Semantic Enrichment for BIM
SeeBridge meeting @ Technion
March, 2017
WP4 Review
Virtual Construction Lab
What is semantic enrichment in SeeBridge
© 2017, Dr. Ling Ma
WP4 in the SeeBridge
Requirement of the enrichment result
Produce feature-based enrichment rules
Algorithm for identification of model features and rule-based model processing
© 2017, Dr. Ling Ma
MVD development
Mapping entities
Mapping properties
Mapping constraints
© 2017, Dr. Ling Ma
Rule engine of SeeBIM 1.0
Rules:
- IF a & b -> X
- IF b & c -> Y
Advantage:
- No computer programing skill is required
Disadvantage:
- Lack of rigor
Fact:
IF a & b & c -> ?
© 2017, Dr. Ling Ma
SeeBIM 2.0
| Features | F1 | F2 | F3 | F4 | F5 | F6 |
|---|---|---|---|---|---|---|
| Type A | y | y | x | y | n | n |
| Type B | n | n | y | x | y | n |
| Type C | y | y | n | y | x | n |
| Type D | n | n | y | y | y | x |
- ‘y’:= Yes
- ‘n’:= No
- ‘x’:= Not always
Find the 'unique' string (skip the comparison with ambiguous 'x' )
| y | n | y | x | n |
| y | x | y | y | n |
Not unique
© 2017, Dr. Ling Ma
SeeBIM 2.0 - pairwise
Physical contact ?
Orthogonality
Length comparison
Width comparison
Elevation comparison
...
Find the 'unique' string (skip the comparison with ambiguous 'x' )
- ‘y’:= Yes;
- ‘n’:= No;
- ‘x’:= Not always;
| y | n | y | x | n |
| y | x | y | y | n |
Not unique
© 2017, Dr. Ling Ma
SeeBIM 2.0 - an example rule set for bridge object classification
Sacks, R., L. Ma, R. Yosef, A. Borrmann, S. Daum. and U. Kattel, Enhancement of a Semantic Enrichment Tool for Building Information Modeling. Journal of Computing in Civil Engineering, under review.
© 2017, Dr. Ling Ma
SeeBIM 2.0 - another thought
| Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | |
| Type A | n | y | X | n | y |
| Type B | n | y | y | n | y |
- ‘y’:= Yes;
- ‘n’:= No;
- ‘x’:= Not always;
Rules:
Fact:
| Obj 1 | n | y | y | n | y |
| Obj 2 | n | y | n | n | y |
PB>PA
PA>PB
© 2017, Dr. Ling Ma
Feature Matching
| Longitudinal | Transverse | Vertical | Convex | ... | |
| Primary Girder | 1 | -1 | -1 | -1 | |
| Transverse Beam | -1 | 1 | -1 | 1 | |
| ... |
Primary Girder = (1,-1,-1,-1)
| Longitudinal | Transverse | Vertical | Convex | |
| Object 1 | -1 | 1 | -1 | 1 |
| Object 2 | 1 | -1 | -1 | -1 |
| Object 3 | 1 | -1 | -1 | 1 |
Object 1 = (-1,1,-1,1)
| Primary Girder | Transverse Beam | |
| Object 1 | 180 degree | 0 degree |
| Object 2 | 0 degree | 180 degree |
| Object 3 | 60 degree | 90 degree |
© 2017, Dr. Ling Ma
Pairwise Feature Matching
| f1 | f2 | f3 | |
|---|---|---|---|
| E1,E1 | 1 | 1 | 1 |
| E1,E2 | -1 | 0 | 0 |
| E1,E3 | -1 | -1 | 0 |
| E2,E1 | 0 | 0 | 0 |
| E2,E2 | 1 | 1 | 0 |
| E2,E3 | 0 | 0 | -1 |
| E3,E1 | -1 | -1 | -1 |
| E3,E2 | 0 | -1 | 0 |
| E3,E3 | 0 | 0 | -1 |
| f1 | f2 | f3 | |
|---|---|---|---|
| O1,O2 | 1 | 1 | 1 |
| O1,O3 | -1 | 1 | -1 |
| O1,O4 | -1 | -1 | 1 |
| O1,O5 | 1 | 1 | 1 |
| O2,O1 | 1 | 1 | 1 |
| O2,O3 | -1 | -1 | 1 |
| O2,O4 | 1 | 1 | 1 |
| O2,O5 | 1 | 1 | 1 |
| O3,O1 | 1 | 1 | 1 |
| O3,O2 | -1 | -1 | 1 |
| O3,O4 | -1 | -1 | 1 |
| O3,O5 | 1 | 1 | -1 |
| O4,O1 | 1 | 1 | -1 |
| O4,O2 | 1 | 1 | -1 |
| O4,O3 | -1 | -1 | -1 |
| O4,O5 | -1 | -1 | 1 |
| O5,O1 | -1 | 1 | -1 |
| O5,O2 | -1 | 1 | -1 |
| O5,O3 | -1 | 1 | -1 |
| O5,O4 | 1 | -1 | 1 |
3 types of bridge elements (e.g., girder, sheer key etc.)
