Loading Assets...

Milad Moradi

Ph.D. Student in Electrical Engineering

About Me

Milad Moradi ___ M.SC. In Mechanical Engineering

Milad Moradi received the B.Sc. and M.Sc. degrees from the University of Guilan, Rasht, Iran, in 2013 and 2016, respectively. He is currently pursuing the Ph.D. degree with the University of Windsor. The selection as a brilliant talent student during his B.Sc. course, winning a prestigious prize from Iran’s National Elites Foundation, and working as a Research Assistant with ISACLAB, University of Guilan from 2016 to 2020 are his honors and research experiences. His research interests include machine learning, fault diagnosis, and application of these areas in biomedical engineering, and other complex engineering systems areas.

Abilities

They were Referred in My Resume

I Am Attempting to elevate my abilities in different aspect of my work

Experinces

NEKA Power plant

Researcher

Research on the fouling problem in the thermal power plant’s boiler was done. a data-driven condition monitoring scheme to predict the fouling condition and extraction the most important features of this occurrence, modeling subsections of the studied boiler, and doing a survey on this problem were the most prominent parts of this research work.

Summer 2018 - Fall 2019
Fall 2013 - Up To Now

University Of Guilan

Research Asistant

Before and After my graduation in Master’s degree program, in order to enrich my research resume, I worked at Intelligent System & Advanced Control Laboratory (ISAC lab) under the supervision of my Master’s thesis supervisor, Dr. Ali chaibakhsh, as a Research Assistant.

University Of guilan

Researcher

.I was researching on my master thesis under the supervision of my master's supervisor, Dr. Ali Chaibakhsk

fall 2013 - summer 2016
fall 2013

University Of Guilan

Teacher Asistant

  • Teaching assistant for  Linear control , a credit course taught by Prof. Farid Najafi at University of Guilan.
    My responsibilities included grading problem sets and holding classes to solve sample questions in order to prepare the students for midterm and final exams.

University Of Guilan

Teacher Asistant

  • Teaching assistant for  Linear control , a credit course taught by Prof. Farid Najafi at University of Guilan.
    My responsibilities included grading problem sets and holding classes to solve sample questions in order to prepare the students for midterm and final exams.
Spring 2014

