Automating data insights and reducing time-to-action

ERM and its technology partner TwinThread recently teamed up to identify actionable and preventative steps for solving issues on a major water treatment system at a former industrial site in Portland, Oregon.

ERM's legacy processes for collecting, analyzing and reporting water treatment system data across many asset types presented challenges to its project and operations teams. Typically, project teams would work closely with analysts and subject matter experts to prepare rigorous, time-consuming regulatory and client-specific reports. These teams depended largely on manual data preparation, disparate approaches, and a variety of tools to identify equipment malfunctions and changes in treatment system conditions.

ERM recognized that by automating reporting and analysis processes, teams across the entire organization could learn faster, connected systems would benefit from the interactions of subject matter experts, and teams could distribute their in-demand knowledge across the enterprise.

Within two months of project initiation, the ERM project team was using data from the system to make field maintenance decisions. These included in-depth data reviews, evaluations and critical maintenance decisions, reducing the decision-making process from two weeks down to a single day. TwinThread Learning Factory's scalable and democratized insights resulted in ERM's ability to take immediate and corrective action, reducing the time required to compile reports and analysis by approximately 30%. The application of machine learning and predictive analytics enables the ERM team to make proactive maintenance decisions for increased system uptime and reduced compliance risks.