Modern day gas turbines are important sources of electrical power generation, and are regarded as the prime movers in aerospace, marine propulsion. The depletion of fossil fuel resources has paved the way for the usage of biofuel and renewable energy. The challenge to this is the fact that biofuel has been considered as an alternative to fossil fuel for power generation to ensure the reliability and dependability of renewable fuels in a complex multi-domain systems such as gas turbines. The main objective of this study is to optimize the fuel control system parameters of the Rowen gas turbine model and the turbine speed controllers. Furthermore, to render the Rowen model simulation relevant for biofuel applications, real-time experimental data on speed and loads were obtained. Thus, this paper proposes micro turbines that run on biofuel-based tuned Fuzzy Sugeno Large of Maxima (FSLOM). Four controllers were used to track the speed and load data. The experimental results show that, fuzzy controllers with online gain tuning, result in the best speed controllers performance (2.0- 1.05 Sec) for the biofuel operation compared to other controllers.

This paper proposes an active pulse-echo ultrasonic testing method to determine the lubricant condition in static mechanical components and assemblies. An ultrasonic inspection system was constructed to produce and receive back, high frequency ultrasonic pulses. Wavelet transform was used to de-noise the acquired signal and extract features from the feedback waveforms. Features data, from different samples, were analyzed and used to develop a fuzzy inference system to define the lubricant condition. Classification system was then examined, using grease samples, with known condition. The results indicated that the novel pulse-echo technique is a suitable method for the inspection of lubricants condition in various engineering systems.

We present a novel approach for the online learning of hand gestures in swarm robotic (multi-robot) systems. We address the problem of online feature learning by proposing Convolutional Max-Pooling (CMP), a simple feed-forward two-layer network derived from the deep hierarchical Max-Pooling Convolutional Neural Network (MPCNN). To learn and classify gestures in an online and incremental fashion, we employ a 2nd order online learning method, namely the Soft-Confidence Weighted (SCW) learning scheme. In order for all robots to collectively take part in the learning and recognition task and obtain a swarm-level classification, we build a distributed consensus by fusing the individual decision opinions of robots together with the individual weights generated from multiple classifiers. Accuracy, robustness, and scalability of obtained solutions have been verified through emulation experiments performed on a large data set of real data acquired by a networked swarm of robots.

We introduce Convolutional Neural Support Vector Machines (CNSVMs), a combination of two heterogeneous supervised classification techniques, Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). CNSVMs are trained using a Stochastic Gradient Descent approach, that provides the computational capability of online incremental learning and is robust for typical learning scenarios in which training samples arrive in mini-batches. This is the case for visual learning and recognition in multi-robot systems, where each robot acquires a different image of the same sample. The experimental results indicate that the CNSVM can be successfully applied to visual learning and recognition of hand gestures as well as to measure learning progress.