Concept Learning in Engineering based on Refinement Operator 28th - - PowerPoint PPT Presentation

▶
concept learning in engineering based on
SMART_READER_LITE
LIVE PREVIEW

Concept Learning in Engineering based on Refinement Operator 28th - - PowerPoint PPT Presentation

Feb 25, 2023 145 likes •383 views

Concept Learning in Engineering based on Refinement Operator 28th International Conference on Inductive Logic Programming Yingbing Hua, Bjrn Hein Institute for Anthropomatics and Robotics Intelligent Process Control and Robotics (IAR-IPR)

slide-1
SLIDE 1

Institute for Anthropomatics and Robotics – Intelligent Process Control and Robotics (IAR-IPR)

KIT – The Research University in the Helmholtz Association

www.kit.edu

Concept Learning in Engineering based on Refinement Operator

28th International Conference on Inductive Logic Programming Yingbing Hua, Björn Hein

slide-2
SLIDE 2

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

Motivation

11/09/18 2

Semantic Interoperability between engineering systems Machine interpretation of user defined concepts “What does one target concept mean using the language of the source system?“

slide-3
SLIDE 3

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 3

AutomationML (IEC 62714)

AutomationML Topology Description Architecture (Schmidt, N. and Lüder, A., 2015)

KR5:Robot Kinect:Sensor KR5_01 Kinect_02 Actuator Robot Sensor RGBSensor IO DigitalIO AnalogIO

slide-4
SLIDE 4

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

AML models OWL Models Example role class class Robot Interface class class DigitalIOInterface system unit individual KR5 external interface individual digital_io_1 relationship

  • bject property

hasIE, hasEI attribute data property hasWeight

11/09/18 4

Semantic Lifting

Add semantic annotation in the OWL models to indicate their roles in CAEX (Runde et. al, 2009)

slide-5
SLIDE 5

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 5

Semantic Lifting – Example

attributes substructures …

slide-6
SLIDE 6

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 6

Semantic Lifting – Example

...

slide-7
SLIDE 7

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 7

Given the semantic representation of AML data, how can we learn a concept description of the data?

slide-8
SLIDE 8

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

Input:

Background knowledge 𝒧: lifted AML Target Concept name 𝐷 Examples (user chosen) ℰ: pos. and neg. Closed-world assumption

Output:

Class description of 𝐷 in OWL 2 DL: 𝒧 ∪ 𝐷 ⊨ ℰ+, 𝒧 ∪ 𝐷 ⊭ ℰ−

11/09/18 8

Concept Learning in AML – Setting

Source AML Target

slide-9
SLIDE 9

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

Framework for concept learning in description logics Top-down refinement operators

𝒝ℒ𝒟 (complete) ℇℒ (ideal) 𝒝ℒ𝒟 with features from OWL 2 DL: concrete roles, cardinality restrictions ...

Learning algorithms for OWL 2 DL:

DL-Learner OWL Class Expression Learner (OCEL) Class Expression Learner for Ontology Engineering (CELOE)

Partial Closed-World Reasoning

Instance retrieval of named classes before learning: a single model Closed-world reasoning using the single model much faster and more suitable in machine learning setting

11/09/18 9

DL-Learner (Bühmann et. al, 2016)

slide-10
SLIDE 10

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 10

Concept Learning in AML – Pipeline

slide-11
SLIDE 11

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 11

Extending the Refinement Operator

slide-12
SLIDE 12

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

Use knowledge in the XML schema to restrict the search space

① Only external interfaces can reference interface classes ② Each external interface can only reference one interface class ③ A system unit can reference multiple role classes ④ A system unit can have (recursive) internal structures ⑤ An external interface has no internal structure

Integrate these constraints into the refinement operator Implemented on top of DL-Learner Can dramatically reduce the number of concept hypotheses

11/09/18 12

Extending the Refinement Operator

slide-13
SLIDE 13

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 13

Extending the Refinement Operator

slide-14
SLIDE 14

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 14

Experiment Results – Performance

T1 T2 T3 T4 T5 default (b1) 0,781 2,38 109,66 136,625 default (b2) 0,704 5,333 184,86 109,9 aml (b1) 0,508 0,595 5,483 5,465 84,419 aml (b2) 0,451 0,8 9,243 8,792 105,779 20 40 60 80 100 120 140 160 180 200

Runtime (sec)

Benchmark 1 & 2

slide-15
SLIDE 15

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 15

Summary

✓Pipeline of concept learning in AML using DL-Learner ✓Extension of the default 𝒝ℒ𝒟 refinement operator ➢Application in data exchange ➢Investigate other semantic languages and refinement operators ➢Better searching algorithms ➢Self-adaptive heuristics (parameter learning) ➢Bottom-up approaches

slide-16
SLIDE 16

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

  • N. Schmid and A. Lüder, “AutomationML in a Nutshell”, November

2015.

  • M. Uschold, “Where are the semantics in the semantic web?” AI Mag.,
  • vol. 24, no. 3, Sept. 2003

AutomationML e.V., “Whitepaper AutomationML Part 1 – Architecture and general requirements”, July 2013.

  • S. Runde, K. Güttel and A. Fay, “Transformation von CAEX-

Anlagenplanungsdaten in OWL: Eine Anwendung von Technologien des Semantic Web,“ in Automation 2009, June 2009

  • L. Bühmann, J. Lehmann, and P. Westphal, „DL-Learner: A Framework

for Inductive Learning on the Semantic Web,“ Web Semantics, vol. 39,

  • Aug. 2016.

11/09/18 16

References

slide-17
SLIDE 17

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 17

Thank you for the attention! Any Questions?

slide-18
SLIDE 18

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 18

slide-19
SLIDE 19

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator

The Automation Mark-up Language International standard as IEC 62714 Data modeling and exchange in the field of production systems engineering and commissioning XML-based

11/09/18 19

AutomationML (AML)

slide-20
SLIDE 20

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 20

AutomationML (AML)

slide-21
SLIDE 21

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 21

We need a formal semantic representation of AML data for concept learning

slide-22
SLIDE 22

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 22

Concept Learning in AML – Example

𝑈 = 𝑆𝑝𝑐𝑝𝑢, 𝑇𝑓𝑜𝑡𝑝𝑠, 𝑈𝑝𝑝𝑚, … 𝑆 = {ℎ𝑏𝑡𝑄𝑏𝑧𝑚𝑝𝑏𝑒, ℎ𝑏𝑡𝐹𝑜𝑒𝐹𝑔𝑔𝑓𝑑𝑢𝑝𝑠, … } 𝐽𝑜𝑒𝐷1

+ 𝒝 = {𝑠1, 𝑠2, … }

𝑆𝑝𝑐𝑝𝑢 𝑠1 , 𝑆𝑝𝑐𝑝𝑢 𝑠2 , … 𝐷1 = 𝑆𝑝𝑐𝑝𝑢⨅ℎ𝑏𝑡𝐹𝑜𝑒𝐹𝑔𝑔𝑓𝑑𝑢𝑝𝑠. 𝐻𝑠𝑗𝑞𝑞𝑓𝑠

slide-23
SLIDE 23

ILP 2018 Yingbing Hua – Concept Learning in Engineering based on Refinement Operator 11/09/18 23

Experiments

Source AML document:

220 classes 497 individuals 73 data properties

Two benchmarks

+50 role classes, +25 interface classes +100 role classes, +50 interface classes

Measure time until first 100% accurate solution: synthetic ground truths

default refinement operator from DL-Learner extended AML refinement operator