5 objects in the model
3 types of features
| E1,E1 | E1,E2 | E1,E3 | E2,E1 | E2,E2 | E2,E3 | E3,E1 | E3,E2 | E3,E3 | |
|---|---|---|---|---|---|---|---|---|---|
| O1,O2 | 1 | 3 | -3 | 1 | -5 | 2 | -3 | 2 | 1 |
| O1,O3 | -5 | 1 | -3 | 2 | -3 | -3 | 2 | 2 | -2 |
| O1,O4 | -2 | 3 | -3 | 5 | 3 | -1 | -5 | -2 | -2 |
| O1,O5 | -1 | 5 | 1 | 5 | 2 | 1 | 3 | 2 | 1 |
| O2,O1 | -3 | 4 | 2 | 0 | 1 | -1 | -4 | 3 | -5 |
| O2,O3 | -1 | 3 | 5 | -5 | 0 | 0 | -3 | 4 | -2 |
| O2,O4 | 1 | 3 | -4 | 4 | 0 | 4 | -1 | 5 | -5 |
| O2,O5 | -5 | -2 | -1 | 0 | 1 | 3 | 2 | 0 | 1 |
| O3,O1 | -3 | 5 | 0 | -2 | -3 | 1 | 5 | -1 | 5 |
| O3,O2 | 4 | 1 | -2 | 3 | -2 | 3 | 1 | 0 | -1 |
| O3,O4 | -2 | 5 | -2 | 0 | -5 | 4 | 5 | 2 | -2 |
| O3,O5 | -2 | -5 | -4 | 3 | -2 | -3 | 1 | 1 | -2 |
| O4,O1 | -4 | 1 | 0 | -4 | 4 | -5 | -5 | 1 | -4 |
| O4,O2 | 5 | 2 | 5 | -5 | 3 | -4 | -4 | -2 | -5 |
| O4,O3 | -5 | 0 | 3 | 1 | 4 | -1 | 2 | 5 | 1 |
| O4,O5 | -1 | -3 | 3 | -5 | 3 | 2 | -5 | -5 | -5 |
| O5,O1 | 1 | 5 | 2 | 5 | 1 | 5 | 0 | 0 | 1 |
| O5,O2 | -3 | -4 | 0 | 4 | 5 | 0 | 1 | -4 | 2 |
| O5,O3 | -5 | 0 | 5 | 3 | -1 | 4 | 2 | 4 | 2 |
| O5,O4 | 3 | 5 | -5 | 5 | 1 | -4 | -1 | 3 | 2 |
obj1?=element1
2n(m-1) relations
m : n
© 2017, Dr. Ling Ma
Experiement
© 2017, Dr. Ling Ma
SeeBIM 3.0
Machine learning:
Classifier: 3 * Feature1 ^ Feature2 + Feature3 / Feature4
| Feature1 | Feature2 | Feature3 | Feature4 | Type | |
| Obj 1 | 1 | 0 | 20.5 | a | Type A |
| Obj 2 | -1 | 1 | 40 | b | Type B |
| Feature1 | Feature2 | Feature3 | Feature4 | Type | |
| Obj 1,001 | ... | ... | ... | ... | Type ? |
| Obj 1,002 | ... | ... | ... | ... | Type ? |
© 2017, Dr. Ling Ma
SeeBIM 4.0?
