• Title/Summary/Keyword: Hybrid Control System

Search Result 1,377, Processing Time 0.03 seconds

Machine learning approaches for wind speed forecasting using long-term monitoring data: a comparative study

  • Ye, X.W.;Ding, Y.;Wan, H.P.
    • Smart Structures and Systems
    • /
    • v.24 no.6
    • /
    • pp.733-744
    • /
    • 2019
  • Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

Enhancing Wind Speed and Wind Power Forecasting Using Shape-Wise Feature Engineering: A Novel Approach for Improved Accuracy and Robustness

  • Mulomba Mukendi Christian;Yun Seon Kim;Hyebong Choi;Jaeyoung Lee;SongHee You
    • International Journal of Advanced Culture Technology
    • /
    • v.11 no.4
    • /
    • pp.393-405
    • /
    • 2023
  • Accurate prediction of wind speed and power is vital for enhancing the efficiency of wind energy systems. Numerous solutions have been implemented to date, demonstrating their potential to improve forecasting. Among these, deep learning is perceived as a revolutionary approach in the field. However, despite their effectiveness, the noise present in the collected data remains a significant challenge. This noise has the potential to diminish the performance of these algorithms, leading to inaccurate predictions. In response to this, this study explores a novel feature engineering approach. This approach involves altering the data input shape in both Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) and Autoregressive models for various forecasting horizons. The results reveal substantial enhancements in model resilience against noise resulting from step increases in data. The approach could achieve an impressive 83% accuracy in predicting unseen data up to the 24th steps. Furthermore, this method consistently provides high accuracy for short, mid, and long-term forecasts, outperforming the performance of individual models. These findings pave the way for further research on noise reduction strategies at different forecasting horizons through shape-wise feature engineering.

A SE Approach for Machine Learning Prediction of the Response of an NPP Undergoing CEA Ejection Accident

  • Ditsietsi Malale;Aya Diab
    • Journal of the Korean Society of Systems Engineering
    • /
    • v.19 no.2
    • /
    • pp.18-31
    • /
    • 2023
  • Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

Recent Progress in Air-Conditioning and Refrigeration Research : A Review of Papers Published in the Korean Journal of Air-Conditioning and Refrigeration Engineering in 2015 (설비공학회 분야의 최근 연구 동향 : 2015년 학회지 논문에 대한 종합적 고찰)

  • Lee, Dae-Young;Kim, Sa Ryang;Kim, Hyun-Jung;Kim, Dong-Seon;Park, Jun-Seok;Ihm, Pyeong Chan
    • Korean Journal of Air-Conditioning and Refrigeration Engineering
    • /
    • v.28 no.6
    • /
    • pp.256-268
    • /
    • 2016
  • This article reviews the papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering during 2015. It is intended to understand the status of current research in the areas of heating, cooling, ventilation, sanitation, and indoor environments of buildings and plant facilities. Conclusions are as follows. (1) The research works on the thermal and fluid engineering were carried out in the areas of flow, heat and mass transfer, cooling and heating, and air-conditioning, the renewable energy system and the flow inside building rooms. Research issues dealing with air-conditioning machines and fire and exhausting smoke were reduced. CFD seems to be spreading to more research areas. (2) Research works on heat transfer area were carried out in the categories of heat transfer characteristics, pool boiling and condensing heat transfer and industrial heat exchangers. Researches on heat transfer characteristics included the economic analysis of GHG emission, micro channel heat exchanger, effect of rib angle on thermal performance, the airside performance of fin-and-tube heat exchangers, theoretical analysis of a rotary heat exchanger, heat exchanger in a cryogenic environment, the performance of a cross-flow-type, indirect evaporative cooler made of paper/plastic film. In the area of pool boiling and condensing, the bubble jet loop heat pipe was studied. In the area of industrial heat exchangers, researches were performed on fin-tube heat exchanger, KSTAR PFC and vacuum vessel at baking phase, the performance of small-sized dehumidification rotor, design of gas-injection port of an asymmetric scroll compressor, effect of slot discharge-angle change on exhaust efficiency of range hood system with air curtain. (3) In the field of refrigeration, various studies were carried in the categories of refrigeration cycle, alternative refrigeration/energy system, system control. In the refrigeration cycle category, a cold-climate heat pump system, $CO_2$ cascade systems, ejector cycles and a PCM-based continuous heating system were investigated. In the alternative refrigeration/energy system category, a polymer adsorption heat pump, an alcohol absorption heat pump and a desiccant-based hybrid refrigeration system were investigated. In the system control category, turbo-refrigerator capacity controls and an absorption chiller fault diagnostics were investigated. (4) In building mechanical system research fields, eighteen studies were reported for achieving effective design of the mechanical systems, and also for maximizing the energy efficiency of buildings. The topics of the studies included energy performance, HVAC system, ventilation, and renewable energies, piping in the buildings. Proposed designs, performance tests using numerical methods and experiments provide useful information and key data which can improve the energy efficiency of the buildings. (5) The field of architectural environment was mostly focused on indoor environment and building energy. The main researches of indoor environment were related to the user and location awareness technology applied dimming lighting control system, the lighting performance evaluation for light-shelves, the improvement evaluation of air quality through analysis of ventilation efficiency and the evaluation of airtightness of sliding and LS window systems. The subjects of building energy were worked on the energy saving estimation of existing buildings, the developing model to predict heating energy usage in domestic city area and the performance evaluation of cooling applied with economizer control. The studies were also performed related to the experimental measurement of weight variation and thermal conductivity in polyurethane foam, the development of flame spread prevention system for sandwich panels, the utilization of heat from waste-incineration facility in large-scale horticultural facilities.

