The Fault library - A new Modelica library allows for the systematic simulation of non-nominal system behavior

Porting Neural Ordinary Differential Equations (NeuralODEs), the combination of an artificial neural network and an ODE solver, to real engineering applications is still a challenging venture. However, we will show that Neural Functional Mock-up Units (NeuralFMUs), an evolved subgroup of NeuralODEs that contain Functional Mock-up Units (FMUs), are able to cope with these challenges. This paper briefly introduces to the topics NeuralODE and NeuralFMU and describes the procedure and considerations to apply this technique to a real engineering use case. Further, different workflows to apply NeuralFMUs dependent on tool capabilities and use case requirements are discussed. The presented method is illustrated with the creation of a Hybrid Twin of an hydraulic excavator arm, which has various challenges such as discontinuity, nonlinearity, oscillations and characteristic maps. Finally we will show, that the created Hybrid Twin, on basis of measurement data from a real system, gives more accurate results compared to a conventional simulation model based on first principles.

Section: Motivationmentioning

confidence: 99%

Paving the way for Hybrid Twins using Neural Functional Mock-Up Units

Thummerer,

Kolesnikov,

Gundermann

et al. 2023

“…Battery package: Battery management systems are used in industry for the protection and operation of Li-Ion battery packs only within safe operating conditions. Because of various requirements the battery management system has to monitor and protect each cell against over-/under-voltage, over-/undertemperature, over-current and other faults (Xing et al, 2011). This leads to the necessity of an uniform testing of the battery management system for every type of battery pack.…”

Section: Automotive Transmissionmentioning

confidence: 99%

Proceedings of the 2nd Japanese Modelica Conference Tokyo, Japan, May 17-18, 2018

2019

Model based product design requires both intuitive and effective user interface and powerful computing power. The presentation will contain a brief history of Modelica evolution and current status including some applications. Some new needs that are currently not covered will be discussed. New technical possibilities will be introduced, such as web apps for intuitive and effective user interaction and easy access, domain specific language extensions for advanced modeling capabilities and cloud computing for large scale simulation deployment..

“…In the following section the library developed for System Reliability Analysis (SRA) is described, whose components are the basis for the systematic fault augmentation of the vehicle model. The SRA library consists of a basic package containing elementary type and class definitions to parametrize faults, as described in (Gundermann et al, 2018). Beyond that, it is structured according to the structure for composable models in the Modelica ® language (Minhas et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Systematic Simulation of Fault Behavior by Analysis of Vehicle Dynamics

Kolesnikov

Tretsiak

Cameron

2019

Self Cite

A new library for System Reliability Analysis for systematic modelling of fault effects in multi-physical systems is introduced. The motivation is outlined as well as a description of the library structure with two helper libraries and an Add-In for semi-automatic fault augmentation. The library is exemplified in the automotive domain with the fault effect simulation of a vehicle model by using a new library for Driving Maneuvers. The vehicle model is systematically augmented with connector and component faults for the analysis of different fault effects in vehicle dynamics.