Search

The landscape of tools available for model-based development of Cyber-Physical Systems (CPSs) is vast, encompassing numerous specialized tools designed to support models at the component-level. In reality, the different parts of the system represented by these component-level models are often physically tightly coupled and interdependent, and the models themselves are subject to change and evolve over time. However, due to the lack of interoperability between tools it is often challenging to integrate component-level models into larger system simulations and to support model evolution across the entire product lifecycle. In order to streamline the system development process and allow for seamless integration of models and a variety of development tools, a comprehensive integrated model-based development environment is required. To address these challenges, this thesis contributes a model-based tool integration approach and an ontology-driven automated traceability method that utilizes a standardized integration convention, language-neutral model transformation technology, and co-simulation technique to integrate several tools for CPSs development as well as to automatically establish and maintain traceability between heterogeneous artifacts created throughout the product development lifecycle. The applicability, validity, and usefulness of these approaches and the developed prototypes are demonstrated through industrial-relevant use case examples. In particular, the main contributions presented in this thesis are summarized as follows: Design, development, and validation of an ontology-driven approach for multidisciplinary collaborative modeling and traceability support throughout the development process for CPSs; Design, development, and validation of a general approach for modeling a composite model containing several tool-specific simulation component-level models which can be integrated, connected, and simulated using the Transmission Line Modeling (TLM) co-simu, Funding agencies: The research presented in this thesis has been supported by Vinnova in the ITEA2 MODRIO, OPENCPS, and EMPHYSIS projects, by EU in the H2020 INTO-CPS project and, by the CleanSky Joint Undertaking project PyModSimA (JTI-CS-2013-2- SGO-02-064). Support from the Swedish Government has also been received from the ELLIIT project, and the Swedish Strategic Research Foundation (SSF) in the Proviking EDOP project. The Open Source Modelica Consortium supports the continuous development of the OpenModelica framework.

ROS2 is an increasingly popular middleware framework for developing robotic applications. A ROS2 applicationbasically is composed of nodes that run concurrently and can be deployed distributedly. ROS2 nodes communicatewith each other through asynchronous interfaces; they reside in memory and wait to respond events that circulatearound the system during the interactions between the robot(s) and the environment. Rebeca is an actor-basedlanguage for modelling asynchronous, concurrent applications. Timed Rebeca added timing features to Rebeca todeal with timing requirements of real-time systems. The similarities in the concurrency and message-basedasynchronous interactions ofreactive nodes justify the relevance of using Timed Rebeca to assist the developmentand verification of ROS2 applications. Model-based development and model checking allow quicker prototypingand earlier detection ofsystem errors without the requirement of developing the entire real system. However, thereare challenges in bridging the gaps between continuous behaviours in a real robotic system and discrete behavioursin a model, between complex computations in a robotic system and the inequivalent programming facilities in amodelling language. There have been previous attempts in mapping Rebeca to ROS, however they could not beput into practice due to over-simplifications or improper modelling approaches. This thesis addresses the problemfrom a more systematic perspective and has been successful in modelling a realistic multiple autonomous mobilerobots system, creating corresponding ROS2 demonstration code, showing the synchronization between the modeland the program to prove the values of the model in driving development and automatic verification of correctnessproperties (freedom ofdeadlocks, collisions, and congestions). Stability of model checking results confirms designproblems that are not always detected by simulation. The modelling principles, modelling and implementingtechniques that are inv

The discovery of complete ammonium oxidation (comammox) has redefined the perception of the nitrification process which plays a vital part in biological nitrogen removal (BNR) from wastewater. Despite the reported detection or cultivation of comammox bacteria in biofilm or granular sludge reactors, limited attempts have been made to enrich or assess comammox bacteria in floccular sludge reactors with suspended growth of microbes, which are most extensively applied at wastewater treatment plants. Therefore, through making use of a comammox-inclusive bioprocess model reliably evaluated using batch experimental data with joint contributions of different nitrifying guilds, this work probed into the proliferation and functioning of comammox bacteria in two commonly-used floccular sludge reactor configurations, i.e., continuous stirred tank reactor (CSTR) and sequencing batch reactor (SBR), under mainstream conditions. The results indicated that compared with the studied SBR, the CSTR was observed to favor the enrichment of comammox bacteria through maintaining a sufficient sludge retention time (40-100 d) while avoiding an extremely low DO level (e.g., 0.05 g-O2/m3), irrespective of the varied influent NH4+-N of 10-100 g-N/m3. Meanwhile, the inoculum sludge was found to greatly influence the start-up process of the studied CSTR. By inoculating the CSTR with a sufficient amount of sludge, finally enriched floccular sludge with a high abundance of comammox bacteria (up to 70.5 %) could be rapidly obtained. These results not only benefitted further investigation and application of comammox-inclusive sustainable BNR technologies but also explained, to some extent, the discrepancy in the reported presence and abundance of comammox bacteria at wastewater treatment plants adopting floccular sludge-based BNR technologies.

For the development of modern software-intensive systems, a large number of development artifacts are created and maintained to design and implement their intended structure and behavior. In this thesis, we consider continuous model-based development settings in which models and other development artifacts are developed incrementally, in short development cycles. Inconsistencies between these development artifacts occur continuously throughout the system's development and maintenance, due to the incremental nature of the development of these artifacts. However, when not known and never resolved, such inconsistencies may ultimately cause failures in developed systems. Therefore, consistency checking across development artifacts is often desirable. Consistency checking approaches face challenges such as adoption in existing engineering settings, the potential informality and incompleteness of models and other development artifacts, as well as the need for shorter development cycles. We show a tight coupling between introducing short development cycles and the need for increased support for consistency checking across models and other development artifacts. From a surveyed set of industrial settings, we identify the need for lightweight consistency-checking approaches. Four aspects that make a consistency checking approach lightweight are formulated on the basis of the surveyed industrial settings. We then study specific challenges to developing consistency checks in four concrete industrial settings. We summarize our experiences in these settings in reference schemas showing the steps of creation and adoption of lightweight consistency checks from various starting points. In summary, this thesis presents contributions to lightweight consistency checking in industrial settings and ultimately aims to facilitate the adoption of continuous model-based development.