Modified Fold Type Helicone Reflector for Efficient Satellite TT&C Having Variable Coverage Area (가변 커버리지를 갖는 위성 관제용 접이식 헬리콘 반사체 안테나 성능 연구)

  • Lee, Sang-Min;Lee, Woo-Kyung
    • The Journal of Korean Institute of Electromagnetic Engineering and Science
    • /
    • v.20 no.9
    • /
    • pp.914-923
    • /
    • 2009
  • Helix antennas have been widely applied to satellite TT&C, data communication and GPS receiver systems onboard military, remote sensing and communication purpose satellites. The helix antennas are known to be convenient to control impedance and radiation coverage characteristics with a maximum directivity in satellite z-axis. Waveguide horn is commonly used for radar system that needs ultra-wideband pulse for exploration ground radar and electromagnetic disability measurement etc. It has high efficiency and low reflection characteristics provided by the low-profile shape and suppressed radiation distortion. In this paper, a waveguide horn structure incorporated with helix antenna design is proposed for satellite applications that require ultra-wideband pulse radar and high rate RF data communication link to ground station over wide coverage area. The main design concern is to synthesize variable beam forming pattern based on modified horn-helix combination helicone structure such that multi-mission antenna is implemented applicable for TT&C, earth observation, high data rate transmission. Waveguide horn helps to reduce the overall antenna structure size by introduction fold type reflector connected to the tapered helix antenna. The next generation KOMPSAT satellite currently under development requires high-performance precision attitude control system. We present an initial design of a hybrid hern-helix antenna structure suitable for efficient RF communication module design of multi-purpose satellite systems.

Educational Framework for Interactive Product Prototyping

  • Nam Tek-Jin
    • Archives of design research
    • /
    • v.19 no.3 s.65
    • /
    • pp.93-104
    • /
    • 2006
  • When the design profession started, design targets were mainly static hardware centered products. Due to the development of network and digital technologies, new products with dynamic and software-hardware hybrid interactive characteristics have become one of the main design targets. To accomplish the new projects, designers are required to learn new methods, tools and theories in addition to the traditional design expertise of visual language. One of the most important tools for the change is effective and rapid prototyping. There have been few researches on educational framework for interactive product or system prototyping to date. This paper presents a new model of educational contents and methods for interactive digital product prototyping, and it's application in a design curricula. The new course contents, integrated with related topics such as physical computing and tangible user interface, include microprocessor programming, digital analogue input and output, multimedia authoring and programming language, sensors, communication with other external devices, computer vision, and movement control using motors. The final project of the course was accomplished by integrating all the exercises. Our educational experience showed that design students with little engineering background could learn various interactive digital technologies and its' implementation method in one semester course. At the end of the course, most of the students were able to construct prototypes that illustrate interactive digital product concepts. It was found that training for logical and analytical thinking is necessary in design education. The paper highlights the emerging contents in design education to cope with the new design paradigm. It also suggests an alterative to reflect the new requirements focused on interactive product or system design projects. The tools and methods suggested can also be beneficial to students, educators, and designers working in digital industries.

