Advanced Analytics for Process Experts: Accelerate Root Cause Analysis & Improve Data-Driven Decision Making

The process and manufacturing industry has seen a rise in industry 4.0 digitalization efforts over the past decade. With these efforts, however, come several challenges such as the complexity of handling mass amounts of data and, more importantly, making sense of that data in order to gain quick, actionable insights to increase plant reliability and safety and improve data-driven decision making. Daily activities for engineers and operators such as troubleshooting equipment and process optimization can take hours to months, depending on the complexity. Engineers spend too much of their time stretching the limits of MS Excel trying to acquire and prepare data and visualize the problem, instead of actually analyzing the problem and gaining crucial insights from it. Additionally, data scientists may also be involved in solving process and manufacturing challenges, which can also create bottlenecks within the organization.

Self-service analytics overcomes these challenges by providing engineers and operators new and efficient methods to solve simple and complex problems efficiently. Users have a visual interface and actionable dashboards showing their time-series data in a recognizable format so they can monitor operational performances in real-time and use their subject matter expertise to find ways to improve process performance and even predict required maintenance. Self-service analytics also allows contextual information from 3rd party applications/sources to be pulled in so there is much better visibility into operations.

In this presentation, we will demonstrate how by deploying self-service analytics tooling, engineers and operators who are intimately involved in the process are not only able to diagnose the root cause of process issues, but also take corrective action in a timely manner. This directly impacts the organization’s bottom line by reducing time to action, optimizing the process, improving cycle time, avoiding unplanned shutdown and maintenance, mitigating safety risks, and more.

Two of the use cases that will be presented will reflect the easy-to-use functionality and the tangible success derived from self-service analytics capabilities. The first case involves heat exchanger efficiency and how predicting fouling can improve cycle time, equipment life, and reduce risk of safety hazards. The second case involves the manual start up of a compressor that has high probability of failure, resulting in time lost, wear and tear, and unplanned maintenance. The gained benefits for utilizing self-service analytics include extended asset availability, predictive maintenance leading to operational and maintenance cost reduction and reduction of safety risk.