3 Key Elements of Data-Driven Sustainable Operations

Tackling sustainability and productivity goals in your operations starts with data. The good news is you may already have relevant data available to help drive progress and results.

Understanding the data you have will help you build a better roadmap and avoid unnecessary cost and complexity in your operations. While you may need future investments, keep in mind that there is value to unlock in your operational technology today.

Knowing the data that’s possible to obtain from existing solutions helps maximize the value of your investments and is also a starting point for:

• Baselining and reporting on data
• Identifying areas of opportunity
• Tracking progress towards goals

These data then inform an actionable plan for process improvements. For example, once baseline energy usage is established, patterns can be uncovered, paving the way for improved ESG reporting and reduced consumption. Not only does this kind of initiative address sustainability goals, but it also supports efficiency, savings and productivity objectives as well.

What this involves:

Take a closer look at your automation solutions. Review the data they create and collect and assess how the data can be used for sustainability (and productivity) purposes. Consider working with an automation expert, as they may be able to conduct this review on your behalf.

You likely already have sensors and machinery in place that provide production efficiency data, or readings on your energy usage. And it’s possible that you may need a few more sensors to obtain the data granularity that’s required. But in most cases, your existing equipment has an important role to play as a source of sustainability-related data.

For example, existing industrial control and automation hardware and software can often double as energy data sources, providing energy data contextualized to production data at the site, area, line and machine levels. When these data are contextualized and integrated across your operations, it can help shed light on broader resource impacts, such as the energy consumed in water-intensive processes. It can also support critical business needs such as emissions reporting.

Evaluate whether key data are quickly visible and available for analysis. In certain cases, there will be work to do around optimizing how data are surfaced, modeled and aggregated. Regardless of your current state, building a picture of sustainability-related data from your existing solutions will help you get the most out of what you already have, and identify gaps to prioritize investments.

Addressing sustainability goals starts with access to contextualized and trusted data for monitoring and reporting.

After data are contextualized and trusted, the next step is to optimize by automating actions based on these data and advanced algorithms. Technologies like machine learning (ML) and artificial intelligence (AI) can guide your control system responses and reveal continuous improvement opportunities.

Automating actions based on data and algorithms takes you from process improvement to performance optimization. On a day-to-day basis, process variables and resource consumption are fine-tuned so that only what’s needed is used.

With ML and AI, systems can dynamically adjust processes in real time based on predicted conditions, boosting efficiency and making it possible to achieve sustainability and productivity goals at scale.

What this involves:

Assess your advanced analytics capabilities. You may already have tools for modeling and uncovering actionable insights from your data. And if there is a gap, keep in mind that adding in ML and AI capabilities could be simpler and faster than deploying new hardware.

Identify high-value use cases for predictive insights. For example, algorithms can be trained to predict energy consumption of a particular line, machine or component, making it possible to detect anomalies and set up rules for corrective action triggers. Similar modeling can be done to predict a host of other scenarios, such as when equipment maintenance will be required or when chemical injection setpoints need to be changed in water treatment operations.

Connect to control systems for automatic improvements. Using algorithms in concert with automation systems unlocks a new level of optimization. Consider a smart water pressure management scenario, where pressure fluctuations are predicted and proactively managed in order to mitigate leaks and improve reliability.

Advanced process control solutions, which provide an intelligence layer on top of an automation system, are designed for this purpose. These solutions continually assess current and predicted data, compare that data to desired results, and proactively drive changes. This makes it possible to automatically reduce process variability and optimize resource usage.

A data-driven sustainability approach must ultimately scale across the full product lifecycle and value chain.

It starts with gathering and contextualizing data from your operations and ecosystem. It also involves automating actions to move from performance improvement to performance optimization. This forms the basis for driving holistic, scalable improvements.

As sustainability reporting continues to mature and as products evolve, adaptation will be critical. Having a quality stream of data allows your operations to adjust to regulatory compliance requirements and emerging needs.

Combining analytics and AI solutions with automation helps you reduce cost and carbon at the same time without impacting your market positioning or pricing.

With these capabilities in place, optimizing for sustainability becomes not just a production focus, but instead an ongoing business process at scale. Setting up optimization efforts now enables you to drive larger initiatives that support a more sustainable world.

What this involves:

Set up data and analytics capabilities for scale. Progress towards a more sustainable operating model across the value chain starts with creating steady streams of actionable data to drive insights and improvements in resource usage—starting with a single machine, then scaling. Next is analyzing and modeling the data and gleaning insights to drive improvements in resource usage—starting at a single line level, then scaling up to cover an entire operation.

Establish an operating system for continuous improvement. The process of uncovering digital sustainability insights and driving changes is the basis for closed-loop improvements. A fully automated continuous improvement approach requires IT/OT convergence, enabling a digital thread of data across every stage of production—and ultimately across the entire value chain. This seamless flow of data creates a holistic understanding of resource usage and fuels a collaborative approach to improvement and optimization.