Download PDF
C3 IoT > Case Studies > Enterprise AI for Predicting HVAC Chiller Failures: A Case Study
C3 IoT Logo

Enterprise AI for Predicting HVAC Chiller Failures: A Case Study

 Enterprise AI for Predicting HVAC Chiller Failures: A Case Study - IoT ONE Case Study
Technology Category
  • Analytics & Modeling - Machine Learning
  • Platform as a Service (PaaS) - Application Development Platforms
Applicable Industries
  • Education
  • Equipment & Machinery
Applicable Functions
  • Maintenance
Use Cases
  • Building Automation & Control
  • Predictive Maintenance
Services
  • Data Science Services
  • System Integration
The Challenge
The building systems division of a Fortune 500 manufacturer, which provides equipment and services for optimizing building energy expenditures, was facing a significant challenge. The division was conducting chiller maintenance reactively, leading to business disruptions, downtimes, and costly emergency repairs. This reactive approach was negatively impacting customer satisfaction. The manufacturer needed a solution that could rapidly integrate all relevant equipment and facility data sources. The goal was to reduce downtime and costly, unscheduled maintenance for its commercial Heating, Venting & Cooling (HVAC) chiller systems.
The Customer

Fortune 500 Manufacturing

About The Customer
The customer in this case study is the building systems division of a Fortune 500 manufacturer. This division provides equipment and services that optimize building energy expenditures, ensuring comfort for customers. The company is a global equipment manufacturer and services company with 100,000 employees and $30 billion in revenue. The company's primary objective was to load and cluster sensor data for use in a predictive model, train a machine learning model to predict chiller failure, and demonstrate the speed of development and deployment by completing the project in less than a week.
The Solution
To address these challenges, the manufacturer deployed C3 AI Reliability for 165 of its chillers. The customer chose C3 AI due to its proven ability to rapidly integrate sensor data, normalize and cluster disparate readings, and run machine learning algorithms to identify deteriorating conditions before failures occur. In just 4 days, C3 AI and the customer loaded, normalized, and mapped 3 years of sensor data for all 165 chillers. They created custom analytics on these data and configured a machine learning algorithm to predict chiller failure events. C3 AI Reliability exceeded the identified accuracy and precision targets.
Operational Impact
  • The deployment of C3 AI Reliability led to significant operational improvements. The manufacturer was able to rapidly integrate sensor data, normalize and cluster disparate readings, and run machine learning algorithms to identify deteriorating conditions before failures occur. This proactive approach to maintenance reduced business disruptions and downtimes, leading to improved customer satisfaction. The project was completed in less than a week, demonstrating the speed of development and deployment. The machine learning model achieved a precision of 73% and a recall of 71%, exceeding the identified accuracy and precision targets.
Quantitative Benefit
  • $178M annual benefit identified
  • Project completed in 4 weeks from receiving data to model delivery
  • Achieved 73% model precision

Related Case Studies.

Contact us

Let's talk!

* Required
* Required
* Required
* Invalid email address
By submitting this form, you agree that IoT ONE may contact you with insights and marketing messaging.
No thanks, I don't want to receive any marketing emails from IoT ONE.
Submit

Thank you for your message!
We will contact you soon.