Loading...
Search for: prediction
0.022 seconds
Total 1062 records

    An Intelligent Triangular Pattern Recognition in Stock Price Charts

    , M.Sc. Thesis Sharif University of Technology Hedayati, Emadeddin (Author) ; Fazli, Mohammad Amin (Supervisor)
    Abstract
    Stock price patterns are a technical analysis approach to forecast future trends with tremendous practical benefits. However, the current algorithms solely rely on machine learning techniques and deep neural networks which could be a problem in countries where data sets such as these are not available. We propose an algorithm based on geometry and mathematics for this problem, leading to an O(n^3logn + n^2k) complexity, where k is the number of triangular patterns  

    , M.Sc. Thesis Sharif University of Technology Sartipizade, Hossein (Author) ; Haeri, Mohammad (Supervisor)
    Abstract
    Gas Metal Arc Welding (GMAW) process is one of the most applicable component in the industry due to its high speed and capability of employing for wide ranges of materials. The quality of products in a welding process is relevant to the quality of welding which is determined by characteristics like shape and size of droplet during detachment. In order to improve the quality of welding, a precise model of the process is required. There are many various model presented for GMAW process based on its dynamic equations. Almost all of these models assume the process as a continuous state system. However the process includes sudden variants in droplet detachment that is known as hybrid behavior.... 

    Deep Learning in a Structured Output Space

    , Ph.D. Dissertation Sharif University of Technology Salehi, Fatemeh (Author) ; Rabiee, Hamid Reza (Supervisor) ; Soleymani, Mahdieh (Supervisor)
    Abstract
    A large number of machine learning problems are considered as structured output problems in which the goal is to find the mapping function between an input vector to a number of variables in the output side which are statistically correlated. Motivated by the advantages of simultaneous learning of these variables compared to learning them separately, many structured output models have been introduced. Decreasing the sample complexity, increasing the generalization ability and overcoming to noisy data are some of these benefits. So in the first step of this research we concentrate on one of classical but important problems in bioinformatics which is automatic protein function prediction.... 

    Learning Molecular Properties Using Deep Learning

    , M.Sc. Thesis Sharif University of Technology Moradi, Parsa (Author) ; Hossein Khalaj, Babak (Supervisor)
    Abstract
    Design and production of a drug is a very time and money consuming process. It takes more than a decade and about 2.5 million dollars on various stages to design a drug. Attempts to reduce this cost and time to market will make drugs available to customers at a more reasonable time. Some stages such as animal testing phase and clinical trials, can not be replaced and must take place in practice. Fortunately, some laboratory steps are interchangeable with software algorithms. These algorithms can significantly reduce the cost and time to market of the drug if they are accurate enough. On the other hand, the remarkable results of machine learning, in particular, Deep Neural Networks, in areas... 

    Path-following in Predictive Rollover Prevention in High CG Vehicles

    , Ph.D. Dissertation Sharif University of Technology Ghazali, Mohammad (Author) ; Durali, Mohammad (Supervisor) ; Salarieh, Hassan (Co-Advisor)
    Abstract
    In this thesis vehicle path-following in the presence of rollover risk is investigated. Vehicles with high center of mass are prone to roll instability. Untripped rollover risk is increased in high center of gravity vehicles and high-friction road condition. Some researches introduce strategies to handle the short-duration rollover condition. These strategies, however, yield to trajectory tracking error in semi-static maneuvers. Tracking error may also cause tripped rollover. In some other works rollover is prevented by velocity reduction. Rollover is again probable before sufficient reduction of velocity. This thesis puts stress on tracking error from rollover prevention. A lower level... 

    Model Predictive Control of a Fed-Batch Bio-ethanol Fermenter Based on Hybrid Neural Networks

    , M.Sc. Thesis Sharif University of Technology Yazdani, Saman (Author) ; Pishvaie, Mahmoud Reza (Supervisor)
    Abstract
    Dynamic modeling and process control, especially the equipment of bioreactors and fermenters, have always faced many challenges due to the complexity and high uncertainty of the kinetics of environmental reactions. Among these, semi-continuous fermentation for bioethanol production is one of the important technologies in biochemical industries. The problem of modeling as well as controlling the use of the main discontinuous and semi-continuous methods of ethanol production is the lack of uniform state conditions and the possibility of aerobic and non-aerobic multiplication conditions in two ways. The main goal of this research is to obtain a new method in modeling bioethanol fermentation and... 

    Analysis and Design of Predictive Control Strategy for Sheppard-Taylor Based PFC Rectifier

    , M.Sc. Thesis Sharif University of Technology Abedi, Mohammad Reza (Author) ; Tahami, Farzad (Supervisor)
    Abstract
    In this thesis CCM/CVM operation and modeling of the Sheppard-Taylor topology is reviewed and a predictive control strategy is applied for a Sheppard-Taylor-based power factor correction (PFC) rectifier. Compared to conventional boost or buck boost PFC’s, this topology allows a better current tracking at the AC side, with a relatively reduced voltage at the DC side. Consequently, the high frequency AC filters required by the buck PFCs are avoided, and the voltage stresses on the boost switches are significantly reduced. Furthermore In predictive control strategy the duty cycle required to achieve unity power factor in a half line period can be calculated in advance. The main advantage of... 

