Asset Performance Prediction Solution employed to Increase Uptime of an Offgas Compressor at a Major Petrochemical Group in India

Business Objective:

To increase Uptime of an Offgas Compressor and derive more value from existing expensive assets at a Major Petrochemical Group in India

A large Petrochemical Group in India turned to Lummus Digital to solve the various problems associated with its Offgas Compressors and wanted to increase their uptime. By doing so, the Petrochemical Group wanted to derive more value out of its existing expensive assets, improve reliability and efficiency, and minimize the costs associated with the running of its equipment. The business objectives would address:

  • Frequent failure of Offgas Compressors leading to unplanned downtime and production loss
  • Costly and time-consuming maintenance activities
  • Hard to identify root cause of the of problems – whether process or equipment

Key Solution:

  • Anomaly Detection: Using supervised and unsupervised machine learning, anomalies were detected, as well as other contributing factors that were responsible for the anomalous behavior of the equipment
  • Root Cause Identification: Performing root cause analysis of the contributing factors led to the equipment part/system and generated corresponding alerts. Further, controlled variables in a data-driven Failure Mode and Effect Analysis (FMEA) of equipment, and the application of Data Science were utilized to ascertain the same
  • Prediction of Failures Ahead of Occurrence: By using deep learning Long Short-Term Memory (LSTM) of the networks, prediction of anomalies, and remaining time before equipment failure were made possible
  • Best Optimal Solution Recommendation: Conducting “what-if”  analysis for failure mitigation/repair management resulted in recommending the most appropriate solution

Business Impacts & Outcomes:

  • By predicting an early compressor failure, way ahead of its occurrence, the Solution helped the Petrochemical Group steer clear of unplanned shutdown and avoid production loss amounting to an Avg. $1.2 Mil/yr
  • Reduced maintenance costs : Avg. $0.25 Mil/yr
  • Reduced cost of safety incidents
  • Improved life of equipment as well as reduced labor and spare parts OPEX

Business Impacts & Outcomes:

  • Reduced unplanned downtime, resulting in savings of millions of dollars due to production loss
  • Improved health of equipment as well as improved reliability of the plant

Remote Plant Monitoring System for a Large Petrochemicals Manufacturer

Business Objective

Remotely monitor real-time health of the various systems in the plant

Key Solution

  • Built a virtual plant as a digital replica of the real plant
  • Enabled monitoring of plant health in real-time with key KPIs, equipment condition and parameters operating range
  • Detailed monitoring of all the systems within the plant – feedstock, cracking, storage, polymerization, bagging, utilities etc.
  • The solution diagnosed the problem of equipment with bad health or those operating at off-limit parameters; identified the root cause and recommended actions, enabling the operator to take quick and valuable plant floor level decisions

Business Impacts & Outcomes

  • Improved production and yield
  • Reduced energy consumption
  • Improved uptime of plant and assets
  • Maximized operational life of plant assets

Business Impacts & Outcomes:

  • Improved production and yield
  • Reduced energy consumption
  • Improved uptime of plant and assets
  • Maximized operational life of plant assets