{"title":"Designing low complexity computational intelligence modules in FPGA using high level synthesis tools","authors":"I. Dogaru, R. Dogaru","doi":"10.1109/ISEEE.2017.8170679","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170679","url":null,"abstract":"High level synthesis tools offered by either FPGA (Field Programmable Gate Array) vendors or from the public domain are evaluated in order to generate efficient and low complexity computational intelligence modules. This paper reports specific issues and comparative synthesis results in implementing basic modules of the FSVC classifier (Fast Support Vector Classifier) and cellular automata starting from an algorithmic description in high level languages such as Python and C/C++. Two particular HLS tools were considered, namely VivadoHLS from Xilinx and MyHDL.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133932279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Direct current control by constant frequency hysteresis controller in active filtering systems","authors":"C. Suru, M. Dobriceanu, G. Subţirelu","doi":"10.1109/ISEEE.2017.8170659","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170659","url":null,"abstract":"The aim of this paper is the conversion of the classical hysteresis controller into a constant frequency hysteresis current controller. The classical alternative to the hysteresis controller is the proportional-integrative controller which gives constant switching frequency and overall better performances with a cost of comprehensive parameter tuning and sensitivity at driven system change. The hysteresis controller main advantage is the simplicity and robustness with the cost of variable switching frequency. The compromise between these two solutions is the constant switching frequency hysteresis controller. This goal can be achieved with a combination of the hysteresis comparator and the PWM modulator. The performances are somewhat less good and depend on the compensating capacitor voltage and PI voltage controller parameter adjustment but with the advantage of constant switching frequency. The regulator implementation was validated on a complete active filtering system implemented in Matlab Simulink.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133487302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Complexity evaluation of implementing the Support Vector Machine algorithm on mobile computing platforms","authors":"Daniel Armanda, Alin-Gabriel Cococi, R. Dogaru","doi":"10.1109/ISEEE.2017.8170701","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170701","url":null,"abstract":"SVM (Support Vector Machine), a state of the art classifier model is implemented on a computational mobile platform and its performances are evaluated against a low complexity classifier such as SFSVC (Super Fast Vector Support Classifier) on the same platform. For a better comparison, similar implementation for the two architectures are considered, such as using the same basic linear algebra library. Similar performances are obtained, but with the mention that the SFSVC algorithm has a more compact structure.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124001291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"High efficiency bridgeless AC/DC power supply with single step conversion for the data centers powered from the three-phase network","authors":"V. Berzan, Iurie Ermurachi","doi":"10.1109/ISEEE.2017.8170654","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170654","url":null,"abstract":"This paper analyzes a new architecture of the AC/DC type power supply for data centers. The source cumulates the following functions: three-phase current rectification, transformation of voltage parameters and DC voltage stabilization. The source ensures the reactive power compensation and does not distort the currents in the power three-phase network. The transfer of power from the alternating current network to the DC circuit is done at high frequency (over 100 kHz). The switching of semiconductor device is done in soft switching mode using Triangular Current Mode. The proposed algorithm for controlling semiconductor devices is performed at variable frequency in PWM mode. This leads to the reduction of loss in the switch regime of transistors. As a result, it is possible to increase the efficiency of the source to approximately 98%. The optimization of the switching mode of the semiconductor devices of the source with the power of about 0.5 kW does not require the use of radiators to ensure the thermal regime of the transistors. This leads, to the miniaturization of power supplies and the reduction of manufacturing costs. In the proposed source, the capacity of the direct current bus — the smoothing filter decreases a few times. At the same time it ensures the reduction pollution of the three-phase power supply circuit with superior harmonics. Verification of the proposed solution was done by mathematical simulations and by testing of a laboratory prototype of 2 kW. The AC supply voltage is 0.4 kV and the DC output voltage is 24 volts. The following mass indexes of the converter were obtained: the specific power 4 kW / kg.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131435838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Bidirectional static system for active D.C. traction substations: Theoretical and experimental evaluation","authors":"A. Bitoleanu, M. Popescu, C. Suru","doi":"10.1109/ISEEE.2017.8170635","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170635","url":null,"abstract":"This paper is focused on the presentation of a active filtering and regeneration system (SISFREG) developed for converting the DC traction substations in active substations. SISFREG will be connected between the catenary-line and the primary of the traction transformer, via a dedicated transformer. The main component of SISFREG is a shunt active power filter based on voltage source inverter structure, whose control guarantees the keeping of the prescribed voltage on the DC-side and the proper current at the inverter output by the indirect control of the supply current. The DC voltage controller is tuned in accordance with the Modulus Optimum criterion and the grid current controller is of hysterezis type. In order to verify the operation of the system and assess its performance, detailed computer simulation studies were conducted using the Matlab/Simulink package. Finally, a laboratory model was designed and build. In order to testing the system and showing its performances, an experimental setup was configured. The experimental results confirmed the good performance of the system during both traction/filtering and regeneration regimes.