TY - CONF A1 - Muñoz Gil, Hernán Darío T1 - MR4SafeOperations: Mixed reality system for training and supporting industrial plant personnel. N2 - Operation and maintenance tasks in industrial process plants are complex and safety-critical, often relying on heterogeneous documentation and limited contextual support for field personnel. This work presents MR4SafeOperations, a mixed reality–based system designed to assist operators during operation and maintenance activities through context-aware, hands-free guidance. Using a vacuum distillation sampling procedure as a case study, operational workflows are formalized with BPMN and structured according to ISA-88.1 principles. Process data, 3D plant models, P&IDs, and procedural information are integrated via standardized interfaces into a mixed reality application. The system enhances situational awareness, reduces cognitive load, and supports safer decision-making during plant operation. The results demonstrate the potential of mixed reality to improve safety, efficiency, and usability in industrial process environments. T2 - MR4B-Konferenz CY - Berlin, Germany DA - 17.07.2025 KW - Safety KW - Mixed Reality KW - Operation & Maintenance KW - Digital workflows PY - 2025 AN - OPUS4-65165 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Lewerenz, Rebecca A1 - Komander, Felix T1 - KEPLER – Kollaborative Mixed Reality Plattform für das Engineering im Anlagenbau durch Integration der Domänenmodelle BIM und DEXPI N2 - In den frühen Entwurfsphasen von verfahrenstechnischen Anlagen innerhalb von Gebäuden müssen Verfahrens- und Bauingenieur:innen eng zusammenarbeiten. Dabei nutzen sie jedoch unterschiedliche Werkzeuge, Datenmodelle und Austauschstandards – etwa DEXPI in der Verfahrenstechnik und IFC im Bauwesen –, was den Datenaustausch zwischen den Disziplinen erschwert und häufig zu Inkonsistenzen führt. Das KEPLER-Projekt entwickelt eine Mixed-Reality-Plattform für die dreidimensionale Anordnung von Anlagenkomponenten durch die Integration der Standards DEXPI und IFC. T2 - MR4B-Konferenz CY - Berlin, Germany DA - 17.07.2025 KW - Interoperabilität KW - DEXPI KW - BIM KW - IFC KW - Preengineering KW - Mixed-Reality PY - 2025 AN - OPUS4-65183 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Scheffold, Lukas A1 - Esche, Erik T1 - Exploring disjunctive programming formulations for optimal design of distillation columns N2 - Automating process synthesis presents a formidable challenge in chemical engineering. Developing frameworks that are both general and accurate – while remaining computationally tractable – is particularly demanding. To further increase the solvable problem size, an advanced optimization framework is proposed, leveraging Generalized Disjunctive Programming (GDP) for process synthesis and design problems. This framework allows for multiple improvements over existing Mixed Integer Nonlinear Programming (MINLP) formulations, aiming to enhance feasibility and reduce solution time. Process synthesis problems are typically posed as nonlinear optimization problems with continuous and discrete variables. Traditionally, these are formulated as MINLP problems, where discrete variables appear as integer or binary variables. These are usually relaxed to continuous variables to solve the MINLP. In practice, the (in-)equality constraints are obtained starting from logical expressions, which are reformulated as algebraic constraints. Disjunctive expressions are typically converted into mixed integer constraints by using “big-M” constraints [1]. An alternative reformulation for treating disjunctions is the convex hull (chull) formulation, which achieves superior relaxation tightness but is rarely used due to its greater complexity and potential numerical difficulties [2]. Recent advances in GDP allow for automatic reformulation of optimization problems, e.g., by big-M or chull. Furthermore, dedicated GDP solution algorithms are now available [3]. Unlike conventional Branch and Bound or Outer Approximation algorithms, their logic-based counterparts can neglect inactive equations, reducing the size and complexity of subproblems. This is achieved by deactivating unused model equations during the solution procedure, as shown by Lee et al. [4]. This point is particularly interesting for chemical engineering, as a lot of time is spent computing NLP subproblems. Also, model formulation can have a large impact on the solution times of MINLP [1]. However, evaluating various model formulations tends to be rather tedious. Especially detailed model formulations that include rigorous thermodynamics and kinetics tend to increase the model size significantly. As a first step for further exploitation of GDP for process synthesis and process design, we developed a modeling environment and automatic code generation framework for GDP. This contribution aims at investigating different problem formulations for GDP in process design facilitated by the new framework. For maximum flexibility and independence from any given programming language, the modeling and problem formulation is implemented within MOSAICmodeling [5], a platform that allows for model formulation at the documentation level. Users formulate equations in LaTeX, which are then translated into MathML/XML