• Journal of Information Processing Systems
• /
• 제19권2호
• /
• pp.258-266
• /
• 2023

Aiming at the problems of poor customer satisfaction and poor accuracy of customer classification, this paper proposes a customer classification model based on speech recognition. First, this paper analyzes the temporal data characteristics of customer demand data, identifies the influencing factors of customer demand behavior, and determines the process of feature extraction of customer voice signals. Then, the emotional association rules of customer demands are designed, and the classification model of customer demands is constructed through cluster analysis. Next, the Euclidean distance method is used to preprocess customer behavior data. The fuzzy clustering characteristics of customer demands are obtained by the fuzzy clustering method. Finally, on the basis of naive Bayesian algorithm, a customer demand classification model based on speech recognition is completed. Experimental results show that the proposed method improves the accuracy of the customer demand classification to more than 80%, and improves customer satisfaction to more than 90%. It solves the problems of poor customer satisfaction and low customer classification accuracy of the existing classification methods, which have practical application value.

• Nuclear Engineering and Technology
• /
• 제56권6호
• /
• pp.2332-2342
• /
• 2024

Lead-cooled fast reactors (LFRs) have a wide range of application scenarios, which require the thermal-hydraulic characteristics of LFRs to be reliable. In the present paper, the Lead-cooled fast reactor Thermal-Hydraulic Analysis Code LETHAC was developed, including the models of pipe, heat exchanger, and pool. To verify the correctness of LETHAC, two experimental facilities and three experimental cases were selected, including GFT and PLOFA tests for NACIE-UP and Test-1 for CIRCE. The calculated results show the same and consistent trend with the experimental data, but there are some discrepancies. It can be found that LETHAC is suitable and reliable in predicting the transient behavior of lead-cooled system.

• 정보처리학회논문지D
• /
• 제19D권4호
• /
• pp.281-292
• /
• 2012

스마트 폰과 같은 모바일 기기에서 동작하는 응용 소프트웨어는 제한된 배터리 용량으로 인하여 안정적인 서비스를 지속적으로 제공하는데 어려움을 갖는다. 과거에는 배터리의 수명을 연장 시키거나 소모전력이 적은 하드웨어 장치들을 개발하는 것으로 모바일 기기의 소모전력을 관리하였다. 그러나 시스템에 탑재되는 소프트웨어가 복잡해짐에 따라 소프트웨어에 대한 소모전력 분석 연구도 관심을 갖게 되었다. 이러한 연구들 중에서 모델 기반의 소모전력 분석은 코드가 개발되기 이전에 미리 소모전력을 분석하고, 분석 결과를 기반으로 소프트웨어를 개발한다는 측면에서 소모전력 감소를 위한 하나의 중요한 전략으로 인식되어 오고 있다. 따라서 본 논문에서는 소프트웨어의 행위 모델인 UML의 상태기계(State Machine) 다이어그램을 이용하는 소모전력 분석 기법을 제안한다. 제안하는 분석기법은 상태기계 다이어그램을 페트리 넷으로 변환하고, 이의 시뮬레이션을 통해 소모전력을 예측하게 된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 D
• /
• pp.2664-2666
• /
• 2000

In this paper, the novel sliding mode control method with virtual state is compared to the SMC with co-states. The former method is shown to have advantage in the respect of computation.

• Journal of Electrical Engineering and Technology
• /
• 제7권5호
• /
• pp.689-697
• /
• 2012

This paper proposes a new coordinated voltage control scheme between STATCOM (Static Synchronous Compensator) and reactive power compensation devices, such as shunt elements(shunt capacitor and shunt reactor) and ULTC(Under-Load Tap Changer) transformer in a local substation. If STATCOM and reactive power compensators are cooperatively used with well designed control algorithm, the target of the voltage control can be achieved in a suddenly changed power system. Also, keeping reactive power reserve in a STATCOM during steady-state operation is always needed to provide reactive power requirements during emergencies. This paper describes the coordinative voltage control method to keep or control the voltage of power system in an allowable range of steady-state and securing method of momentary reactive power reserve using PSS/E with Python. In the proposed method of this paper, the voltage reference of STATCOM is adjusted to keep the voltage of the most sensitive bus to the change of loads and other reactive power compensators also are settled to supply the reactive power shortage in out range of STATCOM to cope with the change of loads. As the result of simulation, it is possible to keep the load bus voltage in limited range and secure the momentary reactive power reserve in spite of broad load range condition.

