=Paper=
{{Paper
|id=Vol-1963/paper651
|storemode=property
|title=Semantic Rule-Based Equipment Diagnostic
|pdfUrl=https://ceur-ws.org/Vol-1963/paper651.pdf
|volume=Vol-1963
|authors=Gulnar Mehdi,Evgeny Kharlamov,Ognjen Savkovic,Guohui Xiao,Elem Guzel Kalayci,Sebastian Brandt,Ian Horrocks,Mikhail Roshchin,Thomas Runkler
|dblpUrl=https://dblp.org/rec/conf/semweb/MehdiKSXKBHRR17a
}}
==Semantic Rule-Based Equipment Diagnostic==
https://ceur-ws.org/Vol-1963/paper651.pdf
Semantic Rules for Siemens Turbines
Gulnar Mehdi1,2 Evgeny Kharlamov3 Ognjen Savković4 Guohui Xiao4 E. Kalaycı4
Sebastian Brandt2 Ian Horrocks3 Mikhail Roshchin2 Thomas Runkler1,2
1
Technical University of Munich, Germany 2 Siemens AG CT, Munich Germany
3
University of Oxford, UK 4 Free University of Bozen-Bolzano, Italy
1 Introduction
Motivation. Diagnostic systems play an important role in industry since they help to
maximise equipment’s up-time and minimise its maintenance and operating costs [16].
In the energy sector companies like Siemens often rely on rule-based diagnostics to
analyse power generating equipment by, e.g., testing newly deployed electricity gener-
ating gas turbines [11], or checking vibration instrumentation [13], performance degra-
dation [14], and faults in operating turbines. For this purpose diagnostic engineers create
and use complex diagnostic rule-sets to detect equipment abnormalities.
An important class of rules that are commonly used in Siemens are signal process-
ing rules (SPRs) that allow one (i) filter, aggregate, combine, and compare signals1
coming from sensors installed in equipment and (ii) send notification messages when a
certain pattern in signals is detected. Authoring SPR based rule-sets is challenging. We
now discuss this challenge in details and then present our solution to address them.
Challenges with Authoring SPRs. The main challenge for authoring is that SPRs
in most modern industrial diagnostic systems including the ones used in Siemens are
highly data dependent in the sense that specific characteristic of individual sensors and
pieces of equipment are explicitly encoded in SPRs. As the result for a typical turbine
diagnostic task engineers have to write from dozens to hundreds of SPRs that involve
hundreds of sensor ids, component codes, sensor and threshold values as well as equip-
ment configuration and design data. E.g., a typical Siemens gas turbine has about 2,000
sensors and a typical diagnostic task is to verify that the purging2 has ended; for the
main flame component of a given turbine, this task requires around 300 SPRs, most of
which are similar in structure but different in equipment specific data values.
Thus, there is a need in industry, and in particular in Siemens for a higher level
diagnostic rule language that allows to express what the diagnostic task should do rather
than how it should do it for specific equipment. Such language should be high level,
data independent, while powerful enough to express in a concise way most of typical
diagnostic tasks in Siemens.
Our Solution. We rely on semantic technologies to address the the above mentioned
challenges. In particular we rely on ontologies [1] to define a novel SPR language and
on reasoning [3] over ontologies to foster execution and maintenance of diagnostic
tasks. In short, an ontology is a formal conceptualisation of the domain of interest that
consists of a vocabulary, i.e., names of classes, attributes and binary relations, and ax-
ioms over the terms from the vocabulary that, e.g., assign attributes of classes, define
relationships between classes, compose classes, class hierarchies, etc. Since ontologies
1
Signals are are time stamped sequences of measurement values.
2
Purging is the process of flushing out liquid fuel nozzles or other parts which may contain
undesirable residues.
2
are specified using a formal logical language such as the W3C standardised ontology
web language OWL 2, one can query ontologies and check their properties using rea-
soning that typically corresponds to logical entailment and implemented in many effi-
cient state-of-the-art reasoning systems such as HermiT [15]. We refer the reader to [1]
for more details on ontologies and reasoning.
In order to address the authoring challenge we propose:
– an SPR language sigRL that treats signals as first class citizens and allows signals
to be processed (filtered, aggregated, combined, and compared) in a high level,
declarative, and data independent fashion;
– semantic diagnostic programs that combine sigRL rules with diagnostic background
knowledge captured using ontologies and allow users to express complex diag-
nostic tasks in an abstract fashion by exploiting both ontological vocabulary and
queries over ontologies to identify relevant information (such as sensor ids and
threshold values) about the equipment that should undergo the diagnostics.
