The paper presents a methodology for parametric fault clustering in analog electronic circuits with the use of a self-organizing artificial neural network. The method proposed here allows fast and efficient circuit diagnosis on the basis of time and/or frequency response which may lead to higher production yield. A self-organizing map (SOM) has been applied in order to cluster all circuit states into possible separate groups. So, it works as a feature selector and classifier. SOM can be fed by raw data (data comes from the time or frequency response) or some pre-processing is done at first. The author proposes conversion of a circuit response with the use of e.g. gradient and differentiation. The main goal of the SOM is to distribute all single faults on a two-dimensional map without state overlapping. The method is aimed for the development stage because the tolerances of elements are not taken into account, however single but parametric faults are considered. Efficiency analyses of fault clustering have been made on several examples e.g. a Sallen-Key BPF and an ECG amplifier. Testing procedure is performed in time and frequency domains for the Sallen-Key BPF with limited number of test points i.e. it is assumed that only input and output pins are available. A similar procedure has been applied to a real ECG amplifier in the frequency domain. Results prove a high efficiency in acceptable time which makes the method very convenient (easy and quick) as a first test in the development stage.
In this paper, the application of the Artificial Neural Network (ANN) algorithm has been used for testing selected specification parameters of voltage-controlled oscillator. Today, mixed electronic circuits specification time is an issue. An analog part of Phase Locked Loopis a voltage-controlled oscillator, which is very sensitive to variation of the technology process. Fault model for the integrated circuit voltage control oscillator (VCO) in ring topology is introduced and the before test stage classificatory is designed. In order to reduce testing time and keep the specification accuracy (approximation) on the high level, an artificial neural network has been applied. The features selection process and output coding for specification parameters are described. A number of different ANN have been designed and then compared with real specification of the VCO. The results obtained gives response in short time with high enough accuracy.
This paper presents the comparison of filtering methods – median filtration, moving average Kalman filtration and filtration based on a distance difference to determine the most accurate arm length for circular motion, as a model of wind turbine propellers movement. The experiments have been performed with the UWB technology system containing four anchors and a tag attached to 90cm arm that was rotated with speed up to 15.5 rad/s (as a linear speed of 50km/h). The trilateration concept based on the signal latency has been described in order to determinate the position of an object on circular trajectory. The main objective is the circle plane rotation (parallel and perpendicular) with respect to the anchors plane reference system. All research tasks have been performed for various cases of motion schemes in order to get the filtration method for object in motion under best accuracy goal. Filtration methods have been applied on one of two stages of the positioning algorithm: (1) on raw data got from the single anchor-tag (before trilateration); (2) on the position obtained from four anchors and tag (after trilateration). It has been proven that the appropriate filtering allows for higher location accuracy. Moreover, location capabilities with the use of UWB technology – shows prospective use of positioning of objects without access to other positioning forms (ex. GPS) in many aspects of life such as currently developing renewable, green energy sources like wind turbines where the circular motion plays an important role, and precise positioning of propellers is a key element in monitoring the work of the whole wind turbine.
The paper presents a method of obtaining short-termpositioning accuracy based on micro electro-mechanical system (MEMS) sensors and analysis of the results. A high-accuracy and fast-positioning algorithm must be included due to the high risk of accidents in cities in the future, especially when autonomous objects are taken into account. High-level positioning systems should consider a number of sub-systems such as global positioning system (GPS), CCTV – video analysis, a system based on analysis of signal strength of access points (AP), etc. Short-term positioning means that there are other locating systems with a sufficiently high degree of accuracy based on, e.g. a video camera, but the located object can disappear when it is hidden by other objects, e.g. people, things, shelves etc. In such a case, MEMS sensors can be employed as a positioning system. The paper examines typical movement profiles of a radio-controlled (RC) model and fundamental filtering methods in respect of position accuracy. The authors evaluate the complexity and delay of the filter and the accuracy of the positioning in respect of the current speed and phase of movement (positive acceleration, constant) of the object. It is necessary to know whether and how the length of the filter changes the position accuracy. It has been shown that the use of fundamental filters, which provide solutions in a short time, enables to locate objects with a small error in a limited time.