Improving Sustainability with Advanced Analytics
Process manufacturing is in the middle of the climate change storm, and as a result, 2021 saw a deluge of pledges from companies to go carbon neutral between 2030 and 2050. Sustainable operation immediately reduces carbon footprint, but it also leads to:
- Measurable progress towards pledges, resulting in better access to capital for investments in new technology, like renewable energy and carbon capture solutions
- Increased profits, decreased waste, and improved process and asset efficiencies
- Positive impact on generations of employees and consumers who want to create a better world
- Increased brand recognition for the company, along with best-in-class operations
Despite these benefits, achieving sustainable operation is challenging without tangible action plans, here’s how to get started.
Barriers to sustainability investment
According to the Climate Action 100+, the vast majority of organizations most responsible for industrial greenhouse gas (GHG) emissions have publicly addressed the environmental and societal demands concerning sustainability, yet 90% do not have capital allocated to sustainability initiatives.
Deloitte’s 2021 Climate Check reports this lack of capital allocation stems from the challenge of quantifying ROI from these initiatives, and the difficulty in determining proper timelines and outcomes. Fortunately, process manufacturers seeking to improve their environment, safety, and governance (ESG) KPIs can tap into a valuable asset already at their disposal in the form of times-series data.
For decades, process manufacturers have collected time-series data in historians. Now, with the right digital tools, they can empower their teams to make sustainability a top priority, and immediately begin progressing toward their ESG KPI goals. Teams can start by monitoring and tracking operations to make data-driven decisions based on emissions, effluents, energy, water consumption, and other information. Analyzing this data can provide practical actions to reduce environmental impacts.
Empowering teams with data accessibility
Similar to safety, achieving an organization’s sustainability goals is everyone’s responsibility. As organizations advance in their adoption of digital technologies and more data becomes available, it is easier for every team member to play their part, without burdensome investments.
For example, operations data touches more than just operators, as it can help asset reliability personnel and environmental engineers. Providing high-quality data to each team member in the shape and form they need it continues to be a challenge, and achieving this requires the right technology applied to the right data.
With Seeq, process engineers and other subject matter experts gain insight into historical and near-real time environmental process data, so they can swiftly focus on process improvement projects, thanks to automated data cleansing and contextualization.
Seeq empowers these users to switch from a reactive, compliance-focused approach to a proactive approach by continuously monitoring parameters to detect and mitigate environmental violations. If detected, a user can assess process performance to identify events that led to the violation.
Seeq’s real-time collaboration capabilities enable teams to make sustainability a shared goal across the organization. With the ability to share insights, teams can alleviate the siloed and error-prone processes that occur when they rely on spreadsheet applications for analysis.
Companies are using Seeq’s self-service analytic applications to not only understand their impact on the environment, but to solve the challenge of meeting aggressive net zero emissions and carbon footprint reduction goals.
At Allnex, multivariate analysis models for total steam demand analyze energy consumption, and these are used to test specific pieces of equipment. When doing this with common tools available to a powerhouse, these models become obsolete quickly. But using Seeq, the models remain in sync with ongoing data capture and the relationships configured by the subject matter expert.
For example, when noticing an irregularity in the performance of a valve feeding a steam jet, the model makes it easy to identify which issue to address, for example an instrumentation or control loop problem.
These types of energy models empower an organization to discover relationships between process equipment and automation systems to improve energy efficiency. In this case, it led to a 30% increase in steam recovery and 15% reduction in steam consumption, which is equivalent to GHG emission of over 1,000 passenger vehicles driven in 1 year.
Other examples of using operational data to implement sustainability initiatives include:
- GHG emission reporting: Seeq helps streamline data collection, cleansing, and analysis, and it can be used to automate corporate GHG reporting workflow. Users can replicate common data rules and standards from site to site, and even among facilities. Seeq serves as the common platform to gain insights and reduce reporting time from weeks to a few hours.
- Safety: Seeq empowers organizations to gain further details into the status of critical equipment, and to closely monitor its performance for reducing risks in operations. For instance, monitoring temperature in a paper machine is critical to prevent fires in the dryer. By capturing and anticipating conditions that can lead to dust collection issues, a multinational paper company reduced this risk in one of their lines, and they replicated this methodology to all similar machines throughout their enterprise.
Leveraging data to make sustainability a priority
Many manufacturing companies are leveraging process data in their quest for operational excellence, but very few are using it for sustainability initiatives. This cannot be overlooked any longer because the bottom line is no longer solely dependent on high throughput and maximum profitability, as environmental impact and recognition are now factors as well.
Regardless of the industry, sustainability-focused projects need not require significant capital investment. Instead, organizations can make positive environmental adjustments by analyzing their data to create insights and make better use of existing assets. Applying self-service advanced analytics to operational data can carry companies toward meeting carbon neutrality goals for 2030 and beyond.
To learn more about Seeq’s use cases, visit the Use Cases page.