| Object | Type |
| Obj 1 | Type A |
| Obj 2 | Type B |
| Obj 3 | Type C |
Deep learning:
| Object | Type |
| Obj 10,001 | Type ? |
| Obj 10,002 | Type ? |
| Obj 10,003 | Type ? |
© 2017, Dr. Ling Ma
Enrichment of other information
© 2017, Dr. Ling Ma
Supplementing information:
- Bridge grids
- Span
- Assembly
Filling in missing objects or fixing their shape caused by occlusion. such as:
- Bearings
- Girders
- Transverse beams
Demo
© 2017, Dr. Ling Ma
Demo 2
© 2017, Dr. Ling Ma
Enhancement of the Semantic Enrichment Engine
Dr. Ling Ma
Technion - Faculty of Civil and Environmental Engineering
SeeBridge WP4 Mid-term Report
Georgia Tech
Additional Data
© 2016, Dr. Ling Ma
Manual input & load from other source
Enhanced Geometry and Spatial Feature
© 2016, Dr. Ling Ma
Spatial Relationship Matrix
© 2016, Dr. Ling Ma
Transverse beam & Abutment
Uniqueness Checking
© 2016, Dr. Ling Ma
Element pairs are unique in terms of the relational features are unique
Other Attempts
© 2016, Dr. Ling Ma
Rule-based object identification
Similarity by feature matching
(Determinate result)
(Result with confidence)
Run-time file enrichment
Document-oriented database
Schema-free BIM model
Cloud service
(Deliver a model)
(Information sharing and collaboration)
The Root of Object Identification
© 2016, Dr. Ling Ma
Feature Matching
© 2016, Dr. Ling Ma
| Longitudinal | Transverse | Vertical | Convex | ... | |
| Primary Girder | 1 | -1 | -1 | -1 | |
| Transverse Beam | -1 | 1 | -1 | 1 | |
| ... | 0 |
Primary Girder = (1,-1,-1,-1)
| Longitudinal | Transverse | Vertical | Convex | |
| Object 1 | -1 | 1 | -1 | 1 |
| Object 2 | 1 | -1 | -1 | -1 |
| Object 3 | 1 | -1 | -1 | 1 |
Object 1 = (-1,1,-1,1)
| Primary Girder | Transverse Beam | |
| Object 1 | 180 degree | 0 degree |
| Object 2 | 0 degree | 180 degree |
| Object 3 | 60 degree | 90 degree |
Pairwise Features
© 2016, Dr. Ling Ma
Closer to the transverse ?
Pairwise feature matrix
Pairwise Feature Matching
© 2016, Dr. Ling Ma
| f1 | f2 | f3 | |
|---|---|---|---|
| E1,E1 | 1 | 1 | 1 |
| E1,E2 | -1 | 0 | 0 |
| E1,E3 | -1 | -1 | 0 |
| E2,E1 | 0 | 0 | 0 |
| E2,E2 | 1 | 1 | 0 |
| E2,E3 | 0 | 0 | -1 |
| E3,E1 | -1 | -1 | -1 |
| E3,E2 | 0 | -1 | 0 |
| E3,E3 | 0 | 0 | -1 |
| f1 | f2 | f3 | |
|---|---|---|---|
| O1,O2 | 1 | 1 | 1 |
| O1,O3 | -1 | 1 | -1 |
| O1,O4 | -1 | -1 | 1 |
| O1,O5 | 1 | 1 | 1 |
| O2,O1 | 1 | 1 | 1 |
| O2,O3 | -1 | -1 | 1 |
| O2,O4 | 1 | 1 | 1 |
| O2,O5 | 1 | 1 | 1 |
| O3,O1 | 1 | 1 | 1 |
| O3,O2 | -1 | -1 | 1 |
| O3,O4 | -1 | -1 | 1 |
| O3,O5 | 1 | 1 | -1 |
| O4,O1 | 1 | 1 | -1 |
| O4,O2 | 1 | 1 | -1 |
| O4,O3 | -1 | -1 | -1 |
| O4,O5 | -1 | -1 | 1 |
| O5,O1 | -1 | 1 | -1 |
| O5,O2 | -1 | 1 | -1 |
| O5,O3 | -1 | 1 | -1 |
| O5,O4 | 1 | -1 | 1 |
3 types of bridge elements (e.g., girder, sheer key etc.)
