Sharif Digital Repository

In this work, we aim to find a way to identify and forecast transients in nuclear power plants with the aid of semi-supervised machine learning algorithm. Forecasting and identifying transients in nuclear power plants at the early stages of formation are essential for safety considerations and precautionary measures. The use of machine learning algorithms provides an intelligent control mechanism that, along with the main operator of the power plant, raises the transient detection and identification rate. Our algorithm of choice is to change the way data is presented, which is a semi-supervised learning approach. The algorithm consists of two methods: quantum dynamics clustering... 

Successful deployment of the next-generation safety-critical systems (e.g., self-driving cars or assistive robots) requires certifying their safety during their operation. Therefore, there is an urgent need for developing safe controllers that respect the system’s constraints all the time. Safety, however, is the bare minimum requirement for any safety-critical system, and it is desired to design safe controllers that achieve as much performance as possible. Most existing results in the literature consider either optimal control design without safety specifications or safe control design with only short-sighted optimality. However, long-term optimality based on long-horizon optimization is... 

Vehicular Ad hoc Network (VANET) is a subclass of Mobile Ad hoc Network (MANET), which provides us ability to communicate between moving vehicles. VANET has been developed as a standard means of communication for Intelligent Transport Systems (ITS) to improve traffic safety and efficiency while providing internet access on the move. Congestion control is a challenging subject in VANETs primarily due to the shared nature of the wireless channel and frequent changes of the network topology. Inefficient congestion control causes periodical safety messages to be lost and introduces latency in threat modelling at the application layer. There are two methods to overcome this problem. First, based... 

Using of physical safety devices such as pressure safety valves, are the most conventional methods to protect vessels against overpressure but operation of these devices have many negative effect on environment also they waste significant amount of valuable hydrocarbon materials. Relying on conventional safety devices needs a flare net to send excess gas to torch and in many cases essential equipments for flare net is so expensive and their maintenance are difficult thus reducing the size of flare net for a chemical plant is beneficial.
Application of new alternative device (HIPPS) is very helpful to reduce flaring load and releasing pollutant materials such as SOx and NOx. The main... 

The HIPS is a safety integrity system that is designed to provide overpressure protection that is at least equivalent in reliability to a mechanical relief device. In this study, the performance evaluation of HIPS in Assaluyeh gas Refiner is studied.In the first stage, over pressure analysis is compiled using dynamic simulation and API RP 520 and the recommended HPPS design procedure is presented. Also, The High Integrity Protection Systems (HIPS) further reduced the relief load and even eliminated the relief from the stabilizer tower for the scenarios tested.In this project, following a detailed study of the commissioning process and its criticalities, Hazop is selected as the most suitable... 

Overpressure protection and flare loading network are critical challenges faced by the Oil & Gas and chemical industries. Whether they are new facilities or aging ones, integrity management of overpressure and flaring systems remain significant throughout the life of the planet. One of the most important ways for protection of over pressure and depressurizing to flare header through pressure safety valve is implementation of safety instrument system (SIS). Application of safety instrumented systems for the process industries causes significant reduction of flaring load and loss prevention of valuable materials through increase protection layer availability and over pressure risk reduction.... 

LOOP accident is one of the most important accidents in NPPS and it leads to loss of power supply of the RCP pumps which are the main pumps of primary circuit. Subsequently trip of the rector occurs. In safety analysis, concerning worst conditions, assumes that after a small period of time, main generator of plant stops working and loss of AC power supply of all power plant loads including safety systems ocures. To control of this accident, it’s necessary to startup and load backup power supply system (EDGs) for at least one safety channels, if not, the accident moves forwards and becomes S.B.O accident which is more important accident that ends to core damage because of stops working of all... 

In recent years, machine learning techniques have been available to predict and interpret the structural behavior of dams. The main goal of this research is to predict structural behavior through modeling with data read by accurate instruments of dams. This requires the selection of several machine learning methods such as Random Forests (RF), Boosted Regression Trees (BRT), Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Decision Tree Regression (DTR) algorithms. In this research, considering the 24 target variables defined from the detailed instrumentations studied, the behavior of the dam is modeled using selected machine learning models. These precision instruments... 

The utilization of tower cranes at construction sites presents numerous inherent risks. These cranes are commonly employed for lifting heavy loads, which carry the potential hazard of accidental falls. Simultaneously, workers may inadvertently overlook overhead dangers while focusing on their tasks. To mitigate these risks, laws in many countries explicitly prohibit individuals from occupying the vicinity directly beneath suspended loads, known as the fall zone. Such measures are vital to safeguard against the peril of heavy loads plummeting onto people. However, existing studies have not offered a comprehensive and efficient approach to identify crane load fall zone. To address this gap,... 

Nearly 1.2 million people die in road crashes each year, and as many as 50 million are injured in the world. In Iran, approximately 800 thousand crashes occur annually killing up to 43 people per day. Given that over 90% of accidents are related to human factors, using models that incorporate driver’s attitudes and behavior can be highly predictive of crashes. The main objective of the current research is to examine the impact of drivers’ attitudes on road crashes along with other factors such as socio-demographic characteristics and vehicle type. This study uses data from a self-completed questionnaire among a representative sample of Iranian drivers living in Tehran. The Questionnaire... 