    Multi-Objective Control of an In-Joint Semi-Active Suspension System with Energy Harvesting Capability Using Neural Network

    , M.Sc. Thesis Sharif University of Technology Soleymanzadeh Fard, Sajad (Author) ; Sayyaadi, Hassan (Supervisor)
    Abstract
    The basic type of suspension systems, which is known as passive suspension systems, creates a balance and compromise between the two goals of ride comfort and road holding. In order to improve the performance of the suspension system, the use of active actuators has been considered. However these actuators require energy and control strategies. To supply the required energy, recovering the energy of vehicle vibrations can be a solution. Therefore, ride comfort, keeping the wheels in contact with the road and the amount of recoverable energy are three important control objectives for modern active and semi-active suspension systems. The control of these systems is considered a challenging... 

    Model Predictive Control of a Solution Copolymerization Reactor

    , M.Sc. Thesis Sharif University of Technology Sarrami Forushani, Sadegh (Author) ; Pishvaie, Mahmoud Reza (Supervisor)
    Abstract
    In the industry, there are nonlinear processes that can not be controlled with classical methods. Also, there are many processes that are more than one controlled variable that with classical methods, the design of a multiple input - multiple output controler is very difficult for them as well as the constraints on the inputs and outputs of the process exist, using classical controllers will be far more difficult. A model-based predictive control method for controlling nonlinear processes is useful in addition to having very high efficiency, extended to multi-mode interference together with constraints on the control variables and other controlled Problem with dynamic properties such as... 

    Multiple Model Predictive Control of Methyl Methacrylate/Vinyl Acetate Synthesis Reactor

    , M.Sc. Thesis Sharif University of Technology Naderi Boldaji, Sara (Author) ; Pishvaie, Mahmoud Reza (Supervisor)
    Abstract
    The purpose of this study is the implementation of multi-model predictive control (MMPC) approach for the co-polymerization system of methyl methacrylate - vinyl acetate. Simpler development of local models and controllers and also convenience of understanding the model and controller structure are the main reasons for using this approach. In the first step, RGA analysis has been used for pairing input and output variables. Then the performance of PI controller on the system has been investigated. For designing model predictive controller (MPC) the nonlinear model has been linearized at operational point and the controller has been designed in MPC toolbox of MATLAB software R2013a. In the... 

    Fuzzy Multi-Model Based Predictive Control for Offshore Wind Turbines

    , M.Sc. Thesis Sharif University of Technology Sanaei, Behnam (Author) ; Sadati, Nasser (Supervisor)
    Abstract
    One of the main drivers for the substantial growth in wind energy utilization in the world is the growing demand for renewable energy sources to reduce greenhouse gas emissions. At greater distances from the coastline, more and steadier potential energy resources are available. This has led the world offshore wind energy industry to grow at a faster rate than onshore in the past two decades. In deep waters, the wind turbine is mounted on a floating platform, whose movements increase the complexity of the turbine control system and enhance the mechanical loads on the various components of the turbine. Reducing these mechanical stresses is equivalent to increasing the lifetime of the turbine... 

    Multivariable Predictive Control of a Fuel Cell-Micro Turbine Hybrid System

    , M.Sc. Thesis Sharif University of Technology Jafari, Solmaz (Author) ; Pishvaie, Mahmoud Reza (Supervisor)
    Abstract
    High efficiency and low-emission fuel cells have the capacity to replace fossil fuels for energy supply concerns. Solid oxide fuel cells operate in relatively high temperature and have power plant applications. Hence, they are acquainted to be coupled with cycle gas turbine to reduce the cost and increase the overall system efficiency. The control of these hybrid systems is so important. Due to the system nonlinearity and having more than one controlled variable, its control with classic methods would be difficult. The model based predictive control is used as an alternative to mitigate these difficulties. In addition to their high performance, their extension to the multivariate case would... 

    Predictive and Nonlinear Control of Aircraft in Presence of Microburst Wind Shear

    , M.Sc. Thesis Sharif University of Technology Jafari, Navid (Author) ; Pourtakdoust, Hosein (Supervisor)
    Abstract
    Airplanes usually experience minor position change and height loss during cruise flight, but under normal circumstances the aircraft total energy is adequately acceptable to maintain the trajectory and the desired performance without severe oscillations. On the other hand, if the airplane encounters a wind-shear or microburst during take-off or landing phases, it would be a dangerous situation, as the aircraft kinetic and potential energy levels are not as high.
    In this research, a model predictive controller is designed and investigated to allow a transport category aircraft to either escape or penetrate the microburst. In this regard, initially a DMC controller is designed for 6-DoF... 

    Robust Model Predictive Control for Nonlinear Systems using Linear Matrix Inequality

    , M.Sc. Thesis Sharif University of Technology Khaksarpour, Reza (Author) ; Haeri, Mohammad (Supervisor)
    Abstract
    The constrained nonlinear systems with large operating regions have attracted great attention due to their correspondence with the most practical systems. There are several tools such as gain scheduling and Nonlinear Model Predictive Control (NMPC) to control them. Gain scheduling, with ability to provide stability guarantees between the estimated stability regions overlapping each other and to cover a large space of the allowable operating range of the system, is an attractive practical approach to control the systems with large operating regions. But this strategy do not account for constraints explicitly by online optimization. On the contrary, NMPC handles constraints on the manipulated... 