5 objects in the model
3 types of features
| E1,E1 | E1,E2 | E1,E3 | E2,E1 | E2,E2 | E2,E3 | E3,E1 | E3,E2 | E3,E3 | |
|---|---|---|---|---|---|---|---|---|---|
| O1,O2 | 1 | 3 | -3 | 1 | -5 | 2 | -3 | 2 | 1 |
| O1,O3 | -5 | 1 | -3 | 2 | -3 | -3 | 2 | 2 | -2 |
| O1,O4 | -2 | 3 | -3 | 5 | 3 | -1 | -5 | -2 | -2 |
| O1,O5 | -1 | 5 | 1 | 5 | 2 | 1 | 3 | 2 | 1 |
| O2,O1 | -3 | 4 | 2 | 0 | 1 | -1 | -4 | 3 | -5 |
| O2,O3 | -1 | 3 | 5 | -5 | 0 | 0 | -3 | 4 | -2 |
| O2,O4 | 1 | 3 | -4 | 4 | 0 | 4 | -1 | 5 | -5 |
| O2,O5 | -5 | -2 | -1 | 0 | 1 | 3 | 2 | 0 | 1 |
| O3,O1 | -3 | 5 | 0 | -2 | -3 | 1 | 5 | -1 | 5 |
| O3,O2 | 4 | 1 | -2 | 3 | -2 | 3 | 1 | 0 | -1 |
| O3,O4 | -2 | 5 | -2 | 0 | -5 | 4 | 5 | 2 | -2 |
| O3,O5 | -2 | -5 | -4 | 3 | -2 | -3 | 1 | 1 | -2 |
| O4,O1 | -4 | 1 | 0 | -4 | 4 | -5 | -5 | 1 | -4 |
| O4,O2 | 5 | 2 | 5 | -5 | 3 | -4 | -4 | -2 | -5 |
| O4,O3 | -5 | 0 | 3 | 1 | 4 | -1 | 2 | 5 | 1 |
| O4,O5 | -1 | -3 | 3 | -5 | 3 | 2 | -5 | -5 | -5 |
| O5,O1 | 1 | 5 | 2 | 5 | 1 | 5 | 0 | 0 | 1 |
| O5,O2 | -3 | -4 | 0 | 4 | 5 | 0 | 1 | -4 | 2 |
| O5,O3 | -5 | 0 | 5 | 3 | -1 | 4 | 2 | 4 | 2 |
| O5,O4 | 3 | 5 | -5 | 5 | 1 | -4 | -1 | 3 | 2 |
obj1?=element1
2n(m-1) relations
m : n
© 2016, Ling Ma
Matching Result
Similarity Instead of Determinate Result
| O1 | E1 | E3 | E2 |
| O2 | E2 | E1 | E2 |
| O3 | E2 | E1 | E3 |
| O4 | E2 | E1 | E3 |
| O5 | E1 | E3 | E2 |
| 1st Candidate | 2nd Candidate | 3rd Candidate |
Conclusion
© 2016, Dr. Ling Ma
Machine learning for more complex cases
Tested on synthetic cases
Semantic Enrichment for Bridges
SeeBridge WP4 Mid-term Report
Georgia Tech
Dr. Ling Ma
Technion - Faculty of Civil and Environmental Engineering
Why Enrichment is Important to BIM
© 2016, Dr. Ling Ma
Enrichment Tasks
© 2016, Dr. Ling Ma
© 2016, Dr. Ling Ma
Why Enrichment is Important in SeeBridge
© 2016, Dr. Ling Ma
Role in the SeeBridge
Requirement of the enrichment result
Produce feature-based enrichment rules
Algorithm for identification of model features and rule-based model processing
MVD Development Discussion
Technion + TUM + buildingSMART + AEC 3
Dr. Ling Ma
Technion - Faculty of Civil and Environmental Engineering
© 2016, Dr. Ling Ma
Workflow
-
Method: mvdXML
- Object typing
- Property/Quantity sets
- Exchange requirements
- Relationship?