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126597168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Behavior of switched reluctance motors with saturated cores during load operation. Fractal analysis","authors":"I. Voncilă, I. Paraschiv, M. Costin, M. Voncila","doi":"10.1109/ISEEE.2017.8170643","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170643","url":null,"abstract":"This paper highlights the widespread use of fractal analysis, by way of example in the comparative study, of the longterm normal functioning of SRMs. In the paper we considered the behaviors of two classes of SRMs: — with linear core and nonlinear core, respectively — for three types of loads (resistant torques): constant torque, linear torque variable with shaft speed, variable torque with the square of speed, respectively. The aim of the paper is to promote a simple analysis method, which will enable the monitoring of the electrical drives on-line, in the near future. This creates the premises for predictive and preventive maintenance. The fractal dimension used in the analysis was determined for any acquired / simulated signal, using the box counting method in the Matlab toolbox.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114451770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Gaiceanu, S. Epure, C. Dache, Răzvan Buhosu, Iulian Ghenea, Cristian Vidan
{"title":"Laboratory power inverter platform for variable speed drive","authors":"M. Gaiceanu, S. Epure, C. Dache, Răzvan Buhosu, Iulian Ghenea, Cristian Vidan","doi":"10.1109/ISEEE.2017.8170689","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170689","url":null,"abstract":"In this paper a laboratory power inverter platform is proposed. The platform can operates autonomously by choosing an adequate signal processor or controlled by the powerful dSpace 1104 board, facilitating the rapid implementation of the design algorithms. At the same time, scalar and field oriented control of the three-phase asynchronous machine through the ControlDesk tool have been developed. Functional tests have been performed both on the control part and on the power section. In order to make safe tests of the modulation strategies the following have been taken into account: — operation of the voltage and current transducers both as independent device (to obtain the circuit information) and as an integral part of the control loop; — operation of the three-phase power IGBT module with the associated system circuits (galvanic isolation, drivers and control); — autonomous operation of the digital pulse width modulated signal (PWM) generating circuit. The experimental results confirm the proper design of the laboratory power inverter platform connected to the three-phase asynchronous machine.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114766038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Building inexpensive sensors based on chaos with good resolution and precision","authors":"H. Teodorescu, V. Cojocaru","doi":"10.1109/ISEEE.2017.8170667","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170667","url":null,"abstract":"The paper summarizes basic rules in the design of simple, low cost sensors based on chaotic dynamics, moreover to analyze the influence of the window comparators on the accuracy and precision of these sensors. We show that the comparator blocks in the circuit for determining the time-in-window parameters can be a significant source of errors that can be easily overlooked. A new version of chaotic circuit is also introduced.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122019777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"System for stress level monitoring","authors":"M. Cenușă, M. Poienar, Paţa Sergiu Dan","doi":"10.1109/ISEEE.2017.8170706","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170706","url":null,"abstract":"This paper presents a method of monitoring the stress level of a company's employees, pupils or students who are working on their computer. The functioning of sweat glands in certain areas of the body, such as palms, arms and soles, is activated by psychological stimuli, independent of external temperature or physical effort, a phenomenon that translates to the skin level by altering the electrical conductivity. Acquiring and monitoring this biosignal which gives us information on stress levels, lies at the heart of the developed and tested device.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128383888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Spatial load forecasting based on unstructured information processing and multi — Attribute deep learning","authors":"Ma Runze, Yu Peng, Huang Minxiang","doi":"10.1109/ISEEE.2017.8170672","DOIUrl":"https://doi.org/10.1109/ISEEE.2017.8170672","url":null,"abstract":"A spatial load forecasting method based on unstructured information processing and multi — attribute depth learning is proposed. In order to solve the problem that the unstructured attributes have great influence on the load density but can't be directly put into calculation, the natural language processing (NLP) technique is used to structure those attributes. In view of the on characterization of the high dimension attributes by traditional method, Stacked Denoising Auto Encoder (SDAE) deep learning network is used to forecast the spatial load density. And the Rectified Linear Unit(ReLU) function is used as the excitation function of the network as well as the network structure gets improved to overcome the gradient disappearance and over-fitting. The results of case study show that the method of spatial load forecasting is effective and feasible.","PeriodicalId":276733,"journal":{"name":"2017 5th International Symposium on Electrical and Electronics Engineering (ISEEE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127426927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}