Note that we designed sigRL in such a way that, on the one hand, it captures the
main signal processing features required by Siemens turbine diagnostic engineers and,
on the other hand allows for efficient execution of diagnostic programs.
2 Our Diagnostic Solution
We first illustrate sigRL with an example and then describe our system SemDia.
sigRL Diagnostic Language. Consider a purging diagnostic task:
Verify that the purging ended in the main flame component of the turbine T1.
Intuitively this task requires to check in the turbine T1 that: (i) the main flame was
on for at least 10s and then stopped, (ii) 15s after this, the purging of rotors in the
starting-component of T1 started, (iii) 20s after this, the purging stopped. The fact that
the purging of a rotor started or ended can be detected by analysing its speed, i.e.,
by comparing the average speed of its speed sensors with purging thresholds that are
specific for individual rotors. The purging diagnostic program in our language sigRL can
then consist of an ontology with one axiom: SubClassOf(RotorSensor SpeedSensor).
two signal processing expressions and one message rule:
PurgingStart = avg rotorStart : value(>, purgingSpeed),
PurgingStop = avg rotorStart : value(<, nonPurgingSpeed),
msg(“Purging over”) = FlameSensor : duration(>, 10s) :
after[15s] PurgingStart : after[20s] PurgingStop
For the complete description of sigRL we refer to our papers [10,7,9]. Here, the
ontology defines a vocabulary over which one can write diagnostic rules in sigRL.
SemDia Diagnostic System. The main functionality of our semantic rule-based diag-
nostics system SemDia is to author and maintain sigRL diagnostic programs, to deploy
them in turbines, to execute the programs, and to visualise the results of the execution.
We now give details of our system by following its architecture in Figure 1 (left) where
the solid arrows indicate data flow and dashed arrows indicate—access to ontologies
and mappings. There are three essential layers in the architecture: application, rule exe-
cution, and signal and data layers. Our system is mostly implemented in Java. We now
discuss the system layer by layer.
3
Fig. 1. Left: Architecture of SemDia. Right (Screenshots): SPR editor (top), Diagnostic visuali-
sation monitor (bottom)
Application
Sem Wiki:
Layer Rule OWL 2
visualisation,
Formulation Reasoner
tracking
semantic semantic
signals, diagnostic
notification programs Ontology
messages
OBDA Virtualisation
Mappings:
Rewriting and Unfolding of Data-to-
Execution Rules, Queries, Answers Ontologies
Layer data level data level
messages diagnostic programs
and queries
Rule Execution Infrustructure
Signal and
Data design service event sensor
Layer data data data signals
Application Layer. On this layer, the system allows engineers to author, store, and load
diagnostic programs by formulating sets of SPRs as well as message rules in sigRL and
sensor retrieving queries. Such formulation is guided by the domain ontology stored
in the system. In Figure 1 (right, top) one can observe a screenshot of the diagnostic
program editor which is embedded in the Siemens analytical tool-kit. Another front
end component is the semantic wiki that allows among other features to visualize sig-
nals and messages (triggered by programs), and to track deployment of programs in
equipment. In Figure 1 (right, bottom) one can see visualisation of signals from two
components of one turbine. The back end of the application layer relies on HermiT [15]
ontology reasoning. Diagnostic programs formulated in the application layer are con-
verted into XML-based specifications and sent to the rule execution layer that returns
back messages and signals. We rely on the REST API to communicate between the ap-
plication and execution layer of our system and the OWL API to deal with ontologies.
Execution Layer. On this layer we support semantic signals that are either native, that
is, represented in terms of the diagnostic ontology as RDF triple, or virtual, that is ob-
tained through the Ontology Based Data Access (OBDA) [12] component of SemDia.
This component allows to present signals stored in relational databases as if they were
native semantic. This requires to connect the relational signals to an ontology via declar-
ative mappings. For the OBDA layer we rely on the extension of the Ontop system [2]
developed during the Optique project [8,6,4,5] that takes care of transforming diagnos-
tic programs written in sigRL into either SPRs written in the Siemens data-driven rule
language or SQL. This transformation has two steps: rewriting of programs and queries
with the help of ontologies (at this step both programs and queries are enriched with
the implicit information from the ontology), and then unfolding them with the help of
mappings. Moreover, the execution layer takes care of planning and executing rules and
queries received either from the rule management or OBDA component. If the received
rules are in the Siemens SPR language then the rule executor instantiates them with
concrete sensors extracted with queries and passes them to the Drools Fusion the en-
gine used by Siemens. If the received rules are in SQL then it plans the execution order
and executes them together with the other queries.
