Explainability of Quality Issues in Manufacturing: a Semantic Based Approach LΓ©a Charbonnier1 , Franco Giustozzi2 , Julien Saunier1 and Cecilia Zanni-Merk1,* 1 INSA Rouen Normandie, Univ Rouen Normandie, UniversitΓ© Le Havre Normandie, Normandie Univ, LITIS UR 4108, F-76000 Rouen, France 2 INSA Strasbourg, University of Strasbourg, ICube laboratory, CNRS (UMR 7357), 67000 Strasbourg, France Abstract This paper presents an approach using stream reasoning for detecting manufacturing quality losses. To semanti- cally detect quality issues situations, an ontology-based context for manufacturing is introduced. Moreover, as heterogeneous data streams have to be integrated, a combination of existing models using stream processing and offline reasoning can be used. This combination allows continuous processing of data and the use of expert knowledge to detect anomalies and provide explanations to operators and stakeholders. An illustrative case study about quality assurance succeeded in detecting anomalies and proposing an explanation. Keywords Quality Assurance and Industry 4.0 (Quality 4.0), Ontology, Explainability, Quality issues detection 1. Introduction With the advent of Industry 4.0 and the ability to monitor production lines in real time, new possibilities in terms of product quality management have emerged. One of them is Quality 4.0 [1], an extension of Industry 4.0 to quality assurance which allows to combine quality data with data from other sources (machine sensors, manufacturing, etc). As industries need to reduce risks and costs and ensure the quality of products, predictive models can use data collected by machine sensors to anticipate breakdowns or manufacturing errors. However, these models are not all inherently explainable and can entail huge difficulties in tracking root causes of anomalies [2]. This work is part of the XQuality 1 project whose main goal is to implement intelligent and automated quality assurance to assist operators in manufacturing companies. We propose to use a hybrid approach to detect and explain quality loss by reasoning over an ontology that integrates all the available knowledge such as results of predictive models, technical documentation and expert knowledge. 2. Quality issues detection and explanation Quality assurance in manufacturing companies is an essential process for ensuring that products meet standards. It contributes to customer satisfaction and reduces the costs of defects. To tackle quality issues, we propose to adapt the approach presented in [3]. The idea is to detect situations that may lead to quality losses by observing products and tracking abnormal sensor values. Expert knowledge will allow the identification and assessment of the root cause that led to a detected abnormal situation. The framework proposed in Figure 1 is based on [3]. Three modules are used to detect and explain quality issue situations reasoning over an ontology: Translation, Temporal Relations and Cause Determination. This reasoning is performed in real time (stream reasoning) or offline (classical reasoning over an ontology). Posters, Demos, and Industry Tracks at ISWC 2024, November 13–15, 2024, Baltimore, USA * Corresponding author. $ lea.charbonnier@insa-rouen.fr (L. Charbonnier); franco.giustozzi@insa-strasbourg.fr (F. Giustozzi); julien.saunier@insa-rouen.fr (J. Saunier); cecilia.zanni-merk@insa-rouen.fr (C. Zanni-Merk) Β© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). 1 http://x-quality.projets.litislab.fr/ CEUR ceur-ws.org Workshop ISSN 1613-0073 Proceedings Figure 1: Proposed framework for quality issue detection with stream reasoning. To detect quality issues, an ontology based on the Context Ontology described in [4] is used. This ontology is composed of three core ontologies (Sensor Ontology, Time Ontology, Location Ontology and Situation Ontology) and three domain ontologies (Resource Ontology and Process Ontology). Therefore, we propose to extend the Situation Ontology with a Quality Assurance Ontology. As the Situation Ontology concerns only situations on machines, we want to extend it with quality issues situation detection on products. The Quality Assurance Ontology is based on TOVE Traceability Ontology [5] which provides representation to identify and trace a quality problem. As TOVE is a core ontology, we mainly use the idea of traceability between products and activities. This allows to link products to the machine that produced or modified them when and where the default occurred. The Translation module is responsible for collecting sensor data and converting it to RDF streams thanks to Stream Generators. This component performs a semantic enrichment of raw data using the concepts and relations defined in the ontology. One Stream Generator is used per sensor. The Temporal Relations module is used to explore the data. RDF streams are continuously queried into the Stream Reasoner using the ontology to contextualize the streams. The queries represent different quality issue situations to detect. For this component, we used RSP4J [6] to query the streaming data. The data from the detected situations is then formatted and put into the ontology. The Cause Determination module identifies the root cause and explains the problem. The Reasoner is used over the ontology to check the consistency of the ontology and then, infer new knowledge. The cause of the quality problem can then be determined using different classifiers as proposed in [7]. 