-
Tool: IFCDoc
- App for mvdXML dev
- Concept rule checking?
- Documentation
IDM development
MVD development
- SeeBridge element types
- Physical elements
- Spatial elements
- Defects elements
- Property sets of elements
- Element relationships
- Composition
- Containment
- Grouping
- Info Exchange Requirements
Object Typing
IfcTypeObject
TypeEnum
- Share PropertySet
- Complex rules
- 2 PredefinedType
- USERDEFINED in TypeObject
- NOTDEFINED / $ in Object
- ElementType in TypeObject
- 2 PredefinedType
- Not all the element has type object
- IfcSurfaceFeature (defect)
- no Type
- has TypeEnum
- IfcSurfaceFeature (defect)
- Binding to Object (e.g. IfcBeam)
© 2016, Dr. Ling Ma
Bridge Element Property Set
- Define the property set for bridge elements and element types
Element Type
Element Family
Element Property Set
Element Property
© 2016, Dr. Ling Ma
Bridge Element Typing
- Select appropriate object types for bridge elements
and many more...
?
© 2016, Dr. Ling Ma
Property/Quantity Set Definition
Concept Rule on TypeEnum
- QuantitySet of PredefinedType
- PropertySet of PredefinedType
© 2016, Dr. Ling Ma
Exchange Requirement
Mandatory in both import & export
Existence:
- Property/Quantity Set of PredefinedType ?
- Property/Quantity in PropertySet (not $)?
<TemplateRules operator="and">
<TemplateRule Parameters="PredefinedType=GIRDER;PropertySetName=Pset_SeeBridgeGirderPropertySet;Properties=IfcPropertySingleValue;SingleValuePropertyName=P_SeeBridgeGirderProperty1;SingleValue=IfcText;" />
<TemplateRule Parameters="PredefinedType=GIRDER;PropertySetName=Pset_SeeBridgeGirderPropertySet;Properties=IfcPropertyBoundedValue;BoundedValuePropertyName=P_SeeBridgeGirderProperty2;SetPointValue=IfcReal;" />
<TemplateRule Parameters="PredefinedType=GIRDER;PropertySetName=Pset_SeeBridgeGirderPropertySet;Properties=IfcPropertyEnumeratedValue;EnumerationValuePropertyName=P_SeeBridgeGirderProperty3;EnumerationValue=IfcText;" />
</TemplateRules>
© 2016, Dr. Ling Ma
MVD Documentation (Deliverable)
© 2016, Dr. Ling Ma
Thanks!
SeeBridge Status Report
MVD Develement
Dr. Ling Ma
Technion - Faculty of Civil and Environmental Engineering
© 2016, Ling Ma
Content in IDM
- List the bridge element types
- Define the property sets of the bridge elements
- Identify the composition, connectivity, grouping relationships among the physical and conceptual bridge elements
- List the bridge defect types and property sets
- Specify the exchange requirements for these information items (Mandatory, optional, N/A)
© 2016, Ling Ma
Bridge Element Typing
- Select appropriate object types for bridge elements
and many more...
?
© 2016, Ling Ma
Bridge Element Property Set
- Define the property set for bridge elements and element types
Element Type
Element Family
Element Property Set
Element Property
© 2016, Ling Ma
Bridge Element Relationship
- Aggregation (IfcRelAggregates)
- element composition: physical element <> physical elements/parts
- spatial composition: spatial element <> subspace
- Spatial Container (IfcRelContainedInSpatialStructure
- spatial container <> physical elements
- Grouping (IfcRelAssignsToGroup)
- system <> subsystems
© 2016, Ling Ma
Damage Typing
- IsDeclaredBy
- IsDefinedBy
- Decomposes
A physical element instance
A property set
An element type
© 2016, Ling Ma
Work items
- Mapping bridge elements in IDM to Ifc type objects
- Convert the property set in IDM to Ifc format
- Mapping the relationship and conceptual elements to IFC elements
- Define the constraints on information items in MVD
SeeBridge Status Report
Enrichment Engine
Dr. Ling Ma, Uri Kattel, Raz Yosef
Technion - Faculty of Civil and Environmental Engineering
© 2016, Ling Ma
Shape Matching
© 2016, Ling Ma
Operators
- Dimension: [x,y,z]
- Axis: [[x1,y1,z1],[x2,y2,z2],[x3,y3,z3]]
-
Viewpoint coordinate system
- Origin: [x,y,z]
- Orientation: [[x1,y1,z1],[x2,y2,z2],[x3,y3,z3]]
- Topology:
- Touch: Boolean
- Disjoint: Boolean
- Euclidean Relation: [Left?,Right?,Above?,Below?]