Signal and Data Layer. On this layer we store all the relevant data: turbine design
specifications, historical information about services that were performed over the tur-
bines, previously detected events, and the raw sensor signals. Currently SemDia support
PostgresQL, Teradata, as well as Sparksee.
4
3 Demonstration Overview
Demo attendees will be able to learn how to do diagnostics of Siemens turbines with
sigRL diagnostic programs. To this end we prepared a deployment of our SemDia sys-
tem on data from 50 Siemens power generating turbines, a diagnostic ontology, and a
catalogue of 15 diagnostic tasks. The attendees will be able to load preconfigured diag-
nostic programs, deploy and execute them, author their own diagnostic programs, and
try out our provenance computation and program verification services.
Acknowledgments This research is supported: EPSRC projects MaSI3 , DBOnto, ED3 ;
and the Free University of Bozen-Bolzano project QUEST.
References
1. Baader, F., Calvanese, D., McGuinness, D.L., Nardi, D., Patel-Schneider, P.F. (eds.): The
Description Logic Handbook: Theory, Implementation, and Applications. Cambridge Uni-
versity Press (2003)
2. Calvanese, D., Cogrel, B., Komla-Ebri, S., Kontchakov, R., Lanti, D., Rezk, M., Rodriguez-
Muro, M., Xiao, G.: Ontop: Answering SPARQL queries over relational databases. Semantic
Web 8 (2017)
3. Calvanese, D., De Giacomo, G., Lembo, D., Lenzerini, M., Rosati, R.: Tractable reasoning
and efficient query answering in description logics: The DL-Lite family. Journal of Auto-
mated Reasoning 39(3) (2007)
4. Horrocks, I., Giese, M., Kharlamov, E., Waaler, A.: Using semantic technology to tame the
data variety challenge. IEEE Internet Computing 20(6), 62–66 (2016)
5. Kharlamov, E., Brandt, S., Jiménez-Ruiz, E., Kotidis, Y., Lamparter, S., Mailis, T., Neuen-
stadt, C., Özçep, Ö.L., Pinkel, C., Svingos, C., Zheleznyakov, D., Horrocks, I., Ioannidis,
Y.E., Möller, R.: Ontology-Based Integration of Streaming and Static Relational Data with
Optique. In: SIGMOD (2016)
6. Kharlamov, E., Jiménez-Ruiz, E., Zheleznyakov, D., Bilidas, D., Giese, M., Haase, P., Hor-
rocks, I., Kllapi, H., Koubarakis, M., Özçep, Ö.L., Rodriguez-Muro, M., Rosati, R., Schmidt,
M., Schlatte, R., Soylu, A., Waaler, A.: Optique: Towards OBDA systems for industry. In:
ESWC Satellite Events. pp. 125–140 (2013)
7. Kharlamov, E., Savkovic, O., Xiao, G., Penaloza, R., Mehdi, G., Horrocks, I., Roshchin, M.:
Semantic rules for machine diagnostics: Execution and management. In: CIKM (2017)
8. Kharlamov, E., Solomakhina, N., Özçep, Ö.L., Zheleznyakov, D., Hubauer, T., Lamparter,
S., Roshchin, M., Soylu, A., Watson, S.: How semantic technologies can enhance data access
at siemens energy. In: ISWC. pp. 601–619 (2014)
9. Mehdi, G., Kharlamov, E., Savkovic, O., Xiao, G., Kalayci, E.G., Brandt, S., Horrocks, I.,
Roshchin, M., Runkler, T.: Semdia: Semantic rule-based equipment diagnostics tool. In:
CIKM (2017)
10. Mehdi, G., Kharlamov, E., Savkovic, O., Xiao, G., Kalayci, E.G., Brandt, S., Horrocks, I.,
Roshchin, M., Runkler, T.: Semantic rule-based equipment diagnostics. In: ISWC (2017)
11. Mitchell, J.S.: An introduction to machinery analysis and monitoring. Pennwell Books
(1993)
12. Poggi, A., Lembo, D., Calvanese, D., De Giacomo, G., Lenzerini, M., Rosati, R.: Linking
data to ontologies. J. Data Semantics 10, 133–173 (2008)
13. Randall, R.B.: Vibration-based condition monitoring: industrial, aerospace and automotive
applications. Wiley (2011)
14. Rao, B.K.N.: Handbook of condition monitoring. Elsevier (1996)
15. Shearer, R., Motik, B., Horrocks, I.: HermiT: A Highly-Efficient OWL Reasoner. In:
OWLED (2008)
16. Vachtsevanos, G., Lewis, F.L., Roemer, M., Hess, A., Wu, B.: Intelligent Fault Diagnosis and
Prognosis for Engineering Systems. Wiley (2006)