• Journal of Power Electronics
• /
• 제11권4호
• /
• pp.471-478
• /
• 2011

This paper addresses the establishment of a kVA-range plug-in hybrid electrical vehicle (PHEV) integration test platform and associated issues. Advancements in battery and power electronic technology, hybrid vehicles are becoming increasingly dependent on the electrical energy provided by the batteries. Minimal or no support by the internal combustion engine may result in the vehicle being occasionally unable to recharge the batteries during highly dynamic driving that occurs in urban areas. The inability to sustain its own energy source creates a situation where the vehicle must connect to the electrical grid in order to recharge its batteries. The effects of a large penetration of electric vehicles connected into the grid are still relatively unknown. This paper presents a novel methodology that will be utilized to study the effects of PHEV charging at the sub-transmission level. The proposed test platform utilizes the power hardware-in-the-loop (PHIL) concept in conjunction with high-fidelity PHEV energy system simulation models. The battery, in particular, is simulated utilizing a real-time digital simulator ($RTDS^{TM}$) which generates appropriate control commands to a power electronics-based voltage amplifier that interfaces via a LC-LC-type filter to a power grid. In addition, the PHEV impact is evaluated via another power electronic converter controlled through $dSPACE^{TM}$, a rapid control systems prototyping software.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.635-656
• /
• 2019

In this paper, we investigate the degrees of freedom (DoF) of a multi-cell multi-user multiple-input multiple-output (MIMO) interference broadcast channel (IBC) with non-cooperation distributed base stations (BS), where each BS serves users of its corresponding cell. When all BSs simultaneously transmit their own signals over the same frequency band in the MIMO IBC, the edge users in each cell will suffer the inter-cell interference (ICI) and inter-user interference (IUI) signals. In order to eliminate the ICI and IUI signals, a distributed space time interference alignment (DSTIA) approach is proposed where each BS has only limited access to distributed moderately-delay channel state information at the transmitter (CSIT). It is shown that the DSTIA scheme can obtain the appreciate DoF gains. In addition, the DoF upper bound is asymptotically achievable as the number of antenna at each BS increases. It is shown that the DSTIA method can get DoF gains over other interference alignment schemes with delayed CSIT in literature. Moreover, the DSTIA method can attain higher DoFs than the IA schemes with global CSIT for certain antenna configurations.

• International Journal of Automotive Technology
• /
• 제8권3호
• /
• pp.361-373
• /
• 2007

In previous work, an approach based on maximizing the efficiency of an internal combustion engine while ignoring the power conversion efficiency of other powertrain components, such as the electric motor and power battery or ultracapacitor, was implemented in the steady-state optimization of an internal combustion engine for hybrid electric vehicles. In this paper, a novel control algorithm was developed and successfully justified as the basis for maximal power conversion efficiency of overall powertrain components. Results indicated that fuel economy improvement by 3.9% compared with the conventional control algorithm under China urban transient-state driving-cycle conditions. In addition, using the view of the novel control algorithm, maximal power generation of the electric motor can be chosen.

• ETRI Journal
• /
• 제31권6호
• /
• pp.806-808
• /
• 2009

A new computationally efficient algorithm-based propagator method for two-dimensional (2-D) direction-of-arrival (DOA) estimation is proposed, which uses two parallel uniform linear arrays. The algorithm takes advantage of the special structure of the array which enables 2-D DOA estimation without pair matching. Simulation results show that the proposed algorithm achieves very accurate estimation at a computational cost 4 dB lower than that of standard methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 A
• /
• pp.91-93
• /
• 1998

In this paper 30 kVA superconducting generator's transient-state electromagnetic analysis by FEM is described. The transient-state analysis by moving air gap technique was performed to analyze its 3 phase sudden short circuit characteristics. External circuit components were connected to generator model with end-winding resistance and inductance.