A number of supporting subsystems is required for optimal exploitation of PEM fuel cells. In this manner, an effective online condition monitoring system provides the means for achieving requirements regarding reliability and durability. Contemporary commercial PEM fuel cell power systems are equipped with DC-DC converters and voltage monitors, which provide only basic information (i.e., voltage measurements at low sampling rates and resolution). The designed embedded system extends the basic functionalities of a DC-DC converter and voltage monitor with advanced condition monitoring capabilities. The originally devised concept of the designed system is the interconnection between the DC-DC converter and the voltage monitor. The designed system incorporates: • a DC-DC converter module capable of injecting excitation signals, which are required for the condition monitoring purposes, • a high resolution voltage monitor capable of acquiring voltage and current measurements on all of the cells within the fuel cell stack, and • a condition monitoring algorithm capable of detecting the presence of PEM fuel cell faulty operation. The designed embedded condition monitoring system aims at bridging the gap between the laboratory-grade measurement equipment (highly accurate and prohibitively expensive for the industrial applications) and contemporary commercial diagnostic systems (inexpensive, but capable of only basic monitoring). The system is jointly commercially viable and precise enough to perform sophisticated diagnostic measurements.
COBISS.SI-ID: 28568359
Fuel cells on diesel fuel are emerging technology with perspectives in transport. Since battery is an auxilliary source, it is important to properly select the capacity in order to enable system operation on various load profiles and operational horizon. For this purpose, a model was developed that describes the power unit behavior energy-wise, and includes the control system and other operational modes, such as startup and shutdown. Additionally, it allows arbitrary choice of battery size. Hence it is possible to simulate behavior of the entire system over a specified time period with an arbitrary load profile. The developed model then evaluates performance parameters, which serve to make an informed decision about the most suitable battery type and capacity for the given load profile. The achievement was published in one of the most prestigious journals in the fields of energy and fuels and chemical engineering, Journal of Applied Energy.
COBISS.SI-ID: 28028967
As faults alter the PEM fuel cell impedance characteristic, the electrochemical impedance spectroscopy is highly appropriate as a condition monitoring tool. The newly proposed methodology treats the impedance components among different frequencies as dependent complex random variables. The information about the fuel cell condition is incorporated into the dependence structure of these complex random variables. This dependence is described through the corresponding joint cumulative density function by employing copula functions. The benefits of such an approach are threefold: (i) the estimation of the joint cumulative density function requires only several measurements of a fuel cell under the fault-free condition, (ii) the procedure is computationally efficient, and (iii) the output of the copula function is directly used as an overall unit-free condition indicator.
COBISS.SI-ID: 28430119
Introduction of the ISA-88 standard in industrial batch-process control has brought many benefits, but it also often leads to repetition of information in recipes and to a low level of their reuse. This problem stems from the deficiencies of the standard batch-process control object model. A solution to the problem is proposed that is based on a more sophisticated object model of equipment and procedural control, with dynamically defined and potentially overlapping unit classes. The new concept, together with its elements, is described, and its use is illustrated and validated by means of a real batch control project. The validation demonstrates that the proposed approach has a significant advantage.
COBISS.SI-ID: 28429607
Standard bearing fault detection features are shown to be ineffective for estimating bearings remaining useful life (RUL). Addressing this issue, in this paper we propose an approach for bearing fault prognostics based on features describing the statistical complexity of the envelope of the generated vibrations and a set of Gaussian process(GP) models. The proposed features are sufficiently sensitive to the changes in the bearing condition and in the same time are sufficiently robust to variations in the operating conditions. Gaussian process models are nonparametric black-box models which differ from most other frequently used black-box identification approaches as they do not try to approximate the modeled system by fitting the parameters of the selected basis functions, but rather search for the relationships among measured data. In this paper the GP models are used for filtering noisy features and estimating the RUL based on filtered features.
COBISS.SI-ID: 27855399