=Paper=
{{Paper
|id=Vol-2721/paper554
|storemode=property
|title=SemML: Reusable ML Models for Condition Monitoring in Discrete Manufacturing
|pdfUrl=https://ceur-ws.org/Vol-2721/paper554.pdf
|volume=Vol-2721
|authors=Yulia Svetashova,Baifan Zhou,Stefan Schmid,Tim Pychynski,Evgeny Kharlamov
|dblpUrl=https://dblp.org/rec/conf/semweb/SvetashovaZSPK20
}}
==SemML: Reusable ML Models for Condition Monitoring in Discrete Manufacturing==
https://ceur-ws.org/Vol-2721/paper554.pdf
SemML: Reusable ML for Condition Monitoring
in Discrete Manufacturing
Yulia Svetashova1,2 , Baifan Zhou1,2 , Stefan Schmid1 ,
Tim Pychinsky1 , and Evgeny Kharlamov3,4
1
Bosch Corporate Research, Robert Bosch GmbH, Germany
2
Karlsruhe Institute of Technology, Germany
3
Bosch Center for Artificial Intelligence, Robert Bosch GmbH, Germany
4
University of Oslo, Norway
Abstract. Machine learning (ML) is gaining much attention for data analysis in
manufacturing. Despite the success, there is still a number of challenges in widen-
ing the scope of ML adoption. The main challenges include the exhausting effort
of data integration and lacking of generalisability of developed ML pipelines to
diverse data variants, sources, and domain processes. In this demo we present our
SemML system that addresses these challenges by enhancing machine learning
with semantic technologies: by capturing domain and ML knowledge in ontolo-
gies and ontology templates and automating various ML steps using reasoning.
During the demo the attendees will experience three cunningly-designed scenar-
ios based on real industrial applications of manufacturing condition monitoring
at Bosch, and witness the power of ontologies and templates in enabling reusable
ML pipelines.
1 Introduction
Industry 4.0 [4] and the Internet of Things [3] behind it lead to unprecedented growth of
data generated from manufacturing processes [1]. Indeed, modern manufacturing ma-
chines and production lines are equipped with sensors that constantly collect and send
data and with control units that monitor and process these data, coordinate machines
and manufacturing environment, and send messages, notifications, requests.
This opens new horizons for data-driven methods like Machine Learning (ML) in
condition monitoring for a wide range of application scenarios, which is to assess or
predict some performance indicators for machine health state, e.g. turbine life-span, or
product quality, e.g. welding spot diameter. The broad practice of development and de-
ployment of intelligent information processing technologies in discrete manufacturing
is a highlighted feature in the grand trend of Industry 4.0 [12–14].
One-time development of an ML pipeline for a specific scenario can be done within
a reasonably short time. However, condition monitoring requires the constant develop-
ment of new ML models. On the one hand, this requires the ML pipeline to deal with
a variety of data; on the other hand, the ML models have to be developed for similar
processes or similar tasks. Therefore, an important challenge in the manufacturing in-
dustry is to scale ML model development and to enable reusability of already-developed
ML pipelines. Direct reuse of an ML pipeline without any modification is unrealistic.
Copyright c 2020 for this paper by its authors. Use permitted under Creative Commons License
Attribution 4.0 International (CC BY 4.0).
Fig. 1. An Architectural Overview of SemML
Thus, the developed ML pipelines require adaptation that should ideally be done with
affordable or minimal modification.
In this work we address this challenge by relying on semantic technologies. Seman-
tic technologies have recently gained a considerable attention in industry for a wide
range of applications and automation tasks such as modelling of industrial assets [5]
and industrial analytical tasks [7], integration [6, 8, 2] and querying [11] of production
data, and for process monitoring [10] and equipment diagnostics [9].
Our solution uses ontologies to integrate data, to infer ML-relevant information for
data of various types (time series, categorical, numerical), to perform automated fea-
ture engineering, ML model construction and ML pipeline reuse. The core component
of the solution is the template-based extensibility mechanism: we employ templates to
extend ontologies to new data sources and to create ontologies for new manufacturing
processes. Graphical user interfaces for ontology extension and data annotation make
these tasks accessible to non-ontologists. Annotated data serves as input to the config-
urable ontology-aware ML pipeline.
We implemented our ideas in the system called SemML. In this demonstration we
will show how SemML facilitates reusability of the developed ML pipelines for quality
analysis using three scenarios. First, we present how SemML allows to reuse ML mod-
els to new production lines and new data sources, e.g., laboratory data and simulations.
Second, we show how SemML helps in adapting ML models to new condition monitor-
ing tasks, e.g., estimation vs prediction, varying quality indicators. Finally, we exhibit
how SemML can help in adjusting ML pipelines to new manufacturing processes.
This demo paper accompanies our accepted ISWC’20 in-use paper [12].
