Search for: prediction
0.016 seconds
Total 1062 records

    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)
    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... 

    Improvement of Routing Approaches in Delay-Tolerant Mobile Networks

    , M.Sc. Thesis Sharif University of Technology Yadegari, Manizhe (Author) ; Hemmatyar, Ali mohammad Afshin (Supervisor)
    Delay Tolerant Networks are types of mobile Ad-hoc networks, in where because of the high node mobility, low node density and node diversity, there is not full connection between nodes in the whole network; therefore, the probability of existence of end-to-end path between source and destination is low. Due to these properties, message routing in delay tolerant networks has turned to be a challenge, this type of networks work based on the concept of store, carry, forward; for instance, a node may store a message in the buffer for a long time and carry it along until meeting an appropriate contact opportunity. Delay tolerant networks are capable of providing communication services in... 

    Investigation of Low Salinity Waterflooding Predictive Capability and the Development of a Tool for Screening Candidates

    , M.Sc. Thesis Sharif University of Technology Golmohammadi, Meysam (Author) ; Mahani, Hassan (Supervisor) ; Ayatollahi, Shahab (Supervisor)
    Among different enhanced oil recovery (EOR) methods, low salinity waterflooding (LSWF) has been attractive to researchers because of its relative simplicity and lower environmental problems compared to other conventional EOR methods. Numerous researchers have attempted to find the main cause of the low salinity effect (LSE). According to previous studies, several experimental techniques have been proposed for predicting LSE and screening potential field candidates. However, there is a lack of a systematic investigation of all (or even some of) the methods to compare and determine their LSE predictive capability. Predictive capability development is essential because it saves costs and time... 

    Development of an Integrated Hybrid Model of Human Cardiovascular and Respiratory System for Control Study purposes

    , M.Sc. Thesis Sharif University of Technology Kehtari, Payam (Author) ; Bozorgmehri, Ramin (Supervisor)
    Mathematical models are used for describing physical systems to make it possible to study and investigate the behavior of these systems and compare their performance and improve them. For this reason, a mathematical model for cardiovascular system and respiratory system is used to study how these two systems interact. The cardiovascular system model and the respiratory system model comprise four and two compartments, respectively. In fact, the combined model contains the left and right ventricles, body tissue, lung, systemic blood circulation, and pulmonary compartments. Heart rate and alveolar ventilation are assumed to be the quantities through them the central nervous system controls the... 

    Prediction of Air Pollutants’ Hourly Concentration in Tehran Using Artificial Neural Network and Specteral Decomposition of Time Series Data

    , M.Sc. Thesis Sharif University of Technology Kamali, Nima (Author) ; Arhami, Mohammad (Supervisor)
    Recent progress in developing Artificial Neural Network (ANN) meta-models has paved the way for reliable use of these models in the prediction of air pollutant concentrations in urban atmosphere. However, improvement of prediction performance, proper selection of input parameters and model architecture remain key challenges to their practical use. This study’s main objectives are: selecting proper input parameters for ANN meta-models, optimizing the ANN models to achieve the most accurate hourly prediction for a case study (City of Tehran), coupling the ANN method with filtered input data and evaluating its privilege. In the current study the ANNs were constructed to predict criteria... 

    A Multi-objective Model Predictive Control Approach to the Energy Trading Problem in Vehicle-to-Grid System

    , M.Sc. Thesis Sharif University of Technology Karimi, Arash (Author) ; Haeri, Mohammad (Supervisor)
    Electric vehicles (EVs) will be used rampantly in future transportation system. Although the uncontrolled charging of these EVs will be threatening for the stability and sustainability of the grid, a well-suited energy trading policy may provide a number of beneficial services to the grid as well as preserving the sustainability of the system along with heightening the performance of operation. In this paper, by taking advantage of block rate tariff, a wholesale pricing policy is introduced. A multi-objective approach is utilized to address the cost reduction and load levelling services, concurrently, in order to guarantee the profits of the both the grid and EVs. Due to the high... 

    Investigation of Strain Jumping and Its Effect on Evaluating Capacity of Steel Bracing Deformations

    , M.Sc. Thesis Sharif University of Technology Karbalaee, Mohammad (Author) ; Moghaddam, Hassan (Supervisor)
    In this study, HSS and double angle braces subjected to cyclic loading in order to study the buckling and post buckling behavior have been investigated by Finite Element method. The results of FE analysis are fairly in good agreement with experiments. Analysis demonstrate that when local buckling occurs in middle span, subsequently, strain rises severely. Accordingly, this strain jumping causes early fracture in braces. Therefore, local buckling can be one of the primary reasons of fracture in braces. As a result, local buckling must be considered one of the primary limit state of Performance-Based design of steel braces. In addition, finding a way to predict local buckling can help us to... 

