Chalmers Open Digital Repository

Välkommen till Chalmers öppna digitala arkiv!

Här hittar du:

Studentarbeten utgivna på lärosätet, såväl kandidatarbeten som examensarbeten på grund- och masternivå
Digitala specialsamlingar, som t ex Chalmers modellkammare
Utvalda projektrapporter

Forskningspublikationer, rapporter och avhandlingar hittar du i research.chalmers.se

Enheter i Chalmers ODR

Välj en enhet för att se alla samlingar.

Visar 1 - 2 av 2

Senast publicerade

Interoperable Medical Device Analytics in Microservice Architectures: Development of a Hybrid Electrochemical and Gaussian Process Regression Framework for Lithium Carbon Monoflouride Battery Prognostics
(2026) Erikmats, David; Celiker, Roni
Reliable battery prognostics for active implantable medical devices (IMDs), such as cardiac pacemakers and neurostimulators, are critical for safeguarding patient health and avoiding premature or delayed surgical replacements. However, primary lithium carbon monofluoride (Li/CFx) cells exhibit an exceptionally flat discharge plateau where the voltage gradient is minimal, making state-of-charge (SoC) estimation notoriously difficult. Furthermore, clinical telemetry data collected during routine hospital follow-ups is inherently sparse and irregular, causing traditional mechanistic tracking models to accumulate drift and pure data-driven estimators to fail. To address these challenges, this thesis proposes an interoperable software architecture and hybrid prognostic framework deployed as a decoupled, stateless microservice. Exposing asynchronous RESTful endpoints via FastAPI, the service integrates Pydantic data models for schema validation at the network boundary and utilizes HL7 FHIR standards to support interoperable data exchange across clinical hospital systems. The core analytical engine couples a physical second-order equivalent circuit model (ECM) prior with a Gaussian Process Regression (GPR) statistical corrector to dynamically compensate for parameter mismatch and patient-specific load profiles. Programmatic thermodynamic guardrails are implemented to strictly enforce monotonic capacity depletion. A containerized simulation environment orchestrated via Docker Compose was developed to validate the system. Across a retrospective cohort of n = 87 active devices, the bounded hybrid observer achieved a Mean Absolute Error (MAE) of 1.346% and a Root Mean Squared Error (RMSE) of 5.654%, outperforming mechanistic (4.611%) and data-driven (6.370%) baselines. In addition, automated stress-testing verified that the centralized exception boundary safely isolated 100% of injected network and data anomalies. Latency benchmarks demonstrated processing execution scaling from 0.382 s (N = 1) to 2.411 s (N = 1000) on a local container mesh. This demonstrates that the microservice architecture successfully balances robust software engineering with high-accuracy algorithmic execution, underscoring its potential utility as an analytical foundation for safety-critical clinical monitoring environments pending future in-vivo and clinical validation.
Tool for life cycle assessment of ship material and structures at the concept level stage using the industrial work breakdown structure
(2026) Galappaththi , Malaka Mihira
The International Maritime Organisation (IMO) and EU have taken wider steps towards decarbonisation of maritime industry with new set targets, introducing tariffs and penalties to motivate the maritime sector. Therefore, Life Cycle Assessment (LCA) is important part of the early design stage of ship design to evaluate the carbon emission impact of the design, which supports the investors, and designers to take decisions at the early stage of ship design. This thesis develops a tool for LCA of ship materials and structures at the concept level stage using the Industrial Work Breakdown Structure. The tool is developed based on the spreadsheet database with four main worksheets: SWBS, LCAI reference, LCA calculation, and result sheet. The tool follows cradle to grave LCA process including four stages: building, operation, maintenance, and scrapping. The tool presents the results as total global warming potential as carbon dioxide equivalent. The LCAI reference data base follows the EN 15804 module to store environmental impact data of the material. The tool applied to a case study Ro-Pax vessel and validated against four published reference vessels. The tool verified through compliance check, formula verification test, consistency check following the ISO 14040/14044 standards. A sensitivity analysis was carried out for the case study Ro-Pax vessel for seven categories. The case study result shows the major contributor for GWP factor is the operational stage (96.5%) for conventional fuelled vessel, and GWP intensity factor lies within the reference vessels. The tool produced maximum gap is 3.1% for four validation case studies. The sensitivity analysis of the main case study vessel shows that operational stage assumptions are dominating and highly sensitive. The tool is complying to the ISO 14040/14044 standards following the formula verification test and consistency check confirming correctness and uniformity. This study presents a generic LCA calculation tool to evaluate LCA at concept level stage for all commercial vessels. The tool is based on spreadsheet database, and it is incorporated with industrial work breakdown structure to organise material at concept level ship design. The tool has been verified and validated with independently published LCA studies. The Future work could focus on populating the LCAI reference database enabling automated import of material records to LCAI Reference database, program to direct import data from bill of materials.
Standstill Auto-Tuning of ADRC for Electro-Hydraulic Articulated Steering
(2026) Timpe, Niklas Leander Luca