3. Illustrative case study In this section, we present an illustrative case study created to test our framework. We consider a manufacturing production line named PL1 composed of two machines M1 and M2 which produce products named P1 , P2 and P3 . The production line is equipped with sensors that observe machine and product properties. The sensors collect data on properties in Table 1. Constraints ranging from 𝑐1 to 𝑐8 relate to machines and the other ones relate to products. Set of constraints C ID Properties Restriction Device ID Properties Restriction Device 𝑐1 Motor temp. > 500Β°C M1 mt1 𝑐7 Roller speed > 600 mpm M2 R1 𝑐2 Punching speed > 2000 times/min M1 p1 𝑐8 Cooling temp. > 25Β°C M2 T1 𝑐3 Punching pressure > 8 MPa M1 p1 𝑐9 Porosity > 10 pu Pr 𝑐4 Environment temp. < 25Β°C PL1 𝑐10 Porosity > 40 pu Pr 𝑐5 Roller temp. > 1300Β°C M2 R1 𝑐11 Roughness > 0.3 πœ‡m Pr 𝑐6 Roller pressure > 450 bar M2 R1 𝑐12 Flatness > 27 I-Units Pr Table 1 Constraints definition Set of situations S Set of quality situations π‘†π‘ž Sit. Constraint(T) Description Sit. Constraint(T) Description 𝑠1 𝑐2 , 𝑐3 M1 t1 Tool wear π‘ π‘ž1 𝑐4 P1 water spot 𝑠2 𝑐3 , 𝑐4 M1 p1 Press Wear π‘ π‘ž2 𝑐12 , 𝑐2 , 𝑐3 P1 punching defects 𝑠3 𝑐1 , 𝑐2 , 𝑐3 , 𝑐4 M1 Machine Wear π‘ π‘ž3 𝑐11 , 𝑐12 , 𝑐2 , 𝑐3 P1 punching defects 𝑠4 𝑐6 , 𝑐7 M2 Machine Wear and Tear π‘ π‘ž3 𝑐9 , 𝑐4 , 𝑐5 , 𝑐6 P2 uneven deformations 𝑠4 𝑐5 , 𝑐8 M2 Fluid leakage π‘ π‘ž4 𝑐9 , 𝑐10 , 𝑐4 , 𝑐5 , 𝑐6 , 𝑐7 P3 surface defects 𝑠5 𝑐5 , 𝑐6 , 𝑐7 , 𝑐8 M2 Mechanical failures Table 3 Table 2 Quality issues situations and their concerned constraints Situations and their concerned constraints Abnormal situations that could lead to machine failures are defined from expert knowledge and expressed as a set of constraints in Table 2. Quality issues situations are also defined from expert knowledge and expressed as a set of constraints in Table 3. They describe quality issues detected on products and the associated machine and product constraints. Data streams are then created by the Stream Generator and continuous queries are performed on them. To do this, the Stream Reasoner is used with an ontology containing information on the production line. Once a situation is detected, is it added to the ontology. An off-line reasoning is done to check the consistency of the ontology. Another Reasoner is then used to provide an explanation thanks to the information contained in the ontology which allows to link defects found with expert information and technical documentation. 4. Conclusion and future work A semantic approach to quality loss explanation in the manufacturing industry is presented. Data streams are processed with stream reasoning allowing real-time situation detection. A context ontology is used to help detect quality issues by enriching the information contained in the streams. In future work, explanations of abnormal situations and their causes will be adapted according to the end user. Acknowledgments This work was supported by the French National Research Agency [grant number ANR-22-CE92-0007]. References [1] A. V. Carvalho, D. V. Enrique, A. Chouchene, F. Charrua-Santos, Quality 4.0: An Overview, Procedia Computer Science 181 (2021) 341–346. [2] T. V. Andrianandrianina Johanesa, L. Equeter, S. A. Mahmoudi, Survey on ai applications for product quality control and predictive maintenance in industry 4.0, Electronics 13 (2024). [3] F. Giustozzi, J. Saunier, C. Zanni-Merk, Abnormal Situations Interpretation in Industry 4.0 using Stream Reasoning, Procedia Computer Science 159 (2019) 620–629. [4] F. Giustozzi, J. Saunier, C. Zanni-Merk, Context Modeling for Industry 4.0: an Ontology-Based Proposal, Procedia Computer Science 126 (2018) 675–684. [5] H. Kim, M. Fox, M. GrΓΌninger, An Ontology for Quality Management β€” Enabling Quality Problem Identification and Tracing, Bt Technology Journal - BT TECHNOL J 17 (1999) 131–140. [6] R. Tommasini, P. Bonte, F. Ongenae, E. D. Valle, RSP4J: An API for RDF Stream Processing, in: Extended Semantic Web Conference, 2021. [7] M. Bellucci, N. Delestre, N. Malandain, C. Zanni-Merk, Ontologies to build a predictive architecture to classify and explain, in: DeepOntoNLP Workshop @ESWC 2022, Hersonissos, Greece, 2022.