preserving all relevant information while remaining as general as possible. The first step hereby consists in the definition of a suitable notation. This defines all possibly occurring variables and their indices and sets the basis of all MathML/XML operations. To include GDP into this workflow, already existing variable definitions were extended to also include logical / Boolean variables. Equations are created based on those extended notations: Basic logical operators – and (∧), or (∨), not (¬), implication (⇒), and equivalence (⇔) – were added to include logical expressions. Furthermore, disjunctions can be created by linking Boolean variables with single equations or sets of equations. The resulting systems defined in MathML/XML can be exported to any programming language using MOSAICmodeling’s UDLS feature [6], which has been extended tocapture connections between disjunctive, logical variables, and their associated equations, allowing for code export to GAMS, Julia, and Pyomo. Four different MINLP/GDP formulations were implemented in MathML/XML in MOSAICmodeling, exported, and evaluated within pyomo regarding their benefits in optimizing thermal separation problems. For this case study, the MINLP formulation of Kraemer et al. [7] is evaluated (pureMINLP), which determines the optimal column height to achieve desired product specifications while minimizing costs for a multicomponent distillation column. The MINLP formulation varies locations of feed, reflux, and boilup streams. Each separation stage is modeled rigorously applying thermodynamics of varying complexity. An alternative, GDP formulation (pureGDP) specifies disjunctions for each separation stage as in [QGrossmann2000rig]. The disjunctive variables decide which stages are active or not. For active stages, the stage formulation is the same as above. For inactive stages, a passthrough of liquid and vapor streams without thermodynamic calculations is applied. The feed location is modeled as a nested disjunction for the active stages. Two additional formulations, in between pureMINLP and pureGDP, apply different levels of relaxation: Feed relaxed GDP (fr-GDP) employs the disjunctive formulation for the stages, while applying pureMINLP’s formulation for the feed location. Decision variable GDP (dv-GDP) on the other hand, applies a formulation that translates directly into the pureMINLP formulation if the dv-GDP is relaxed by BigM and the M is chosen accordingly. The four different MINLP/GDP formulations are combined with two different implementations for thermodynamics calls: (1) explicit formulation using the Antoine equation for vapor pressures, linearized heats of evaporation, and constant specific heat capacities; (2) external thermodynamic function calls using a CAPE-OPEN interface with TEA as thermodynamics engine [8]. Note that the same thermodynamic models are used for explicit and external thermodynamics implementations to ensure comparability of the solutions. However, the interface supports any CAPE-OPEN compliant thermodynamics engine, allowing for even highly complex equations of state, such as, PC-SAFT. Future work will therefore also include non-idealities, which is not in scope of this contribution. To evaluate the performance of available GDP solvers, the formulations in MathML/XML are exported to pyomo. Exports to julia and GAMS were also developed. However, they currently lack support for dedicated GDP solvers. Three different GDP formulations (rGDP, cGDP and bGDP) were investigated with respect to runtime until an optimal solution was found. These formulations were benchmarked against a commonly used pMINLP formulation. The maximum number of stages for all columns were 32, of which 30 were choosable by the optimizer. We discovered that all GDP formulations perform worse or equal to the pMINLP formulation. However, some formulations outperform others. It was shown, that the inclusion of mass and energy balances of the separation stages into the global constraints is absolutely nescessary to robustly find the optimal stage number. Their inclusion into the disjuncts leads to a degradation of the outer approximation linearization and therefore hinders the solution process. It was also shown, that the bGDP formulation can greatly improve the solution time, by structuring the active stages into binary encoded blocks. This reduces the required binary variables, leading to improved solver Performance. Lastly, we were able to show, that the bGDP achieves pairity in runtime with the pMINLP benchmark, showing strong indications that bGDP can surpass the pMINLP formulation in future, more advanced optimization Problems. This study also shows that simply transforming an MINLP formulation into a GDP does not necessarily yield benefits. Runtime strongly varies across the three GDP formulations. To this end, further investigations for efficient exploitation of GDP for process synthesis is required. Our modeling framework in MathML/XML now supports fast formulation of highly complex GDPs and evaluation in a variety of supporting platforms (pyomo, julia, GAMS), speeding up the process of tailoring problem formulations. The investigated problem sizes are small, chosen as a proof of concept for formulation, code generation, and