort, using advanced analytic applications to reach sustainability goals ensures an organization is fully leveraging its workforce’s expertise. Additionally, any changes or process optimizations implemented as a result of insights typically result in immediate performance improvements.

Sustainable manufacturing is a significant topic, and many people are passionate about the issue. By arming personnel with the right advanced analytics applications to provide more insight into environmental performance, companies can engage their employees at all levels to directly and  positively impact the organization’s environmental footprint.

All figures courtesy of Seeq Corporation

This article originally appeared in the February 2022 issue of InTech magazine.

About The Author


Lindsey Wilcox is a customer success manager at Seeq Corporation, where she helps end users discover new ways to interact with their process data to drive continuous improvement using advanced analytics software. Before her role at Seeq, she served in engineering positions at the Westinghouse Electric Company and Control Station, a software company focused on process control optimization. She has a BS in chemical engineering from the University of Connecticut.

Read More

Did you enjoy this great article?

Check out our free e-newsletters to read more great articles..

Subscribe