Predictive maintenance Industry 4.0 - A Pump Manufacturer

A Pump Manufacturer wanted to get advanced alert on the state of the machines and their need for repair to avoid fatal accidents and mishaps.

Coreview used AI/ML to analyse the machine data and predict the potential failures, while alarming the warnings for immediate attention.

The Challenges

The key challenges were -

  • A Gas Pump can fail anytime without any warning, causing significant loss of production
  • Ability to predict any possibility of failure is critical
  • Silos data and Scale of the data – pumps, logs, environmental, SOPs etc
  • Parameters for pump failures are not well defined

Coreview’s Solution

CoreView built a solution with below features.

  • Analysis of existing dataset which consisted of 5000 pump’s historical operating data for the past 2 years.
  • Building a data model using Python/Spark/Cassandra pipeline
  • Advanced mathematical models based on time series forecasting and classifiers
  • Visualization of the results using D3 libraries.

The Results - Reduced Downtime with Huge Monthly Savings

This helped the company to bring a great customer experience with -

  • Real time monitoring and predictive failure analysis is expected to save 1500 hours of downtime resulting in savings of $100K per month.
  • Prescriptive recommendation for informed decision
  • 10 % reduction in downtime

10% reduction in downtime and huge monthly savings in maintenance

View All Case Studies

Book a Free Consultation

Success! Your message has been sent to us.
Error! There was an error sending your message.