solution of GDPs. Given the runtime of the investigated problems, increasing system size is feasible. Future work will aim to increase the total system size and move towards more general process synthesis, potentially putting GDP problem runtime below that of relaxed MINLP. T2 - AIChE Annual Meeting CY - Boston, MA, USA DA - 02.11.2025 KW - Process Design KW - Process Optimization KW - Generalized Disjunctive Programming KW - Automatic Code Generation KW - Distillation Column PY - 2025 AN - OPUS4-65157 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Muñoz Gil, Hernán Darío T1 - Mixed Reality for Safe Operations: Connecting MR Devices to Process Automation and Documentation N2 - The industrial sector faces challenges in ensuring safety and efficiency of operation and maintenance tasks (OMT). These tasks involve manual interventions such as equipment inspections or sample extractions. OMT require workers to communicate with control rooms and follow strict operational protocols while managing physical and cognitive loads. Common challenges include safety risks, the difficulty of using safety gear, limited accessibility to information, inefficient communication, and high (human) error rates. While chemical plants traditionally rely on paper-based workflows to tackle the mentioned challenges, we present an approach that leverages digital checklists to model workflows, integrating them with industrial documentation and process automation systems. We combine these elements into contextualized workflows that are deployed in a Mixed Reality (MR) application allowing to support personnel with hands-free execution, real-time verification, and an MR-based human-machine interface (HMI). This integration enhances safety through automated system checks and MR-guided validation while reducing the cognitive load on personnel. We present an MR prototype based on a vacuum distillation sampling procedure that grants access to documentation, interfaces with process control systems, and manages workflows dynamically. Compared to conventional industrial checklists, our approach reduces errors by combining gamification, IT-based validation, and immersive task visualization while enabling hands-free task execution. As future work, we envision a generalized framework for rapidly incorporating new tasks, enhancing adaptability in industrial environments. This research paves the way for standardized MR solutions in chemical plant operations, ultimately improving efficiency, safety, and workforce engagement. T2 - Process Engineering and Materials Technology (PEMT) CY - Frankfurt am Main, Germany DA - 10.11.2025 KW - Safety KW - Mixed Reality KW - Operation & Maintenance KW - Digital workflows KW - Process control system PY - 2025 AN - OPUS4-65156 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Talis, Torben T1 - Applying Time Series Extrinsic Regression to Parameter Estimation Problems for Dynamic Models - an Alternative for Gradient-Free Approaches? N2 - Time series analysis is a well-established field within the machine learning community, with two prominent applications being time-series forecasting, i.e., surrogate models, predicting the next time step for the systems outputs, and time-series classification, where complete timeseries are mapped to discrete labels, e.g. a sensor is either working or defective. Time-Series Extrinsic Regression (TSER), however, is a method for predicting continuous, time-invariant variables from a time series by learning the relation between these underlying parameters and the complete dynamic time series of the outputs without focusing on the recent states. E.g., it can be used to predict the heart rate based on an ECG signal. TSER as a research field was only established in 2021, but it is gaining traction ever since and it is used e.g. in the field of manufacturing technology to predict steel surface roughness from laser reflection measurements. It is applied, when there are no models available. Parameter Estimation (PE) is a common task in chemical engineering. It is used to adjust model parameters to better fit existing dynamic models to experimental time series data. This becomes more challenging in higher dimensions and for dynamic systems, where sensitivity and identifiability may change over time. There already exists a multitude of algorithms to solve the problem, including second-order methods that leverage information from Jacobian and Hessian matrices, as well as gradient-free optimization techniques, such as particle swarm optimization (PSO) or simulated annealing. However, with the growing establishment of machine learning (ML) in an increasing number of domains, the question arises as to whether, and if so, how, ML in general and TSER in particular can be employed to solve PE problems. This study marks the first application of TSER to PE problems. A comparative analysis is conducted between TSER and PSO, in terms of prediction accuracy, computational cost and data efficiency. We investigate, whether it is viable to use TSER, when there is a model available. Our methodology to regress model parameters via ML builds on the typical assumption, that a structurally correct and rigorous model, which can be simulated at low cost, is available. At the beginning, the