© 2016, Ling Ma
Operators
Near
Overlap
Touch
© 2016, Ling Ma
Operators
- Three beams in the model
- Two are non-axis-aligned
- Get the dimensions
- Get the orientations
© 2016, Ling Ma
Operators
Wider
Perpendicular
Parallel
Longer
Bigger
© 2016, Ling Ma
Inference Rule
© 2016, Ling Ma
Domain Knowledge
| A | B | C | D | E | |
|---|---|---|---|---|---|
| A | 0 | 3 | 0 | 2 | 1 |
| B | 2 | 0 | 0 | 3 | 1 |
| C | 0 | 0 | 0 | 0 | 4 |
| D | 1 | 4 | 0 | 0 | 0 |
| E | 1 | 2 | 4 | 0 | 0 |
Matrix 1: Perpendicular
| A | B | C | D | E | |
|---|---|---|---|---|---|
| A | 0 | 0 | 1 | 0 | 0 |
| B | 0 | 0 | 1 | 0 | 0 |
| C | 2 | 1 | 0 | 2 | 0 |
| D | 0 | 0 | 1 | 0 | 2 |
| E | 0 | 0 | 0 | 2 | 0 |
Matrix 2: Parallel
| A | B | C | D | E | |
|---|---|---|---|---|---|
| A | 0 | 1 | 4 | 1 | 2 |
| B | 0 | 0 | 0 | 3 | 1 |
| C | 0 | 0 | 0 | 3 | 4 |
| D | 0 | 0 | 0 | 0 | 2 |
| E | 0 | 0 | 0 | 0 | 0 |
Matrix 3: Above
Rating score of being the determinant relationship for identifying A
© 2016, Ling Ma
Truth
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 1 | 0 | 0 | 1 | 0 | 0 | 1 |
| 2 | 0 | 0 | 1 | 0 | 1 | 0 | 1 | |
| 3 | 0 | 0 | 1 | 1 | 0 | 1 | ||
| 4 | 0 | 0 | 1 | 0 | 0 | |||
| 5 | 0 | 1 | 1 | 0 | ||||
| 6 | 0 | 1 | 0 | |||||
| 7 | 0 | 0 | ||||||
| 8 | 0 |
Matrix 1: Perpendicular
Matrix 3: Above
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 0 | 1 | 1 | 0 | 0 | 0 | 1 |
| 2 | 1 | 0 | 0 | 1 | 0 | 1 | 0 | 1 |
| 3 | 0 | 0 | 0 | 0 | 1 | 1 | 0 | 1 |
| 4 | 0 | 0 | 0 | 0 | 0 | 1 | 0 | 0 |
| 5 | 1 | 0 | 0 | 1 | 0 | 1 | 1 | 0 |
| 6 | 1 | 0 | 0 | 1 | 0 | 0 | 1 | 0 |
| 7 | 0 | 0 | 1 | 0 | 0 | 0 | 0 | 0 |
| 8 | 0 | 0 | 0 | 0 | 1 | 0 | 1 | 0 |
© 2016, Ling Ma
Matching of Relations
| 1 |
|---|
| 2 |
| 3 |
| 4 |
| 5 |
| 6 |
| 7 |
| 8 |
| A |
|---|
| B |
| C |
| D |
| E |
Element A's Feature
© 2016, Ling Ma
Work items
- Test the operators on bridge model provided by WP3
- Complete the relationship matrices
- Develop the matching algorithm
SeeBIM 2.0 : a Cloud-based Platform for Information Collaboration on BIM model
SeeBridge Workshop @ Cambridge
Dr. Ling Ma
Technion - Faculty of Civil and Environmental Engineering
ionlny0irvononeinyhSnfrctuoeao1eTvcopuirU2tatHbgienongesngrhd5eilzgeg9nlayne1rsfdiec
Technology global 2015 engineering University...
