Mohammed Abu Mallouh

Performance evaluation and tuning of a fuzzy control strategy for a fuel cell hybrid electric auto rickshaw

One of the most important factors that determine the performance of hybrid vehicles is the energy management and power distribution between the different energy sources. This paper reports on a project whose objective is to examine the potential and compare the performance of intelligent control strategies as applied to a fuel cell/battery hybrid electric auto rickshaw. A previous study found that a novel fuel cell load following strategy (FCLS) showed better results when compared to an equivalent consumption minimization strategy. In this paper, a fuzzy control strategy (FCS) is benchmarked against FCLS using a realistic drive cycle. It was found that after careful tuning, FCLS and FCS were equivalent in terms of achievable fuel economy.

Hybrid vehicular fuel cell/battery powertrain test bench: design, construction, and performance testing:

The development of hybrid vehicular power systems has been conducted for decades to improve transportation quality mainly in terms of environment pollution and fuel economy. Hence, hybrid electric vehicular systems are considered an attractive and potential solution in the long run to replace conventional combustion engine vehicles. In this paper, a scaled-down vehicular powertrain test bench is designed and constructed utilizing a hybrid fuel cell/battery energy sources. The performance of the proposed test bench is also investigated experimentally to explore the modes of operation for system components under various road conditions. Load-following energy management strategy is implemented experimentally in this hybrid configuration. The concepts that can be learned from such test bench are certainly essential for any future implementation on real full-size vehicles. In this study, it is shown that even though fuel cells have a good energy-to-weight ratio, they have a slow response and that is why they must be combined with other fast-response energy sources like a battery or supercapacitor. The test bench is mainly built to explore the implementation of various energy management strategies and control algorithms without the need to have a real vehicle and an automotive test track. In addition, it is an excellent platform for training highly qualified automotive engineers and university undergraduate students as well as automotive researchers.

AUTOMATED INTELLIGENT DIAGNOSTIC OF ALZHEIMER DISEASE BASED ON NEURO-FUZZY SYSTEM AND DISCRETE WAVELET TRANSFORM

Alzheimers disease (AD) is the deterioration of cognitive functions such as problem-solving, memory and reasoning that interferes with an individuals daily functioning. Symptoms are exhibited in accordance to the affected brain area (e.g. language and learning). Magnetic Resonance Imaging is the best diagnostic method to monitor the damage in brain tissues. Therefore, this paper proposed a hybrid method to segregate between the MRIs of healthy subjects and those diagnosed with AD. In this combined method, around 70 MRIs collected from local hospitals of Jordan are analyzed based on the use of Low-pass morphological filters and equalizer filter. Discrete wavelet transform (DWT) described as mathematical functions that discriminate data into different frequency components, and then each component is considered as resolution — scale matching. In this work, we used the best DWT type namely Haar because it is satisfactory for most of applications of image processing. The DWT then applied on the same MRIs where the entropies and energy values were extracted from each sub-band of the third-level wavelet coefficients to be fed into adaptive neuro-fuzzy inference system (ANFIS) classifier. The ANFIS was trained with the back-propagation gradient descent method in combination with least squares method. The combined method has demonstrated the best classification accuracy of 93% which can be reliably used for diagnosis purposes.

Artificial neural netwroks-based modeling for electrical actuated automotive cooling systems

In this study, artificial neural network-based models for electrical actuated automotive cooling systems are developed and analyzed. The proposed models are constructed to represent the dynamical behavior of advanced automotive cooling systems. Three types of artificial neural networks (ANNs) are constructed; MPL, Elman, and NARX networks where experimental data are utilized in the development process of the models. The proposed ANN models are developed and tested in simulation to approximate the performance of the actual system. Statistical results are demonstrated to show the effectiveness of the proposed ANNs.