boundaries of the parameter space are defined. This space is then sampled using Sobol sequences and the model is simulated. The resulting trajectories, along with their corresponding parameters, constitute the training data set. These trajectories are transformed through application of the “RandOm Convolutional Kernel Transform” method resulting in novel features, which are subsequently used to train the regressor model. This regressor returns predictions for the parameters. In a case study, the method is applied to predict the heat transfer and kinetic parameters of a batch reactor based on simulated data. However, real measurements are often not continuously available, but are taken only at rare, discrete points in time, and different variables are measured at different, asynchronous intervals. This is also mimicked in the synthetic training data, so the influence of heterogeneity on the results can be shown and over- or undersampling strategies are applied to counteract the effect. T2 - European Symposium on Computer Aided Process Engineering 35 CY - Gent, Belgium DA - 06.07.2025 KW - Time Series Extrinsic Regression KW - Parameter Estimation KW - Machine Learning PY - 2025 AN - OPUS4-65155 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Khella, Shady T1 - Generating Design Options in Basic Engineering Using the Semantic Web N2 - Chemical process design begins with a pen and paper draft of a block flow diagram (BFD). This BFD is then further specified into a process flow diagram (PFD), which contains more detailed design decisions and elaborates on the type of unit operation or equipment to realize the functional process steps. Currently, most of this design workflow is done manually and relies on heuristics and engineering expertise. Instead, this contribution automates the generation of design alternatives in the early stages of process design using semantic web technologies. DEXPI Process, a newly developed standard, offers a semantic data model designed to formalize design information relevant for BFDs and PFDs. Using the DEXPI Process standard to formalize basic BFDs, our approach queries publicly available standards, reference data libraries (RDLs), and ontologies to generate design options that shall then be further investigated in simulation tools. The queries retrieve lists of equipment types capable of realizing respective functions. Throughout this process, our framework makes use of the SPARQL query language as part of the semantic web technology stack. The key benefit of this approach is its reliance on dynamic, linked open data rather than on hard-coded relationships between process steps and equipment. This ensures that data can be regularly updated and sourced from multiple providers. In doing so, our work showcases the importance of RDLs and linked open data, encouraging engineers, equipment vendors, and other stakeholders to adopt technologies for machine-accessible data. We demonstrate the functionality of this workflow by generating design alternatives for the well-known Tennessee Eastman process. In this case study, our system successfully identifies a range of feasible design alternatives, illustrating both the potential of the semantic web approach and the current limitations of available RDLs. While this work focuses on generating design options in basic engineering, future research aims to use semantic web technologies to generate P&ID base structures starting with information from BFDs and PFDs. T2 - PEMT 2025 - Annual Meeting of Process Engineering and Materials Technology CY - Frankfurt am Main, Germany DA - 10.11.2025 KW - Process Design KW - Semantic Web KW - DEXPI KW - Knowledge Graph KW - Artificial Inteligence PY - 2025 AN - OPUS4-65316 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Grunewald, Thomas T1 - Nichtelektrischer Explosionsschutz: Zündgefahren durch Funken - Grundlagen und Maßnahmen zum Explosionsschutz N2 - Geräte und Maschinen, die zur bestimmungsgemäßen Verwendung in explosionsgefährdeten Bereichen gemäß 2014/34/EU konstruktiv vorgesehen sind, muss in der europäischen Union eine Zündgefahrenbewertung durchgeführt werden. Dabei müssen alle 13 Zündquellen betrachtet werden. Eine Teilmenge der 13 Zündquellen sind die Gefahren von nichtelektrischen Zündquellen, zu denen auch die mechanischen Schlag-, Schleif- und Reibvorgänge gehören. Bei mechanischen Schlagvorgängen kommt es infolge des Zusammenstoßes zweier Werkstücke bzw. Bauteile zu einer Umwandlung der kinetischen Energie. Dabei erhöht sich die Temperatur der Werkstoffe an der Kontaktstelle und es kommt unter Umständen zu einem Abtrennvorgang kleiner Partikel erhöhter Temperatur. Sowohl die heißen Kontaktstellen (Zündquelle "heiße Oberflächen") als auch die abgetrennten Partikel (Zündquelle "mechanisch erzeugte Funken") können eine wirksame Zündquelle für ein explosionsfähiges Gasgemisch darstellen. Zur Festlegung von Grenzwerten wurden in der Norm DIN EN ISO 80079-36:2016 die Gasgemische anhand ihrer Explosionsgruppe klassifiziert und zu jeder Gruppe die maximale Energie des Schlagvorgangs festgelegt, unter derer die Entstehung einer wirksamen Zündquelle als unwahrscheinlich angenommen werden kann. Weitere Festlegungen von Grenzwerten für die kinetische Schlagenergie und