AV¾ãÀÖ²¿

You are cordially invited to the Graduate Student Research Seminar of the Department of Industrial Engineering.

Date: Wednesday, March 26, 2025
Time: 1:00pm – 3:40pm AST
In Person:ÌýÌýÌýÌýÌýÌýÌýÌýÌýÌý Room MA310, Sexton Campus

Online:Ìý°Õ±ð²¹³¾²õ:ÌýÌýÌýÌý
(Meeting ID:Ìý226 323 499 964;ÌýPasscode:ÌýPe7Uj3ZE)

Schedule:

Abstracts:

Design of Picker-to-Parts Warehouse Fulfillment Sections Using Surrogate Machine Learning Model
Basava Sri Krishna Vamsy Lanka, MASc. Student

The design of picker-to-parts warehouse sections contains various decision parameters such as warehouse dimensions, routing policy and storage assignment policy. Assessing the holistic importance of each decision parameter cannot be easily measured or quantified due to their mutual interdependence. It is crucial to obtain this information and investigate the possible combinations of policies and warehouse specifications. To solve this problem we use a surrogate machine learning model to simulate the warehouse conditions across varying pick list size. Seasonally varying demand and pick face requirements are also considered. Dataset derived from simulation is fed to train various machine learning algorithm. The model uses Monte Carlo method and average travel distance as the output parameter to evaluate performance. The Random Forest, Decision Tree, Gradient Boost, XG Boost, LightGMB, CatBoost and a tuned Artificial Neural Network show the best performance in terms of error and fit. SHAP feature importance is calculated and analyzed. Warehouse design practitioners and fourth party logistics can easily adapt and deploy the developed warehouse simulation methodology and machine learning model to help with bid design in determining optimal warehouse parameters and policies.

A Network-based Simulation Model for Helicopter Rescue Time Estimation in the Canadian Arctic
Mahroo Mohammadi, MASc. Student

Search-and-rescue (SAR) helicopter operations in the remote Canadian Arctic encounter extreme weather conditions, limited infrastructure, and vast distances. To improve response times, this study develops a network-based simulation model aimed at supporting helicopter rescue missions in harsh environments. The model combines network analysis techniques, high-resolution meteorological data, and simulation-based evaluation to create realistic rescue scenarios and determine efficient routes from SAR bases to potential incident sites. The methodology is divided into four phases. In Phase One, weather data from Spire Global is acquired and processed from GRIB files into a structured format. Key meteorological parameters—temperature, wind speed, visibility, and precipitation—are used to classify flight conditions as favorable, unfavorable, or no-go, establishing mission feasibility under rapidly changing conditions. Phase Two generates possible routes connecting multiple SAR bases to incident locations across the Arctic using a Breadth-First Search algorithm that considers constraints such as route length, fuel capacity, and refueling requirements. In Phase Three, the weather framework is integrated into the candidate route network by dividing each route into segments and assessing meteorological conditions for every segment, capturing the impact of localized weather variability on helicopter performance. Finally, Phase Four applies discrete-event techniques to model complete SAR missions. The simulation covers helicopter dispatch, flight operations, refueling stops, and on-scene rescue procedures, yielding quantitative estimates of rescue times and revealing potential operational bottlenecks. Preliminary findings indicate incorporating local weather data with operational constraints influences route selection and mission duration, providing a tool for SAR coordinators, policymakers, and emergency planners.

A Hybrid Bi-LSTM Model for Data-Driven Maintenance Planning
Alex Noussis, MASc. Student

Modern industries depend on the reliable operation of a multitude of assets under constrained resources. The advent of Industry 4.0 has increased the use of sensors for monitoring asset/system performance, while deep learning models have allowed for accurate system health predictions, enabling more effective maintenance planning. Most existing papers on intelligent maintenance develop deep learning models solely for asset remaining useful life (RUL) point predictions. However, this paper develops a hybrid model utilizing bi-directional long short-term memory and dense neural network architecture with Monte Carlo dropout to generate a set of RUL predictions. This set of point estimates is then integrated within a selective maintenance problem (SMP) optimization framework using sample average approximation to inform maintenance planning. The proposed hybrid deep learning and optimization model is used to plan the maintenance of a mission-oriented series k-out-of-n:G system. Numerical experiments are performed to compare the model’s performance against prior SMP methods and highlight its strengths and limitations. The proposed method is found to frequently produce maintenance plans resulting in mission survival while also being capable of avoiding unnecessary maintenance actions when minimizing costs.

Optimizing a Staged Net-Zero Transition Strategy for Small Communities under Multi-Horizon Uncertainty: Models and Insights
Mostafa Mostafavi Sani, Ph.D. Candidate

The transition of diesel-dependent communities to renewable energy (RE) is crucial for achieving the net-zero targets. However, optimally planning this transition is challenging due to uncertainty about future levels of technology maturity and regulator-imposed policies such as carbon caps. In this context, a staged transition strategy is hypothesized to reduce energy costs compared to one that prescribes immediate large-scale deployment, as the former can benefit from the declining costs of RE technologies and adapt to different carbon policies. This research proposes a multi-stage stochastic-robust optimization model to test this hypothesis and help policymakers design cost-effective net-zero staged transition strategies while considering numerous technologies and energy carriers, including hydrogen. Short-term uncertainties in demand and RE supply are handled via an adaptive robust optimization framework to achieve high reliability, whereas a developed multi-stage stochastic programming approach deals with long-term uncertainties. An exact augmented column-and-constraint-generation algorithm is developed to solve the problem efficiently, with each subproblem representing a node in the decision tree. A real case study that spans 25 years, divided into five stages with 32 scenarios, is used to test the proposed approach. Results demonstrate the substantial cost advantage of the staged strategy due to the gradual addition of cost-effective technologies like photovoltaic-thermal and combined-heat-and-power instead of installing expensive technologies like fuel-cells upfront. Moreover, considering multiple scenarios for technology cost declines and carbon caps enables further cost reduction, albeit small, compared to using a single trajectory. The transition strategies developed for specific scenarios are carefully analyzed to understand the effect of different factors and draw useful insights.

Sustainable Energy Transition for the Mining Industry: A Bibliometric Analysis of Trends and Emerging Research Pathways
Angela Amegboleza, Ph.D. Student

The mining industry (MI), one of the largest energy consumers globally, is under increasing pressure to transition towards more sustainable energy systems. This paper explores the current trends in sustainable energy transition (SET) in mining operations, focusing on integrating renewable energy, decarbonization efforts, economic and technological enablers, and sustainability frameworks. Through a systematic literature review utilizing bibliometric tools such as Scopus and VOSviewerÌý1.6.20, this study identifies key themes, trends, and challenges shaping the future of energy transition in mining. Despite advancements in renewable technologies such as solar, wind, and hydrogen, the MI faces significant barriers, including high upfront costs, logistical challenges in remote operations, and inconsistent regional decarbonization policies. The review highlights the importance of global regulatory alignment, technological innovation, and financial mechanisms to overcome these challenges and accelerate the industry’s shift towards clean energy. Future research directions address gaps in renewable energy deployment, energy efficiency, and sustainability practices in the mining sector. This study aims to contribute to the academic discourse and provide actionable insights for industry stakeholders striving to achieve a SET.

Decision-Making Models for Sustainable Displaced Persons Campsites Selection
Clifford Ojukannaiye, Ph.D. Student

The rise in global displacement due to natural and man-made disasters necessitates effective decision-making models for selecting sustainable campsites for displaced persons. Prior studies have utilized various decision-making techniques adopting multi-criteria approaches to evaluate displaced persons' shelter site selection while balancing environmental, social, and economic sustainability factors. However, a comprehensive synthesis of these models, selection criteria, sub-criteria, and their applications in the phases of the disaster management cycle has not been explored. This study examines decision-making models applied to sustainable campsite selection, incorporating a meta-analysis approach. A thorough screening process based on predefined inclusion and exclusion criteria was conducted following the PRISMA protocol, reviewing 2,053 records published between 2014 and 2024 in Scopus and Google Scholar databases. Out of these 28 eligible articles were selected for review. The selected studies were analyzed by sustainability criteria, sub-criteria, indicators, problem areas, methodologies, and goals. The findings reveal that Multi-Criteria Decision Analysis (MCDA) and Geographic Information Systems (GIS)- based models are the dominant approaches in campsite selection. Key sustainability factors include environmental impact, accessibility, and socio-economic considerations; the application area is mainly in pre-disaster earthquake planning. However, these models lack robust uncertainty and dynamic adaptability to changing conditions. This review introduces new sustainability criteria, integrating community engagement, and site efficiency into campsite selection models. Ìýdditionally, methodological gaps in previous studies are identified, highlighting the need for hybrid decision-support frameworks that incorporate machine learning, participatory approaches, and mathematical models for man-made disasters preparedness.

Contact Person:
Hamid Afshari, Ph.D., P.Eng.
email: hamid.afshari@dal.caÌý