A5078040373- Advanced Vision and Imaging
- Aluminum Alloys Composites Properties
- Robotics and Sensor-Based Localization
- Mineral Processing and Grinding
- Advanced Image and Video Retrieval Techniques
- Advanced ceramic materials synthesis
- Reliability and Maintenance Optimization
- Magnesium Alloys: Properties and Applications
- Granular flow and fluidized beds
- Optical measurement and interference techniques
- Landslides and related hazards
- Fault Detection and Control Systems
- Corrosion Behavior and Inhibition
- Machine Fault Diagnosis Techniques
- Anomaly Detection Techniques and Applications
- Advanced Statistical Process Monitoring
- Particle Dynamics in Fluid Flows
- Hydrology and Sediment Transport Processes
- Advanced Drug Delivery Systems
- Assembly Line Balancing Optimization
- Risk and Portfolio Optimization
- Machine Learning and Data Classification
- Scheduling and Optimization Algorithms
- Pharmaceutical studies and practices
- Tropical and Extratropical Cyclones Research
Islamic Azad University, Isfahan
2025
Kharazmi University
2025
Dalhousie University
2012-2024
National University of Skills
2024
West Virginia University
2023
Clemson University
2022-2023
École Polytechnique Fédérale de Lausanne
2012-2021
Shahid Bahonar University of Kerman
2015-2021
Technische Universität Berlin
2017-2020
Ludwig-Maximilians-Universität München
2019
Condition based maintenance (CBM) is on collecting observations over time, in order to assess equipment's state, prevent its failure and determine the optimal strategies. In this paper, we derive an CBM replacement policy when state of equipment unknown but can be estimated observed condition. We use a proportional hazards model (PHM) represent system's degradation. Since unknown, optimization formulated as partially Markov decision process (POMDP), problem solved using dynamic programming....
This article proposes a model to calculate the reliability function, and mean residual (remaining) life of piece equipment, when its degradation state is not directly observable. At each observation moment, an indicator underlying unobservable observed, monitoring information collected. The process due condition system where obtained perfect. For that reason, doesn't reveal exact state. To match indicator's value state, stochastic relation between them given by probability matrix. It assumed...
The effect of synthesized 5-((4-hydroxy-3,5-di-tert-butylphenyl)diazenyl)isophthalic acid (HBA) containing a hinderedphenol derivative on the thermooxidation, hydrochloric release time, and mechanical strength PVC/CuO nanocompositeswas studied. Moreover, 5-((4-hydroxy-2,5-dimethylphenyl)diazenyl)isophthalic (HMA) was for comparison ofcorresponding PVC nanocomposite properties. thin films were prepared through in situ surface modificationof CuO nanoparticles with HBA HMA, individually,...
This article proposes methods to estimate the parameters of condition monitored equipment whose failure rate follows Cox's time-dependent Proportional Hazards Model. Due errors measurement, interpretation, or due limited accuracy measurement instruments, observation process is not perfect, and does directly reveal exact degradation state. At each moment, we observe collect information about an indicator underlying unobservable To match indicator's value state, stochastic relation between...
Abstract In this study, a magnetic disk was prepared using nanoparticles with diameter of less than 15 nm. The morphological and structural characteristics these were systematically examined X‐ray diffraction (XRD), scanning electron microscopy (SEM), transmission (TEM), alternating force gradient magnetometry (AGFM). XRD analysis confirmed that the average copper–magnesium ferrite doped cadmium approximately 12 nm, consistent TEM results, which also showed uniform particle distribution...
This paper develops a prognostics model to estimate the Mean Residual Life of Rail Wagon Bearings within certain confidence intervals. The is constructed using Proportional Hazards approach, informed by imperfect data from bearing acoustic monitoring system, and failure database. supports prediction defined maintenance planning window time receipt latest condition information. We use decide whether replace bearing, or leave it until collection next indicators. tested on limited number cases,...
Abstract Electromagnetic Time Reversal (EMTR) has been used to locate different types of electromagnetic sources. We propose a novel technique based on the combination EMTR and Machine Learning (ML) for source localization. show first time that ML techniques can be in conjunction with reduce required number sensors only one localization sources presence scatterers. In part, we use 2D-FDTD method generate 2D profiles vertical electric field as RGB images. Next, take advantage transfer...
During recent years, active learning has evolved into a popular paradigm for utilizing user's feedback to improve accuracy of algorithms. Active works by selecting the most informative sample among unlabeled data and querying label that point from user. Many different methods such as uncertainty sampling minimum risk have been utilized select in learning. Although many algorithms proposed so far, them work with binary or multi-class classification problems therefore can not be applied which...