    User Profiling in Social Networks

    , M.Sc. Thesis Sharif University of Technology Ketabchi, Mohammad Amin (Author) ; Sameti, Hossein (Supervisor)
    Due to the emergence of social networks in recent years and people’s usage of them for expressing their thoughts and emotions, there are lots of user data in these networks. The development of social networks has created a good opportunity for organizations and people to extract user profiles from social networks. Hence, user profiling has become an interesting problem for researchers. Predicting users’ occupational class is one of the main problems in this field. Most of the existing related works use only textual features of users, whereas users’ relations graph can give useful information about users. In this research, we propose a model based on Graph Neural Networks (GNNs) to predict... 

    Three Dimensional Multi-Objective Terrain Following/Avoidance Optimization Using Heuristic Approach

    , M.Sc. Thesis Sharif University of Technology Kamyar, Reza (Author) ; Pourtakdoust, Hossein (Supervisor)
    Thus far, there has been a great attraction toward the optimal flight path planning problem. Terrain following/avoidance (TF/TA) flight is one of the most significant applications of this issue. To prevent from detection by the radars, fighter aircrafts, cruise missiles and helicopters often have to fly as close as possible to the surface during the operations. Such types of maneuvers are much more demanding and effortful than to be designed and implemented by human. The optimal TF/TA guidance system design comprises three phases: optimal path planning, closed-loop control system design for trajectory tracking and sensor blending to match the onboard and measured terrain data. So far, the... 

    Capital Market Forecasting with Machine Learning Model and Comparing it with Forecasting Using System Dynamic

    , M.Sc. Thesis Sharif University of Technology Kazem Dehbashi, Sina (Author) ; Kianfar, Farhad (Supervisor)
    Prediction is an important issue in many areas. Proper planning for the future requires careful forecasting, so providing accurate methods, especially in the financial field, is invaluable. In this study, the main problem is predicting the price of global gold. Factors for gold prices include oil, gas, silver, soybeans, copper, the s & p500 index, the Dow Jones index, the British and Japanese stock market indices, the dollar index, the multi-currency exchange rate (pound-euro-yuan-yen) with the dollar to The title of the influential factors in this research is considered. The time frame of this research is daily, in other words, the data is collected on a daily basis and the goal is to... 

    Optimum Power Dispatch in Wind Farm Considering Energy Storage Systems and Dispatchable Resources

    , Ph.D. Dissertation Sharif University of Technology Kazari, Hessam (Author) ; Oraee, Hashem (Supervisor)
    In this dissertation, two parts of research has been conducted. First, with the aim of minizing the fluctuations of power output of wind farms and the need for energy storage system, optimization of wind farm (WF) layout has been studied. Deployment of battery energy storage system (BESS) is a viable option to alleviate the inherent power fluctuation of wind farms. In this thesis and based on the power spectrum density (PSD) theorem, it is hown that the WF layout affects not only the total harvested energy but also the level of power fluctuation, which in turn influences required capacity of battery energy storage system (BESS) needed to mitigate the inherent power fluctuation of the wind... 

    Prediction and Compensation of Intraoperative Brain Shift Using Biomechanical Modeling

    , M.Sc. Thesis Sharif University of Technology Pasandideh Pour, Javad (Author) ; Farahmand, Farzam (Supervisor)
    The human brain is the most sensitive and important human organ and surgery must be done with high precision and without risk. During surgery, brain tissue deform continuously due to gravity, out of the cerebrospinal fluid and the changing pressure of the cerebrospinal fluid and the surgical maneuvers. Because the surgeon has no direct view on brain internal, the ways to solve this problem is to pay attention. This method makes it possible to the surgeon see in the brain and the brain tissue deformation. This thesis method is based on biomechanical modeling. After forming finite element model from the pre-operative MRI, brain surface and volume datasets during surgery as a load, apply to the... 

    Water-flooded On-line Reservoir Management Using Multi-variable Multi-model Predictive Controllers

    , M.Sc. Thesis Sharif University of Technology Prrrang, Sahar (Author) ; Pishvaie, Mahmoud Reza (Supervisor)
    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... 

    Improving System-Level Thermal Management for Multi-Core Embedded Processors

    , M.Sc. Thesis Sharif University of Technology Valikhani, Hadi (Author) ; Ejlali, Alireza (Supervisor)
    Due to the technological improvement, decreasing transistor’s size and increasing demand for more processing abilities, designing and implementing multi core processors becomes a hot topic. One of the direct effects of decreasing the size is increasing the rate of power consumption in a unit area. Thus, the generated heat by the processor will be increased. Increasing the temperature could has undesired effects on the other features of the processor such as reliability, efciency, and failure rate. The problems that caused due to the high temperature in the multicore processors is not limited to the maximum temperature, but temperature fluctuations and variation between different parts of the... 

