In this paper an artificial neural network, which realizes a nonlinear adaptive control algorithm, has been applied in a control system of variable speed generating system. The speed is adjusted automatically as a function of load power demand. The controller employs a single layer neural network to estimate the unknown plant nonlinearities online. Optimization of the controller is difficult because the plant is nonlinear and no stationary. Furthermore, it deals with the situation where the plant becomes uncontrollable without any restrictive assumptions. In contrast to previous work  on the same subject, the number of neural networks has been reduced to only one network. The number of the neurons in a network structure as well as choosing certain design parameters was specified a priori. The computer test results have been presented to show performance of proposed neural controller.
The Low Temperature Joining Technique (LTJT) using silver compounds enables to significantly increase the thermal conductivity between joined elements, which is much higher than for soldered joints. However, it also makes difficult to measure the thermal conductivity of the joint. The Laser Flash Analysis (LFA) is a non-intrusive method of measuring the temperature rise of one surface of a specimen after excitation with a laser pulse of its other surface. The main limitation of the LFA method is its standard computer software, which assumes the dimensions of a bonded component to be similar to those of the substrate, because it uses the standard Parker’s formula dedicated for one-dimensional heat flow. In the paper a special design of measured specimen was proposed, consisting of two copper plates of different size joined with the sintered silver layer. It was shown that heat properties of these specimens can also be measured after modifying the LFA method. The authors adapted these specimens by masking the false heat signal sourced from the uncovered plate area. Another adaptation was introducing a correcting factor of the heat travel distance, which was calculated with heat-flow simulations and placed into the Parker’s formula. The heat-flow simulated data were compared with the real LFA measurement results, which enabled estimation of the joint properties, e.g. its porosity.
The article presents the analysis of the simulation test results for three variants of the power electronics used as interface between the power network and superconducting magnetic energy storage (SMES) with the following parameters: power of 250 kW, current of 500 A DC and voltage of 500 V DC. Three interface topologies were analyzed: two-level AC-DC and DC-DC converters; three-level systems and mixed systems combining a three-level active rectifier and a two-level DC-DC converter. The following criteria were considered: input and output current and voltage distortions, determined as THDi and THDu, power losses in power electronics components; cost of the semiconductor components for each topology and total cost of the interface. Results of the analysis showed that for high-power low-voltage and high-current power electronics systems, the most advantageous solution from a technical and economical perspective is a two-level interface configuration in relation to both AC-DC and DC-DC converters.
Fault detection and location are important and front-end tasks in assuring the reliability of power electronic circuits. In essence, both tasks can be considered as the classification problem. This paper presents a fast fault classification method for power electronic circuits by using the support vector machine (SVM) as a classifier and the wavelet transform as a feature extraction technique. Using one-against-rest SVM and one-against-one SVM are two general approaches to fault classification in power electronic circuits. However, these methods have a high computational complexity, therefore in this design we employ a directed acyclic graph (DAG) SVM to implement the fault classification. The DAG SVM is close to the one-against-one SVM regarding its classification performance, but it is much faster. Moreover, in the presented approach, the DAG SVM is improved by introducing the method of Knearest neighbours to reduce some computations, so that the classification time can be further reduced. A rectifier and an inverter are demonstrated to prove effectiveness of the presented design.
A simple analog circuit is presented which can play a neuron role in static-model-based neural networks implemented in the form of an integrated circuit. Operating in a transresistance mode it is suited to cooperate with transconductance synapses. As a result, its input signal is a current which is a sum of currents coming from the synapses. Summation of the currents is realized in a node at the neuron input. The circuit has two outputs and provides a step function signal at one output and a linear function one at the other. Activation threshold of the step output can be conveniently controlled by means of a voltage. Having two outputs, the neuron is attractive to be used in networks taking advantage of fuzzy logic. It is built of only five MOS transistors, can operate with very low supply voltages, consumes a very low power when processing the input signals, and no power in the absence of input signals. Simulation as well as experimental results are shown to be in a good agreement with theoretical predictions. The presented results concern a 0.35 1m CMOS process and a prototype fabricated in the framework of Europractice.