This thesis presents an inventory control system which is based on Meta-heuristic Algorithms.In this thesis we will optimize the input values of our tree-echelon inventory model (keeping costs,stock worth,reorder costs,...) with these Algorithms. The presented method is able to determine the optimal stock level, costs of system and number of shipments in the system. The method is basically a decision support system (DES) and it is able to provide the order scheduling parameters of goods at operational level. The aim of the current research is to demonstrate that a Meta-heuristic algorithmis capable of solving complex inventory problems and with future improvements it is able to achieve... 

A Balanced Scorecard (BSC) model is proposed to evaluate performance of Health, Safety and Environment (HSE) management systems. This model includes key performance indicators at three integrated levels. It has been tested and verified in a project-based organization in Iran, active in the area of power and energy. Results show that the company has done well in implementing HSE management processes, but no so well in growth and learning. This model may be used as a basis for comparing different companies and various proposed programs in the field of HSE management systems. The model includes indicators and sub-indicators in each category particularly related to stakeholders, processes, and... 

Construction is a large industry in Iran, it engages in a wide range of products. The raw materials which are used in making a building are fairly standard items: iron, cement, glass, and so on. Because the technologies for making a building are well-known, contractor can solicit bids from variety suppliers for raw materials without worrying about the possible disclosure of trade secrets. Unfortunately bidding processing in Iran becomes very slow and inefficient. Each transaction required to request the relevant telephone number to supplier that might be interested in bidding on the item, it would often take purchasing personnel more than one week to gather the information, send it to... 

Nowadays, using smart buildings to improve performance and welfare of residents is of interest. Usually, these systems consist of safety systems that provide safety and security for residents. For example, fire detection system, sound the alarm and activating sprinkler in the building. For different types of critical events that can occur, variety of safety systems has been designed. Response time of these systems should be less than the deadline and the correct operation must be compeleted. As a result, analyzing and checking out the real-time and logical features of safety systems are the issues that we treat and investigate in this thesis.
In general, these systems are either... 

In this work the large break loss of coolant accident at Boushehr Nuclear Power Plant (NPP) has been studied. At first, primary and secondary side’s components which play important role in the accident have been modeled using RELAP5/MOD3.2 GAMMA system code. The components are: reactor pressure vessel, main pipe lines, main coolant pumps, pressurizer, steam generators, steam lines, emergency core cooling accumulators, boron solution supply tanks and pumps (LP& HP) and KWU accumulators. After preparing the input file and running the code, thermal hydraulic properties such as radial distribution of temperature in fuel rods, temperature distribution in steam generator primary and secondary... 

In this study, the determination of the distribution and the differences concentration of hydrogen in containment of Bushehr power plant by modeling of containment and Hydrogen removal system of Bushehr power plant during LB-LOCA accident is accomplished. In Bushehr nuclear power plant, which has a unique design, the containment is similar to PWR power plants with a metal sphere, but the installed reactor is a VVER-1000. After a full study on the containment and its systems, the required data for modeling is gathered and afterwards, the engineering handbook is prepared for MELCOR input code and then the modeling and size classification of the containment is done in 4 different ways,... 

The application of ultra-high performance concrete (UHPC) as an alternative to conventional/ normal concrete (NC) has grown rapidly in recent years. However, there is limited knowledge on its shear behavior, which is essential for developing design guidelines for structural applications. A detailed parametric study was conducted on 38 beam specimens, half of which were made of UHPC and the other half made of NC. To ensure applicability of findings, two types of UHPC mixes were used, a proprietary and a generic mix. Eighteen of the beams were prepared and tested in Tabriz, Iran, while the other 20 were made and tested in Miami, FL. Test parameters included type of concrete (UHPC and NC),... 

Today safety is one of the major competition factors in automotive industries . The vehicles of today are more and more dependent on electronic systems , for driving safety and ease on control for the driver . Some systems are more or less standard in vehicles on the market , examples of such systems are ABS , ABC , etc. Despite of the effect of these systems on vehicle dynamics ,because they only control longitudinal dynamics and don't receive any feedback from vehicle lateral behavior , now control systems ,named VDC , have been developed and implemented in advanced vehicles. The operation of such systems is as this that in any time instance they evaluate vehicle dynamical behavior.... 

Performing a safe and effective endoscopic sinus and skull based surgery (ESSS), requires special training programs to gain sufficient hand-eye coordination and instrument manipulation skills. In this regard, virtual-based haptic surgical training systems have been considered among the medical students and residents as an effective approach for training practices. Therefore, in this study, the development of a haptic training system for ESSS, based on an animal model has been addressed. By conducting various indentation and relaxation experiments, mechanical properties of the specific sino-nasal regions of sheep head, as a function of force, displacement and tool insertion rate, for three... 

Low back disorders (LBD) is one of the most musculo-skeletal disorders in industrial environments in which it can impose to the society.Therefore, it is very important to reaserch the causes of LBDs, prevention methods and evaluation risk factor in lifting tasks in order to avoid the prevalence of LBDs in society. There is no doubt heavy lifting has a significant role in emerging of LBDs. Hence, many safety risk assessment tools have been made by researchers.Using assessment tools, we need to know the input parameters corrospending to the assessment tools. Input parameters in assessment tools have been measured in a way of traditional method or by expensive equipment in laboratories. On...