    Model Predictive Inferential Control for Electrochemotherapy of Tumors

    , M.Sc. Thesis Sharif University of Technology Valibeknejhad, Mohammad (Author) ; Pishvaie, Mahmoud Reza (Supervisor)
    The purpose of this project is to use adaptive model predictive and fuzzy controllers to control the pH in a proper location and right amount as well as applying optimal dose of electrical current to prevent the destruction of healthy tissue during treatment. Comsol software has been used to simulate the electrochemical treatment of liver cancer. Since the Comsol software does not have the ability to solve the tumor model in spherical coordinates, the modeling/simulation was performed in cylindrical ordinates. In this study, only the reactions of oxygen and chlorine production in the anode were considered. The predictive control used in this study is GPC type and fmincon algorithm is used... 

    Simulation and Control of Fixed Bed OCM Reactor

    , M.Sc. Thesis Sharif University of Technology Valadkhani, Ali (Author) ; Shahrokhi, Mohammad (Supervisor) ; Pishvaei, Mahmoud Reza (Supervisor) ; Zarrinpashneh, Saeed ($item.subfieldsMap.e)
    Oxidative coupling of methane (OCM) in a fixed bed tubular reactor over Mn-Na2WO4/SiO2 catalyst has been studied. Four kinetic models have been considered for OCM reactions. Based on an objective function and using genetic algorithm, kinetic parameters have been estimated. A reactor tube with 20 mm diameter and 400 mm length surrounded by molten salt for removing heat of reaction has been used for experimental study. Effects of different factors such as CH4/O2 ratio, nitrogen content in feed and contact time are investigated experimentally and by simulation. A good agreement has been observed between simulation and experimental data. Oxidative coupling of methane (OCM) in an industrial fixed... 

    Predictive Cordon Pricing to Reduce Air Pollution

    , Ph.D. Dissertation Sharif University of Technology Vosough, Shaghayegh Sadat (Author) ; Poorzahedy, Hossain (Supervisor) ; Lindsey, Robin (Co-Supervisor)
    Traffic is a major contributor to emissions in many large cities with severe air pollution. Experience in London, Milan, and Stockholm shows that charging for the use of roads can be effective in reducing emissions, as well as congestion. This study examines the use of predictive cordon tolls based on weather forecasts to reduce ambient air pollution and congestion. Travelers choose their destinations inside or outside the cordon, and whether to drive or take public transport. Passenger vehicles are divided into three classes according to their emission characteristics, and higher tolls are imposed on more polluting vehicles. The Box model of emission dispersion is used to predict air... 

    Flight Formation Control & Obstacle Avoidance of a UAV Team Using Fuzzy Predictive Artificial Potential Field Method

    , M.Sc. Thesis Sharif University of Technology Vahedi, Amir Mohammad (Author) ; Nobahari, Hadi (Supervisor)
    This thesis focuses on the development of a flight formation control algorithm and obstacle avoidance of a UAV team using fuzzy predictive artificial potential field (FPAPF) method. One of the common methods for path generation and obstacle avoidance is the artificial potential field (APF) method. The basis of the APF method is that the UAV is attracted to the target point and repelled from the obstacles by using the potential fields of attraction and repulsion. The popularity of this method is due to its computational simplicity and efficiency. The APF method has limitations due to constant attraction and repulsion coefficients. The proposed real-time FPAPF method uses fuzzy logic to... 

    Aerodynamic Design of Radial Inflow Turbine’s Volute Casing

    , M.Sc. Thesis Sharif University of Technology Heravi, Sajjad (Author) ; Hajilouy-Benisi, Ali (Supervisor)
    For several decades, turbocharging of internal combustion engines has been a wide spreading technology to increase the engine output power as much as possible. Turbocharger has two main components: compressor, and turbine. Therefore, increasing the efficiency of turbine and compressor has a major role in engine performance improvement. This has been a continuous research goal in 20th century. Considerable advances has been achieved until now. Turbocharger turbine should be matched to engine in a wide range operation conditions with high efficiency. Many researchers have published their achievements considering turbine elements design improvements. This research is focused on the turbine... 

    An Intelligent Triangular Pattern Recognition in Stock Price Charts

    , M.Sc. Thesis Sharif University of Technology Hedayati, Emadeddin (Author) ; Fazli, Mohammad Amin (Supervisor)
    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