Copyright 2012 Data-Driven Facility Management CIFE TAC 2014 1 Uncovering Best Practices for Data-Driven Energy Management and Facility Maintenance PIs: Professors Martin Fischer and Michael Lepech Research Staff: Amir Kavousian, Pat Shiel, Jasmine Wei
Uncovering Best Practices for Data-Driven Facilities Energy Management
Jun 23, 2015
Energy costs represent about 20% of total operating expenditures for office buildings. Our case studies of more than fifty buildings have demonstrated that savings of up to 54% are achievable with very little capital investment and little to no distraction for building occupants. As with any mechanical system, building systems performance decline with time and require regular maintenance to work as expected. However, there is no established literature on optimal maintenance strategy based on real performance data from real world projects. Using performance and asset data from our industry partners, we propose to examine the impacts of building systems maintenance on building performance. Additionally, we will identify processes by which the design and construction phases of the project can contribute to implementing optimal facility maintenance strategies.
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 20141
Uncovering Best Practices for Data-Driven Energy Management and Facility Maintenance
PIs: Professors Martin Fischer and Michael LepechResearch Staff: Amir Kavousian, Pat Shiel, Jasmine Wei
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 20142
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Maintenance, operation, and utility costs of a facility over its life cycle ~ the initial costs of the facility1.
3
1 Stanford Land and Buildings Department (2005)2 Whitestone (2013)
Maintenance costs of rooftop HVAC systems ~ $0.45/sqft per year2.
Unscheduled maintenance and repairs: 36% of total maintenance costs2.
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Effective maintenance can reduce HVAC energy costs by 5 to 40 percent1.
4
1 Institute for Building Efficiency (2013) Chart: US EPA (2012)
Energy 30%
Repairs & Maintenance
23%
Cleaning19%
Admin.18%
Other10%
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
HVAC system of a normal commercial building has 100+ components3. Keeping track of all pieces of equipment is not manageable manually.
5
3 Institute for Building Efficiency (2013)
Reactive maintenance (run-to-failure)
Preventive maintenance (scheduled)
Predictive maintenance
Can be very costly if problems are unnoticed.Comfort will be compromised.
Not cost- effective
Based on actual operations of HVAC, user comfort, historical trends, etc.
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Predictive maintenance has great potential, especially thanks to widespread use of Building Management Systems (BMS).
6
Institute for Building Efficiency (2013)
Reactive (run to failure)
55%
Preventive (scheduled)
31%
Predictive 14%
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Research questions (1/3)
7
Reactive maintenance (run-to-failure)
Preventive maintenance (scheduled)
Predictive maintenance Energy
consumption
User comfort
…
What are the impacts of different maintenance strategies on building performance, energy costs, and other operational factors?
?
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Research questions (2/3)
8
Predictive maintenance
?
What are the data infrastructure requirements for predictive maintenance? What can be done using existing infrastructure?
- Our intuition: a lot !!
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Research questions (3/3)
9
Predictive maintenance ?
What are the energy savings and return on investment from predictive maintenance?
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Comparison
10
Predictive maintenance
Automatic Fault Detection, FD
Different from automatic fault detection:Predictive maintenance is prospective, real time
tracking;FD is retrospective, periodically with time
intervals.
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Data sources: we will use existing sources of data in buildings and organizations.
11
Building mechanical systems
Building control systems
Building structural Systems and facade
Energy management practices
Occupant comfort reports
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Methods
• Statistical analysis of building performance, and correlating it with maintenance strategies
• – Efficiency score of building at time – Efficiency score of building at time – Cumulative volume of maintenance hours
performed on building up to time
12
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Example: uncovering energy management practices that contribute to efficiency improvement
13
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Deliverables (1/3)
14
Facility Maintenance Asset
Management Practices
Lifecycle Costs,
ROI
Occupant
Comfort
Energy, Carbon,
etc.
A technical report explaining the relationship between facility maintenance strategies and lifecycle costs and occupant comfort.
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Deliverables (2/3)
15
Facility Maintenance Asset
Management Practices
Data Infrastructu
re
In-house analytics
capabilities
Processes, milestones,
work breakdown
A set of best practices for implementing data-driven asset management and building systems maintenance.
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Deliverables (3/3)
16
Facility Maintenance Asset
Management Practices
Lifecycle Costs,
ROI
Occupant
Comfort
Energy, Carbon,
etc.
A framework for evaluating facility maintenance practices, using metrics such as ROI, lifecycle costs, and occupant comfort.
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Example: data-driven asset management framework
17
Machine Learning Method
Operation Data
Database
Decisions
Notice & Action
Devices Infrastructure
Notification & Action System
Smart Storage
Data Organization
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
CIFE Community Involvement
CIFE Partner Industry role as is related to this project
Potential Ways to Collaborate
Johnson Controls, Inc.
Energy efficiency products and services provider
- Collecting building systems data- Devising optimal maintenance strategies
DPR - General Contractor- Owner and facility manager
- Collecting design and construction data- Examining building performance data and how design and construction can help improve facility management operations
Microsoft Owner & Facility Manager
- Collecting operational data from buildings- Examining existing facility management operations and possible ways to improve them
General Services Administration (GSA)
Owner & Facility Manager
- Collecting operational data from buildings- Examining existing facility management operations and possible ways to improve them
Disney Imagineering
Owner & Facility Manager
- Collecting operational data from buildings- Examining existing facility management operations and possible ways to improve them18
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Benchmark buildings
Evaluate historical Energy
Conservation Measures (ROI, energy savings,
etc.)
Select optimization strategies based on
ROI analysis and historical ECM
analysis
Analyse individual buildings (retrofit
candidates)
Implement energy reduction strategies
Re-calibrate benchmarking
models
Population of buildings
Individual building analysis19
Impact: closing the loop on data-driven building energy management
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Research plan
20
Oct
‘14
Jan
‘15
Ap
r ‘1
5
Identify existing data
Collect additional data
Statistical analysis of data
Validate results by case studies
Report to CIFE partners
Research team & CIFE partnersResearch team
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Next steps
• Automated asset management and building systems
maintenance
– Automate the data collection and analysis for
building systems
– Integrate such processes into existing FM processes
• Failure prediction systems
• Feedback to design and construction processes
21
Copyright 2012
D a t a - D r i v e n Fa c i l i t y M a n a g e m e n t
CIFE TAC 2014
Q & A
Photo: Google/Connie Zhou
Related Documents