Huazhong University of Science and Technology ranked top 19 global university for engineering in 2015
Huazhong University of Science and Technology ranked top 19 global university for engineering in 2015
Goal?
(Rank by US news 2015 and Thomson Reuters)
© 2015, Dr. Ling Ma
Previous work
© 2015, Dr. Ling Ma
Previous work
SeeBIM
Michael Belsky, PhD, “A FRAMEWORK FOR SEMANTIC ENRICHMENT OF IFC MODELS”, Civil and Env. Eng., Technion. 2015
© 2015, Dr. Ling Ma
© 2015, Dr. Ling Ma
Previous work
Ease the information retrieval
SeeBIM
Michael Belsky, PhD, “A FRAMEWORK FOR SEMANTIC ENRICHMENT OF IFC MODELS”, Civil and Env. Eng., Technion. 2015
Extend the schema
© 2015, Dr. Ling Ma
Horizontal/Vertical Element ? ->
bounding box ->
major axis ->
parallel/perpendicular to the ground
© 2015, Dr. Ling Ma
Previous work
Rationalize Domain Knowledge
Ease the information retrieval
SeeBIM
Michael Belsky, PhD, “A FRAMEWORK FOR SEMANTIC ENRICHMENT OF IFC MODELS”, Civil and Env. Eng., Technion. 2015
Extend the operand and operator
Extend the schema
© 2015, Dr. Ling Ma
SeeBIM 2.0
© 2015, Dr. Ling Ma
© 2015, Dr. Ling Ma
As-damaged model
© 2015, Dr. Ling Ma
© 2015, Dr. Ling Ma
© 2015, Dr. Ling Ma
© 2015, Dr. Ling Ma
© 2015, Dr. Ling Ma
Next?
© 2015, Dr. Ling Ma
©2016, Dr. Ma, Ling
- Develop domain ontology for bridge inspection
- Upload BIM model, query data
- Develop APIs
You can join us
© 2015, Dr. Ling Ma
Semantic Enrichment for Bridges
Dr. Ling Ma
Technion - Faculty of Civil and Environmental Engineering
© 2016, Dr. Ling Ma
Conditions of the Highway Bridges
One in nine of the bridges in the US are structurally deficient
FHWA needs $20.5 billion annually to eliminate the bridge deficient backlog by 2028, but $12.8 billion is being spent
Numbers from 2013 ASCE report card for America's infrastructure
607,380 National Bridges in the US !!!
Over two billion trips are taken daily across these bridges
© 2016, Dr. Ling Ma
Bridge Inspection - Current Practice
14,700 bridges in Georgia
42 Inspectors in GDOT
Descriptive Inspection Report
AASHTOWare Bridge Management System (BMS)
| Good? |
| Satisfactory? |
| Desirable? |
Bridge Risk Prediction
© 2016, Dr. Ling Ma
Bridge Management System
3D Semantically rich bridge model (Bridge Information Model)
+
=
McGuire, B., et al., (2016) Bridge Information Modeling for Inspection and Evaluation. Journal of Bridge Engineering
Average age: 42 years
Numbers from 2013 ASCE report card for America's infrastructure
Time consuming
Infravation - SeeBridge
© 2016, Dr. Ling Ma
© 2016, Dr. Ling Ma
Data Collection
Videogrammetry
(GoPro4 black)
Mobile laser scanning
(Trimble MX7)
Terrestrial laser scanning
(Leica c10)
© 2016, Dr. Ling Ma
Georgia (3)
Data Collection
Cambridge (10)
Haifa (1)
3D Reconstruction
© 2016, Dr. Ling Ma
Semantic Enrichment
© 2016, Dr. Ling Ma
Bridge Defects
© 2016, Dr. Ling Ma
