Case study #1: SMART BUILDING AND HYDROPONICS

Key drivers by role

Tenant experience

  • World-Class High Tech For Best Yield​
  • Remote Management and Alerting​

Owner 

  • Adding Value to Facility​
  • Maturing facility management practices​
  • New data- and services-driven business models​
  • Smarter decisions about maintenance, ability to view big picture across portfolio of buildings​

Operation Management

  • Preventive, proactive, and reactive maintenance​
  • Remote Equipment management​, Energy management​

 

 

 

System Architecture

 

 

1. Challenge:

Fixed Schedule Maintenance is Inefficient
-Fixing the unnecessary things
-Critical assets fails before maintenance

 

2. Solution to explore:

Predictive Maintenance
-Monitor and fix what is strategic is needed

 

3. Requirement:

Techniques that monitor equipment in service
to predict the best tie for maintenance.

 

More IoT Analytics, more value

 

Machine Learning: anomaly detection

 

 


Case study #2: PREVENTIVE MAINTENANCE

Overview:

Predictive maintenance, the ability to use data-driven analytics to optimize connected assets upkeep, is one of the most valuable applications of IOT.

Predictive Maintenance enables businesses to increase the efficiency of maintenance related tasks by anticipating maintenance needs and avoiding unscheduled downtime through monitoring real time data from connected assets— e.g. Elevators , Aircraft Components, ATM Machines, Wind Turbines, Brake Disc etc.

Important qualification criteria include whether the problem is predictive in nature, that a clear path of action exists in order to prevent failures when they are detected beforehand and most importantly, data with sufficient quality to support the use case is available.

 

 

 

1.Challenge: Fixed Schedule Maintenance is Inefficient:

Predictive Maintenance.
Monitor and Fix what is strategic when is needed

2.Solution to Explore:

Predictive Maintenance.
Monitor and Fix what is strategic when is needed

3.Requirement:

Techniques that monitor equipment in-service to predict the best time for maintenance.

 

 


ROI Opportunities:

 

 

 

a) Predicting if a given component will fail or not before scheduled maintenance

Predicting the most likely causes of failure

 

b) Predicting when a component
will fail

Predicting the yield failure on a asset