Manual tuning of the steering controller for an autonomous articulated vehicle is time-consuming and scales poorly across vehicle variants. This thesis proposes an automated pipeline that identifies a small set of plant parameters and uses them to configure an error-based Active Disturbance Rejection Control (ADRC) law, without manual calibration. The steering plant is described by three blocks, an input deadband, a second- order linear time-invariant (LTI) core, and a mechanical output saturation. The pipeline runs three steps in sequence at vehicle standstill. First, the input deadband width is identified offline using a breakpoint grid search, and then statically compensated. Second, a step is applied to the plant and a nonlinear least-squares estimator fits the gain K and time constant τ of the LTI core to the recorded response. Third, an empirical tuning rule built on top of bandwidth parameterisation and half-gain tuning turns K and τ into the ADRC controller and Extended State Observer gains, after which the observer estimates and cancels unmodelled dynamics online during operation. The pipeline is verified on three test environments, a set of second-order plants with known parameters, an OpenModelica multi-body simulation model of the vehicle, and the real articulated vehicle as the final end-to-end check. Within the simulation environment, nine vehicle configurations span differences in chassis mass, cylinder bore, ground friction, valve flow capacity, and linkage geometry. Across these configurations the auto-tuned controllers achieved low tracking error, maintained control smoothness under measurement noise, and absorbed the shift in plant gain produced by payload and ground-friction changes away from the standstill operating point at which the parameters were identified. On the real vehicle the identification stages ran end to end and returned a deadband and gain comparable to the simulated family, but the closed loop did not track the reference sweep. The plant model omits a transport delay, assumed negligible, which leaves the auto-tuned bandwidth too high for the real plant, and a measured deadband hysteresis the model also omits adds to the gap. Lowering the bandwidth helps but does not close it, and accounting for these effects is left as future work.
AI-driven MPC/DMC: Automated Model Generation & Smart Control for the Future Process Industry
(2026) Forsman, Filippa
Traditionally, Model Predictive Control (MPC) controllers applied in refinery plants rely on linear prediction models derived from step response tests, under steady state operation. Modern process industries often produce large amounts of measurement data, which brings potential for AI-driven modeling instead. Through deep learning frameworks such as Long Short-Term Memory (LSTM), a model could learn system dynamics through historical input-output data. However, identifying dynamics can be challenging, since process data often is collected in closed-loop setting with an active controller. This thesis investigates an LSTM-based MPC controller applied to a pass-balancing problem in an industrial furnace. The LSTM prediction model was trained using either real historical process data or synthetically generated open-loop data based on a First Order Plus Dead-Time (FOPDT) process model. A Hybrid Physics-Guided LSTM-MPC was also evaluated, utilizing the FOPDT model to ensure the correct physics of the system while applying the LSTM model for nonlinearities and disturbances. The performance of the proposed LSTM-MPC controller was evaluated in comparison to the traditional linear MPC controller in a custom simulation environment. The results demonstrate that performance and stability of an AI-driven MPC strongly depend on the quality of the training data, particularly in closed-loop settings. The prediction performance in regards of MSE error of the LSTM network alone is not enough to determine if the model will do well in closed loop control, hence evaluation through simulation is essential. Furthermore, stable closed loop performance was achieved using synthetically generated training data, showing that LSTM-based MPC can be a promising approach for future nonlinear process control, and motivating further research into automated model generation for industrial control systems.
AEBS Event Classification Under Data Heterogeneity and Limited Trusted Labels
(2026) Liu, Yuchen; Li, Yiming
Advanced Emergency Braking System (AEBS) interventions can be classified according to whether the braking response was justified by the surrounding traffic situation. Accurate event classification is important for vehicle safety and driver trust, while fleet-scale assessment is challenging because most events are labeled by deterministic signal-based scripts and trusted video labels are scarce, costly, and privacy-sensitive. In addition, event data may exhibit distributional heterogeneity across operating contexts. This thesis investigates AEBS full-braking event classification under these challenges of data heterogeneity and limited trusted labels. The study uses logged full-braking events from Volvo heavy-duty vehicles from different countries under scarce trusted video labels. Within a Machine Learning framework, the task is formulated as binary multivariate Time-Series Classification. A one-dimensional CNN is used for supervised learning, unsupervised clustering is used to examine event structure, and Mean Teacher is used for semi-supervised learning. Federated Learning is evaluated with FedAvg and FedMeanTeacher to assess country-partitioned collaboration. Country partitions were strongly imbalanced, with the two largest accounting for 62% of the selected events and the three smallest accounting for 9%. Scriptgenerated outcomes agreed with 75% of the trusted FP events, while agreement with trusted TP events was 94%. Supervised classification achieved a Macro-F1 of 0.9995 on script-generated outcomes and 0.9374 on trusted video labels. FedMean- Teacher reduced the cross-country Macro-F1 standard deviation to 0.0343 compared with 0.1796 for local semi-supervised learning, while its trusted-label Macro-F1 remained lower than that of centralized learning, 0.7867 versus 0.8523. Overall, scriptgenerated outcomes enabled near-perfect reproduction of the deterministic labeling procedure, while scarce trusted labels, especially for FP events, limit correctnessoriented conclusions.