    Model Predictive Control of an Autonomous Semi-Submersible Vehicle for Depth Control

    , M.Sc. Thesis Sharif University of Technology Amin Hatamy, Erfan (Author) ; Nejat Pishkenari, Hossein (Supervisor) ; Salarieh, Hassan (Supervisor)
    Abstract
    In the past few decades, with the advancement of technology, using autonomous robots has been receiving growing interest. Autonomous semi-submersible vehicles are a subset of autonomous underwater vehicles (AUV). This type of vehicle operates near the surface of the water and is semi-submerged. Nonlinear coupled dynamics, structural uncertainties, model parameters dependency to robot velocity, external disturbances, and model constraints are AUV’s workspace challenges. For this reason, depth control of these vehicles in the presence of environmental disturbances is crucial. However, MPC as one of the advanced control methods in the field of robotics is increasingly developing. This control... 

    Multiple-Horizon Model Predictive Control of Spacecraft for Landing on Asteroids

    , Ph.D. Dissertation Sharif University of Technology Alandi Hallaj, Mohammad Amin (Author) ; Asadian, Nima (Supervisor)
    Abstract
    This dissertation investigates the Multiple-Horizon Multiple-Model Predictive Control method and its application in soft landing problem on an irregular-shaped asteroid. In this way, a predictive framework including a heuristic guidance law named Predictive Path Planning and Multiple-Horizon Multiple-Model Predictive Control (MHMM-PC) as the control scheme is introduced for soft landing on an asteroid. Obviously, reducing the fuel consumption is a priority in space missions. Thus, the employed control framework should minimize the required control effort. Furthermore, the control method should be robust enough to deal with the effects of model uncertainties and disturbances. The unique... 

    Model Predictive Orbit Control of a LEO Satellite Using Gauss’s Variational Equations

    , M.Sc. Thesis Sharif University of Technology Tavakkoli, Mohammad Mahdi (Author) ; Asadian, Nima (Supervisor)
    Abstract
    In comparison to attitude control of a satellite which is widely used in practical missions, orbit control (espescialy autonomous orbit control) has been only recently paid attention. Autonomous, on-board orbit control, also called autonomous stationkeeping, means the automatic maintenance of all of orbital elements by the satellite itself. In this thesis, an autonomous absolute orbit control strategy for a single Low Earth Orbit (LEO) satellite is presented. When the satellite violates the control trigger error limits, then the controller is activated and calculates a sequence of orbital maneuvers that move the satellite towards its desired states. The absolute orbit control of the... 

    Distributed Robust Model Predictive Control for Multi-zone Air Conditioning Systems

    , M.Sc. Thesis Sharif University of Technology Azim Mezerji, Hojat (Author) ; Moradi, Hamed (Supervisor)
    Abstract
    Optimizing the energy consumption of air conditioning systems has gained great importance in recent years. In addition, maintaining thermal comfort and air quality in buildings is important. The multi-evaporator air conditioning system, which is a direct expansion system, shows the complex and distributed structure of air conditioning systems due to the thermal connection between zones and its large scale. The modeling of these systems is associated with uncertainties. Therefore, designing a suitable control structure for multi-zone systems is very important to achieve optimal energy consumption and maintain comfort conditions in the presence of uncertainty. Model predictive control has been... 

    Economic Model Predictive Control of a Multiproduct CSTR Based on Elementary Reactions

    , M.Sc. Thesis Sharif University of Technology Soofi, Vahid (Author) ; Vafa, Ehsan (Supervisor)
    Abstract
    One of the model based control strategies that has been proposed in recent years for the control of process systems is the one based on the economic models, in which objective functions with an economic basis are used along with the equations and constraints to perform control calculations. In this work, the control of a multiproduct continuous stirred reactors is discussed, in which, it is possible to produce different products based on changes in the market demand, the price of the products or the primary raw materials according to a specific schedule. One of the recently used methods is the economic predictive control method based on the Lyapunov function. In this method a quadratic... 

    Finite-Control-Set Model Predictive Control for Doubly Fed Induction Generator of a Floating Offshore Wind Turbine

    , M.Sc. Thesis Sharif University of Technology Shafie, Hossein (Author) ; Sadati, Naser (Supervisor)
    Abstract
    The purpose of this project is designing a controller for a floating offshore wind turbine to exctract maximum power from wind energy in the first operating region of wind turbine. The NREL 5 MW OC3-Hywind floating wind turbine with BARGE platform will be used for this project. By using Turbsim software, proper wind profile for the first operating region of wind turbine will be produced. This profile will be excecuted for the FAST software that is simulates the mechanical part of wind turbine. By implementing the doubly fed induction generator in Simulink enviroment and designing the controller for doubly fed induction generator, the desired torque for maximizing the exctraction power of...