2 Our System SemML and Data Requirements
A typical workflow that supports the development of ML models for manufacturing
consists of 5 steps shown in Figure 1: (i) data acquisition, (ii) task negotiation, (iii) data
preparation, (iv) ML model construction, (v) ML model interpretation. SemML follows
this workflow and provides semantic support for unambiguous process description, task
negotiation, convenient data integration and configurable ML pipeline training, testing
and interpretation. Thus SemML primarily focuses on Steps 2-5 of the workflow in
enabling adaptability of ML pipelines. More precisely, SemML enhances traditional
ML modules with the following semantic components:
– Ontology Extender allows experts to extend and create domain ontologies that cap-
ture manufacturing processes and ML practices by using terms from an upper-level
ontology, Core Ontology, for condition monitoring in manufacturing, and by fill-
ing in Ontology Templates. The GUI of Ontology Extender, which can be seen in
Sub-figures 1.1 and 1.2 of Figure 2, exposes templates as UI forms, and its backend
transforms user input into OWL 2 ontologies.
– Domain Knowledge Annotator enables users to do data integration by annotat-
ing raw data with terms from domain ontologies and stores these annotations as
ontology-to-data mappings. Sub-figure 2 of Figure 2 shows its browsing function-
alities. Existing and newly created ontology terms become available for the annota-
tion of data. Annotations together with the dataset form the input to the ML-related
parts of SemML.
– ML-Pipeline Adaptation Module uses automated reasoning to infer ML-relevant
information from ontology-to-data mappings and creates the mappings between
ML ontologies and data for each raw data source.
– Machine Learning Annotator and Processor enables the uniform handing of the
prepared data by ML algorithms in the Feature Engineering module. This module
performs various transformations of data categorised as feature groups and can also
add new Engineered Groups of features. After feature engineering, several machine
learning models are constructed in the ML Model Construction module.
– Machine Learning Visualizer and Interpreter uses information about the feature
engineering algorithms and engineered features to facilitate the visualisation of the
machine learning modelling and select the best model.
SemML is suitable for the development and reuse of ML pipelines for various
datasets representing discrete manufacturing processes [?]. Thus, SemML requires that
some specific feature types to be present in the data: (1) performance indicators, i.e.,
machine health state or quality indicator, the estimation of which is one major task of
condition monitoring. (2) unique identifiers for each manufacturing operation (3) single
numeric features, such as the geometrical properties of the products or equipment, (4)
single categorical features, e.g. control mode A, B, C, (5) time series, continuous sen-
sor measurements (e.g. force) with time stamps, (6) count features, e.g. counts of man-
ufactured products since the last maintenance, (7) other data types like images, videos,
log-files, etc. Among which, (1) is mandatory to be present, at least one of (3)-(7) needs
to be present, (2) is needed to find the correspondence between different feature types.
3 Demonstration Scenarios
For the demonstration purposes, we prepared the instance of our system and two anony-
mised Bosch datasets from the manufacturing production lines, which represent two
welding processes: resistance spot welding (RSW) and hot-staking (HS). We will start
the demo with the demonstration of the Core Ontology for discrete manufacturing and
the ontology templates library via the graphical user interface of the Ontology Extender.
We then present the datasets and shortly introduce two manufacturing processes. For
the resistance spot welding dataset, we will create an RSW domain ontology, then map
the column names in the dataset to its terms, and execute the developed ML pipelines,
Fig. 2. Graphical User Interfaces for (1) Ontology Extension and (2) Data Annotation
which take the data and this mapping as input, and output trained ML models and
predictions.
Scenario 1: Pipeline adaptation to a new production line. The typical scenario for
the reuse of the developed ML pipeline is its adaptation to the new production line.
Data preparation for the ML component of SemML relies on the description of the
schema for each new dataset in terms of the domain ontology. The attendees will create
a mapping for the RSW dataset by using the Domain Knowledge Annotator GUI with
the RSW ontology. The mapping of the suggested dataset will require to extend the
domain ontology. We formulated the typical extension requests (e.g. add a new config-
uration of the assembly) as tasks. For example, the initial version of the ontology will
contain terms to describe a chassis part with two worksheets, the attendees will add a
three-component assembly. Another adaptation use case is to extend the ML pipeline
developed for the robust control system to the adaptive one (i.e. add corresponding
reference parameters to the measured actual values). Thirdly, the pipeline reuse will
be demonstrated for the new data sources: the simulation and laboratory datasets. In
all mentioned cases, adaptation is reduced to adding new classes and properties to the
RSW ontology and using them in the mappings for the new datasets.