Education

My Degrees

Ph.D. Electrical Engineering

University of Windsor

2021-2024

University of Windsor

Diploma

2008

Ranked 3 among the city in the comprehensive diploma examination

GPA: 19.91  / 20

M.SC Mechanical Engineering

Faculty Of Mechanical Engineering, University Of guilan

2013-2016

Accepted through resorting to brilliant talent

123

GPA : 17.22 /20

B.SC Mechanical Engineering

Faculty Of Mechanical Engineering, University Of guilan

2009-2013

Among first 10% of B.Sc. students of department of Mechanical Engineering

123

GPA : 16.73 /20

Papers, Thesis and Certifications

  • ALL
  • Master Thesis
  • Journal Papers
  • Conference Paper
  • Certifications
Multi-Sensor Data Fusion Based Fault Detection and Isolation in a Steam Power Plant Unit
In this thesis, fault detection and isolation based on data / sensor fusion in a 440 MW Benson type steam generator unit was investigated. Due to relatively slow dynamics and time-consuming procedure of recovering and start-up of thermal power plant, preventing from unplanned emergency shutdown would be the main key in enhancing the performances of these units. For this aim, the effective parameters on the undesired system trips during transient conditions first were recognized and then appropriate dataset from real system performances were obtained for fault detection and isolation purposes. Pre-processing of the recorded data was performed to analyze and find the suitable features for distinguishing between normal and abnormal system behaviors, and then the best features were extracted for fault detection. Two different statistical techniques including ReliefF and improved distance evaluation (IDE) were employed for ranking features, then Dempster-Shafer evidence theory were used to fuse the dissimilar results of two methods and to achieve more reliable ranking of features. The most dominant features were selected for using in the fault detection and fault isolation stages. Three different intelligent classification techniques including support vector machine (SVM), neural networks (NN) and adaptive neuro-fuzzy inference systems (ANFIS) were employed for fault detection. The effects of parameters changes on the performances of each approach were investigated. An optimization approach based on genetic algorithm was also employed for finding the optimal parameters in order to enhance the fault detection accuracy of each technique. Finally, the responses of these fault detection techniques were fused by Yager combination rule on decision level to improve the reliability of fault detection system. For the fault isolation stage, a support vector machine based classifier was employed. As a case study, the proposed fault detection and isolation approach was applied for detecting abnormal behaviors of the boiler’s start-up vessel and its level fluctuations during load changes. The performances of fault detection system were evaluated with respect to the similar faults happened at two different periods of time. The obtained results indicated the accuracy and feasibility of the proposed approach for early fault detection and isolation during the unit’s load variations.
Multi-Sensor Data Fusion Based Fault Detection and Isolation in a Steam Power Plant Unit
Early Fault Detection in Transient Conditions for a Steam Power Plant Subsystem Using Support Vector Machine
In this study, an application of support vector machine (SVM) for early fault detection in increasing the level of the start-up vessel in a Benson type once-through boiler during load changes is presented. The level increasing in the start-up vessel is happened due to thermal conditions disruption inside the boiler especially while the unit load is ramped-down. In this regard, first, the variables effective on increasing the level of start-up vessel was identified based on experimental data from a power plant unit, then the dimension of input variables was reduced by selecting appropriate features. Experimental results show that the hotwell surfaces’ temperature could be considered as the most appropriate indicator for steam quality deterioration. By comparing the extracted features from healthy and unhealthy conditions, appropriate fault model was developed using SVM with radial basis function (RBF) as the kernel. The performances of fault detection system were evaluated with respect to the similar faults at two different time periods happen in a steam power plant. The obtained results show the accuracy and feasibility of the proposed approach in early detection of faults during the unit’s load variations. Advantages of the proposed technique is preventing false alarm in power plants’ boilers as load changes.
Early Fault Detection in Transient Conditions for a Steam Power Plant Subsystem Using Support Vector Machine
http://lrr.modares.ac.ir/article-15-5772-en.html
An intelligent hybrid technique for fault detection and condition monitoring of a thermal power plant
Highlights • A Hybrid fault detection approach based on intelligent classifiers was proposed. • Experimental data during emergency shut-downs were employed. • Decision fusion technique was applied to combine the outlet of classifiers. • Fault detection prevented from undesired system trips. Abstract This study presents an application of intelligent fault detection system for recognizing abnormal conditions during transient operation of a steam generator unit. Unobserved dynamics of evaporator section have been caused multiple false alarms and boiler emergency shut-downs. In order to detect faulty conditions, four different classifier agents were employed in parallel. The experimental data from real system performances during system trips were collected to train and validate the intelligent classifiers. The outlet results of all classifiers were combined using Yager's rule of fusion in order to improve the reliability and accuracy of fault detection process. The performances of the proposed fault detection system were evaluated during the unit's load variations and at different scenarios as one or two classifier(s) failed to detect the correct situations. The obtained results indicated the capability and feasibility of the proposed technique in preventing from raising false alarms by early detection of abnormal conditions.
An intelligent hybrid technique for fault detection and condition monitoring of a thermal power plant
https://www.sciencedirect.com/science/article/pii/S0307904X18301185?via%3Dihub
Certifications
Certifications
Certifications
Certifications
Certifications
Certifications
Multi-Feature Fusion Approach for Epileptic Seizure Detection from EEG Signals
Abstract: In this paper, a new fusion scheme based on the Dempster–Shafer Evidence Theory (DSET) is introduced for Epileptic Seizure Detection (ESD) in brain disorders. Firstly, various features in temporal, spectral, and temporal-spectral domains are extracted from Electroencephalogram (EEG) signals. Afterward, a Correlation analysis via the Pearson Correlation Coefficient (PCC) is conducted on the extracted features to select and remove highly correlated features. It leads to the second feature set with about half numbers of the first feature set. Next, three separate filter-type feature selection techniques, including Relief-F (RF), Compensation Distance Evaluation Technique (CDET), and Fisher Score (FS), are conducted to this second feature set for ranking features. Following that, a feature fusion is engaged by the DSET through the individual feature ranking results to generate high qualified feature sets. Indeed, the DSET-based feature fusion is devoted to enhancing the feature selection confidence using the least superb ranked features. In the classification stage, an Ensemble Decision Tree (EDT) classifier, along with two common validation procedures, including hold out and 10-fold cross-validation, is appropriated to classify the selected features from the EEG signals as normal, pre-ictal (epileptic background), and ictal (epileptic seizure) classes. Finally, several test scenarios are investigated using experimental data of Bonn University to evaluate the proposed ESD performance. Moreover, a comparison with other research works on the same dataset and classes is accomplished. The obtained results indicate the effectiveness of the proposed feature fusion approach and superior accuracy compared to the traditional methods.
Multi-Feature Fusion Approach for Epileptic Seizure Detection from EEG Signals
https://ieeexplore.ieee.org/abstract/document/9204737

Contact

Sending Massage

123