  • PDF

Impacts of green technologies in distribution power network

  • Suwanapingkarl, Pasist;Singhasathein, Arnon;Phanthuna, Nattaphong;Boonthienthong, Manat;Srivallop, Kwanchanok;Ketken, Wannipa
    • International Journal of Advanced Culture Technology
    • /
    • v.3 no.1
    • /
    • pp.90-100
    • /
    • 2015
  • Green technologies such as renewable energy resources, Electric Vehicles and Plug-in Hybrid Electric Vehicles (EVs/PHEVs), electric locomotives, etc. are continually increasing at the existing power network especially distribution levels, which are Medium Voltage (MV) and Low Voltage (LV). It can be noted that the increasing level of green technologies is driven by the reduction emission policies of carbon dioxide ($CO_2$). The green technologies can affect the quality of power, and hence its impacts of are analysed. In practical, the environment such as wind, solar irradiation, temperature etc. are uncontrollable, and therefore the output power of renewable energy in that area can be varied. Moreover, the technology of the EVs/PHEVs is still developed in order to improve the performance of supply and driving systems. This means that these developed can cause harmonic distortion as the control system is mostly used power electronics. Therefore, this paper aims to analyse the voltage variation and harmonic distortion in distribution power network in urban area in Europe due to the combination between wind turbine, hydro turbine, photovoltaic (PV) system and EVs/PHEVs. More realistic penetration levels of SSDGs and EVs/PHEVs as forecasted for 2020 is used to analyse. The dynamic load demands are also taken into account. In order to ensure the accurate of simulation results, the practical parameters of distribution system are used and the international standards such as Institute of Electrical and Electronics Engineers (IEEE) standards are also complied. The suggestion solutions are also presented. The MATLAB/Simulink software is chosen as it can support complicate modelling and analysis.

Design and Implementation of User-Oriented Virtual Dedicate Network System Based on Software-Defined Wide Area Network (SD-WAN 기반의 사용자 중심 가상 전용 네트워크 시스템 설계 및 구현)

  • Kim, Yong-hwan;Kim, Dongkyun
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.41 no.9
    • /
    • pp.1081-1094
    • /
    • 2016
  • KREONET is a principal national R&E network running by KISTI in Korea. It uniquely provides production research network services for around 200 non-profit research and educational organizations, based on hybrid (IP and non-IP) network infrastructure. However, KREONET is limited to meet various needs of new network services for advanced Science & Technology (S&T) users because its infrastructure is inherently derived form classical hardware-based, fixed and closed environments. So, KREONET-S is designed to provide advanced S&T services to catch up with time-to-research and time-to-collaboration. In this paper, we present a system architecture of KREONET-S based on network infrastructure that consists of data and control planes separately. Furthermore, we propose and describe VDN service which is capable of building a virtual dedicate & bandwidth-guaranteed network for S&T group dynamically. we implement VDN application on KREONET-S and then perform performance analysis for proving that KREONET-S system and VDN application can be a good solutions to cope with new network paradigms for various advanced S&T applications and users.

Development of Vehicle Arrival Time Prediction Algorithm Based on a Demand Volume (교통수요 기반의 도착예정시간 산출 알고리즘 개발)

  • Kim, Ji-Hong;Lee, Gyeong-Sun;Kim, Yeong-Ho;Lee, Seong-Mo
    • Journal of Korean Society of Transportation
    • /
    • v.23 no.2
    • /
    • pp.107-116
    • /
    • 2005
  • The information on travel time in providing the information of traffic to drivers is one of the most important data to control a traffic congestion efficiently. Especially, this information is the major element of route choice of drivers, and based on the premise that it has the high degree of confidence in real situation. This study developed a vehicle arrival time prediction algorithm called as "VAT-DV" for 6 corridors in total 6.1Km of "Nam-san area trffic information system" in order to give an information of congestion to drivers using VMS, ARS, and WEB. The spatial scope of this study is 2.5km~3km sections of each corridor, but there are various situations of traffic flow in a short period because they have signalized intersections in a departure point and an arrival point of each corridor, so they have almost characteristics of interrupted and uninterrupted traffic flow. The algorithm uses the information on a demand volume and a queue length. The demand volume is estimated from density of each points based on the Greenburg model, and the queue length is from the density and speed of each point. In order to settle the variation of the unit time, the result of this algorithm is strategically regulated by importing the AVI(Automatic Vehicle Identification), one of the number plate matching methods. In this study, the AVI travel time information is composed by Hybrid Model in order to use it as the basic parameter to make one travel time in a day using ILD to classify the characteristics of the traffic flow along the queue length. According to the result of this study, in congestion situation, this algorithm has about more than 84% degree of accuracy. Specially, the result of providing the information of "Nam-san area traffic information system" shows that 72.6% of drivers are available.

A Study on the Performance Characteristics of an Energy Saving Unit in a Hydraulic Elevator (유압식 엘리베이터 에너지 저감장치의 성능특성에 관한 연구)

  • Cho, Ihn-Sung
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.14 no.6
    • /
    • pp.2588-2595
    • /
    • 2013
  • In a traditional hydraulic elevator, elevator car is descended by down control valve, and the oil hydraulic energy must be lost during the descending stroke. In this paper, the performance characteristics of the hybrid type energy saving unit, is used to save the hydraulic energy which is lost during the descending stroke, for a hydraulic elevator are studied. The energy can be reused as the auxiliary power. The results show that the performance characteristics, such as the pressure, flow rate, output current and voltage, efficiency, and the energy recovery rate of the unit are stable and good as the energy recovery rate is 54%, and the energy saving unit is useful to reuse the saved energy during the descending stroke of elevator car. Also, it was confirmed that the energy saving unit can be deployed on a commercial scale.