Scenario 2: Pipeline adaptation to a new monitoring task. This scenario demon-
strates the interplay between the domain knowledge acquisition and the task negotiation
processes, often involving stakeholders with different backgrounds. We suggest that at-
tendees introduce new quality indicators and show the adaptability of the pipeline on the
level of the ML task. Reliable quality indicators are highly dependent on the available
data. For example, simulation data in the welding domain contains such quality indica-
tor as welding nugget diameter. This indicator is rarely present in the production data
because it would mean the destruction of the welded part. The attendees will observe
how the monitoring pipeline for a particular dataset handles various ML tasks.
Scenario 3: Pipeline adaptation to a new manufacturing process. In this scenario,
the attendees will go through the complete cycle of data preparation for a new manu-
facturing process: hot-staking, and adapt the ML pipeline to an HS dataset. This will
include the creation of a new domain ontology from scratch based on the compact de-
scription of the process, the mapping of data, the specification of quality indicators, and
the execution of a pipeline.
References
1. Chand, S., Davis, J.: What is Smart Manufacturing. Time Magazine Wrapper 7, 28–33 (2010)
2. Horrocks, I., Giese, M., Kharlamov, E., Waaler, A.: Using Semantic Technology to Tame the
Data Variety Challenge. IEEE Internet Comput. 20(6), 62–66 (2016)
3. ITU: Recommendation ITU – T Y.2060: Overview of the Internet of Things. Tech. rep.,
International Telecommunication Union (2012)
4. Kagermann, H.: Change Through Digitization – Value Creation in the Age of Industry 4.0.
In: Management of Permanent Change (2015)
5. Kharlamov, E., Grau, B.C., Jiménez-Ruiz, E., Lamparter, S., Mehdi, G., Ringsquandl, M.,
Nenov, Y., Grimm, S., Roshchin, M., Horrocks, I.: Capturing Industrial Information Models
With Ontologies and Constraints. In: ISWC (2016)
6. Kharlamov, E., Hovland, D., Skjæveland, M.G., Bilidas, D., Jiménez-Ruiz, E., Xiao, G.,
Soylu, A., Lanti, D., Rezk, M., Zheleznyakov, D., Giese, M., Lie, H., Ioannidis, Y.E., Kotidis,
Y., Koubarakis, M., Waaler, A.: Ontology Based Data Access in Statoil. J. Web Semant. 44,
3–36 (2017)
7. Kharlamov, E., Kotidis, Y., Mailis, T., Neuenstadt, C., Nikolaou, C., Özçep, Ö.L., Svingos,
C., Zheleznyakov, D., Ioannidis, Y.E., Lamparter, S., Möller, R., Waaler, A.: An Ontology-
Mediated Analytics-Aware Approach to Support Monitoring and Diagnostics of Static and
Streaming Data. J. Web Semant. 56, 30–55 (2019)
8. Kharlamov, E., Mailis, T., Mehdi, G., Neuenstadt, C., Özçep, Ö.L., Roshchin, M., Solo-
makhina, N., Soylu, A., Svingos, C., Brandt, S., Giese, M., Ioannidis, Y.E., Lamparter, S.,
Möller, R., Kotidis, Y., Waaler, A.: Semantic Access to Streaming and Static Data at Siemens.
J. Web Semant. 44, 54–74 (2017)
9. Kharlamov, E., Mehdi, G., Savkovic, O., Xiao, G., Kalayci, E.G., Roshchin, M.:
Semantically-Enhanced Rule-Based Diagnostics for Industrial Internet of Things: The SDRL
Language and Case Study for Siemens Trains and Turbines. J. Web Semant. 56, 11–29 (2019)
10. Ringsquandl, M., Kharlamov, E., Stepanova, D., Hildebrandt, M., Lamparter, S., Lepratti, R.,
Horrocks, I., Kröger, P.: Event-Enhanced Learning for KG Completion. In: ESWC (2018)
11. Soylu, A., Kharlamov, E., Zheleznyakov, D., Jiménez-Ruiz, E., Giese, M., Skjæveland, M.G.,
Hovland, D., Schlatte, R., Brandt, S., Lie, H., Horrocks, I.: Optiquevqs: A Visual Query
System Over Ontologies for Industry. Semantic Web 9(5), 627–660 (2018)
12. Svetashova, Y., Zhou, B., Pychynski, T., Schmidt, S., Sure-Vetter, Y., Mikut, R., Kharlamov,
E.: Ontology-enhanced machine learning: a bosch use case of welding quality monitoring.
In: ISWC (2020)
13. Zhou, B., Svetashova, Y., Byeon, S., Pychynski, T., Mikut, R., Kharlamov, E.: Predicting
Quality of Automated Welding with Machine Learning and Semantics: a Bosch Case Study.
In: CIKM (2020)
14. Zhou, B., Svetashova, Y., Pychynski, T., Baimuratov, I., Soylu, A., Kharlamov, E.: Semfe:
Facilitating ml pipeline development with semantics. In: CIKM (2020)