Andrea Schrems

  • Citations Per Year
Learn More
In part II of this paper two important methods for the monitoring procedure of the fuel cell (part I) are presented. First, a time delay estimation method, which allows a better data based modeling of the underlying fuel cell system. Second, the sequential probability ratio test (SPRT) which improves the fault detection results concerning over-detection and(More)
A data based modeling procedure for PEM (proton exchange membrane) fuel cell monitoring is presented. Assuming a black box system a set of prediction models is generated by extracting the relevant information from measured data. The models are used both for fault detection and isolation. The overall goal is the verification of fuel cell characteristics on a(More)
Data driven variable selection, without including physical knowledge, is an important prerequisite for many applications in the field of data based modeling. This paper deals with a novel approach to optimize the dimension of the input space by a combination of common variable selection methods with multivariate correlation analysis. The results are input(More)
This paper presents a novel approach to diagnosing faults in reciprocating compressor valves. Based on easily available vibration data, a transformation to a high-dimensional vector space is performed. By defining a metric in this vector space, the distance between the actual compressor state and a reference compressor state is calculated. Excessive(More)
This work presents a black-box input selection approach to reveal causal dependencies between process variables of complex industrial systems. This allows data based modeling with physically interpretable model structure. For this purpose a method is used which combines statistical and analytical approaches to find causal relations between measured data,(More)
  • 1