geeignete Werkstoffpaarungen finden sich u.a. in der DIN EN 1755 (ex-geschützte Flurförderzeuge) und in der DIN EN 14986 (ex-geschützte Ventilatoren). T2 - Ausbildung zum Explosionsschutzbeauftragten CY - Essen, Germany DA - 20.01.2026 KW - Schlagfunken KW - Schleiffunken KW - Reibfunken KW - Explosionsschutz KW - Nichtelektrischer Explosionsschutz KW - Mechanischer Explosionsschutz PY - 2026 AN - OPUS4-65398 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Khella, Shady T1 - MR Datenhub - Das Rückgrat für die industrielle MR-Anwendung N2 - Der Einsatz von Mixed-Reality-(MR)-Anwendungen in der chemischen Prozessindustrie bietet das Potenzial für sicherere und effizientere Prozessauslegung, Anlagenwartung und Betriebsabläufe sowie für eine vereinfachte Schulung von Bedienpersonal. In der Praxis wird die Umsetzung jedoch häufig durch hohen Backend- und Frontend-Entwicklungsaufwand, die heterogene Landschaft an Datenquellen (z. B. Automatisierungssysteme und Engineering-Daten) sowie Anforderungen an Datenschutz, Pseudonymisierung und Rechtemanagement erschwert – insbesondere bei kleinen und mittleren Unternehmen. Diese Arbeit stellt den MR-Datenhub als wiederverwendbares Entwicklungs-Framework und Integrationsrückgrat für industrielle MR-Anwendungen vor. Der Ansatz kombiniert (1) ein vorkonfiguriertes, wiederverwendbares Backend- und Frontend-Framework, (2) standardisierte Schnittstellen zur Datenintegration sowie (3) einen Pseudonymisierungsdienst für personenbezogene und potenziell gesundheitsbezogene Daten, um DSGVO-konforme MR-Anwendungen zu unterstützen. Der Datenhub setzt auf eine GraphQL-basierte Serverarchitektur und ermöglicht die systematische Modellierung und Anbindung relevanter Datenquellen. Ergänzend wird eine Datenlandkarte vorgestellt, die domänenspezifische Standards und technische Frameworks systematisch erfasst, einordnet und strukturiert. Sie dokumentiert zudem die Mappings zwischen den Standards und spezifiziert deren Zuordnungsregeln. Der MR-Datenhub wird bereits in Projekten wie MR4SafeOperations und KeepCool eingesetzt und dient dort als Integrationsbasis für MR-gestützte Arbeitsabläufe. T2 - MR4B-Konferenz (Mixed Reality for Business) CY - Berlin, Germany DA - 17.07.2025 KW - Mixed Reality KW - Datenintegration KW - Digitalisierung KW - Standardisierung KW - Pseudonymisierung PY - 2025 AN - OPUS4-65327 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Karioui, Sarah T1 - Query Your Handbooks – Processing of Industrial Documentation with LLMs N2 - Operation and maintenance tasks in an industrial context are complex and often time- consuming processes. The manufacturer-provided manuals form the foundation for these processes. However, finding the required information from manuals remains an arduous task. During a maintenance task, the relevant information from plant documentation should be directly available. Along the individual process steps, questions may arise that require information from documentation. To make plant documentation queryable, a Retrieval Augmented Generation (RAG) system was developed. This technique is ideal for cases with little training data, in which fine-tuning of large language models (LLM) is ill-advised. The plant documentation serves as an external knowledge base for answering incoming questions with links to the original documents. Before the RAG development, comprehensive pre-processing of documents takes place, which here is divided into three main blocks: (1) Bill of materials are recognized, page references are stored, and tables are extracted. (2) Technical drawings are also recognized, their page reference is saved, and then passed to a multi-modal LLM (MMLLM), which extracts title and drawing number. (3) The manual is divided into chapters so that each query can be thematically assigned to one or more chapters where appropriate answers are sought. To provide further context, the operation and maintenance tasks are modeled using Business Process Model and Notation (BPMN), an international standard for representation of business processes. As a case study, the maintenance of an industrial pump is used. Along the maintenance process, questions are passed to LLM and RAG to provide concise answers. T2 - PEMT CY - Frankfurt am Main, Germany DA - 10.11.2025 KW - AI KW - ML KW - Maintenance PY - 2025 AN - OPUS4-65332 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Karioui, Sarah T1 - Handbuch2AR - Von technischer Dokumentation zur Interaktion in Betrieb und Wartung N2 - Der Vortrag stellt das Projekt „Handbuch2AR“ vor, das einen KI-gestützten, kontextbasierten Zugriff auf technische Dokumentation für Betriebs-, Wartungs- und Instandsetzungsaufgaben adressiert. Vorgestellt wird ein prototypischer Ansatz auf Basis von Retrieval-Augmented Generation (RAG), der Prozessmodelle der Wartungsaufgabe mit relevanten Inhalten aus Handbüchern verknüpft, um situationsabhängige Informationen bereitzustellen. Anhand mehrerer industrieller Anwendungsfälle wird der aktuelle Entwicklungsstand sowie das geplante Vorgehen zur qualitativen Evaluation der Ergebnisse erläutert. T2 - MR4B Konferenz CY - Berlin, Germany DA - 17.07.2025 KW - KI KW - Wartung KW - BPMN PY - 2025 AN - OPUS4-65333 LA - deu AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -