Amin Kaboli | EPFL Graph Search

Dr. Amin Kaboli is an external lecturer for at the Mechanical Engineering Section at EPFL and teaches Production Management (ME-419), Continuous Improvement (ME-498) to graduate students and Digital Supply Chain, Innovation and Digitization, and Sustainable Change Leadership to business executives and managers at International Institute for the Management of Logistics and Supply Chain (IML). Amin supports many organizations ranging from Fortune 500 corporations to entrepreneurial firms and industries as diverse as Watch, Consumer Goods, Food and Beverage, MedTech, and Pharma. He obtained his Ph.D. in Manufacturing Systems & Robotics, specialized in Supply Chain Management from EPFL. You can watch his TEDx talk on “Leading Change Consciously” here. TEDx talk here.

A multi-functional tri-objective mathematical model for the pharmaceutical supply chain considering congestion of drugs in factories

Amin Kaboli

Supply Chain Management (SCM), by way of one of the critical issues in the managerial aspect, plays a significant role in tackling humanitarian problems and difficulties. Due to some limitations (e.g., production capacity and storage capacity) and desires (e.g., cost reduction and rising revenues), supply chain managers always seek the best response to the amount and type of communication between different SCM levels. In the upcoming research, a Pharmaceutical Supply Chain (PSC) with three objective functions is developed, aiming to simultaneously minimize total costs, unfulfilled demands, and reduce the waiting time at the factory entrance. In the forthcoming research, the subject literature and research in the PSC modeling and problem-solving are discussed. A nonlinear programming model is then proposed in line with the previous research to solve the existing short-comings. Also, multi-objective decision-making methods are used to match the conflicting objectives of the model simultaneously. Then, GAMS commercial software is used to solve the problem of different sizes. Finally, the wide sensitivity analysis and evaluation of the results are discussed, and future development suggestions are presented.

ELSEVIER SCI LTD2022

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery

Amin Kaboli

Fault diagnosis plays an essential role in reducing the maintenance costs of rotating machinery manufacturing systems. In many real applications of fault detection and diagnosis, data tend to be imbalanced, meaning that the number of samples for some fault classes is much less than the normal data samples. At the same time, in an industrial condition, accelerometers encounter high levels of disruptive signals and the collected samples turn out to be heavily noisy. As a consequence, many traditional Fault Detection and Diagnosis (FDD) frameworks get poor classification performances when dealing with real-world circumstances. Three main solutions have been proposed in the literature to cope with this problem: (1) the implementation of generative algorithms to increase the amount of under-represented input samples, (2) the employment of a classifier being powerful to learn from imbalanced and noisy data, (3) the development of an efficient data preprocessing including feature extraction and data augmentation. This paper proposes a hybrid framework which uses the three aforementioned components to achieve an effective signal based FDD system for imbalanced conditions. Specifically, it first extracts the fault features, using Fourier and wavelet transforms to make full use of the signals. Then, it employs Wasserstein Generative Adversarial with Gradient Penalty Networks (WGAN-GP) to generate synthetic samples to populate the rare fault class and enrich the training set. Moreover, to achieve a higher performance a novel combination of Convolutional Long Short-term Memory (CLSTM) and Weighted Extreme Learning Machine (WELM) is also proposed. To verify the effectiveness of the developed framework, different bearing datasets settings on different imbalance severities and noise degrees were used. The comparative results demonstrate that in different scenarios GAN-CLSTM-ELM significantly outperforms the other state-of-the-art FDD frameworks.

MDPI2022

On the role of trust types and levels on inventory replenishment decision

Naoufel Cheikhrouhou, Maryam Darvish, Rémy Glardon, Amin Kaboli

Using a participatory simulation platform, this paper investigates the inventory replenishment decisions made under different trust categories. Depending on the type of trust (trust in supplier versus trust in customer) and level of trust (high versus low), each decision is categorized and analyzed. We investigate how the inventory manager`s ordering behavior varies regarding their type and level of trust. This study provides evidence for the role of trust in inventory replenishment decision. The findings on the influence of trust on inventory decision indicators provide a new perspective in respect to the supply chain management literature, which generally postulates a positive influence of trust on supply chain stability and uncertainty reduction.

2014

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery

Amin Kaboli

MDPI2022