arXiv subjects

Alp Akcay

Publications and source records attributed to Alp Akcay.

6 recordsLinked to original sources

arXiv2026

Minimizing Material Waste in Additive Manufacturing through Online Reel Assignment

We study a variant of the online bin packing problem that arises in filament-based 3D printing systems operating in make-to-order settings, where only a limited number of filament reels of finite capacity can be handled at once. Components are assigned to reels upon arrival and insufficient reels are discarded to be replaced with new ones, resulting in material waste. To minimize the long-run average discarded filament through an online assignment policy, we formulate this problem as an infinite-horizon average-cost Markov Decision Process and analyze the structure of policies under stochastic, sequential demand. We first show that under a random allocation policy, the system decomposes into a collection of identical single-reel processes, allowing us to derive a closed-form expression for the average waste and enabling a tractable baseline analysis. Building on this decomposition, we construct a theoretically grounded index policy that assigns each reel a score reflecting the marginal cost of assignment and prove that it constitutes a one-step policy improvement over random allocation. We embed the index-based structure within a Deep Reinforcement Learning framework using approximate policy iteration. The resulting method achieves near-optimal performance across a range of simulated and real-world scenarios. Our results demonstrate that Reinforcement Learning policy significantly reduces material waste while maintaining real-time feasibility and interpretability.

math.OC↗

arXiv2021

Policies for the Dynamic Traveling Maintainer Problem with Alerts

Downtime of industrial assets such as wind turbines and medical imaging devices comes at a sharp cost. To avoid such downtime costs, companies seek to initiate maintenance just before failure. Unfortunately, this is challenging for the following two reasons: On the one hand, because asset failures are notoriously difficult to predict, even in the presence of real-time monitoring devices which signal early degradation. On the other hand, because the available resources to serve a network of geographically dispersed assets are typically limited. In this paper, we propose a novel dynamic traveling maintainer problem with alerts model that incorporates these two challenges and we provide three solution approaches on how to dispatch the limited resources. Namely, we propose: (i) Greedy heuristic approaches that rank assets on urgency, proximity and economic risk; (ii) A novel traveling maintainer heuristic approach that optimizes short-term costs; and (iii) A deep reinforcement learning (DRL) approach that optimizes long-term costs. Each approach has different requirements concerning the available alert information. Experiments with small asset networks show that all methods can approximate the optimal policy when given access to complete condition information. For larger networks, the proposed methods yield competitive policies, with DRL consistently achieving the lowest costs.

math.OC↗

arXiv2021

Biomanufacturing Harvest Optimization with Small Data

In biopharmaceutical manufacturing, fermentation processes play a critical role in productivity and profit. A fermentation process uses living cells with complex biological mechanisms, leading to high variability in the process outputs, namely, the protein and impurity levels. By building on the biological mechanisms of protein and impurity growth, we introduce a stochastic model to characterize the accumulation of the protein and impurity levels in the fermentation process. However, a common challenge in the industry is the availability of only a very limited amount of data, especially in the development and early stages of production. This adds an additional layer of uncertainty, referred to as model risk, due to the difficulty of estimating the model parameters with limited data. In this paper, we study the harvesting decision for a fermentation process (i.e., when to stop the fermentation and collect the production reward) under model risk. We adopt a Bayesian approach to update the unknown parameters of the growth-rate distributions, and use the resulting posterior distributions to characterize the impact of model risk on fermentation output variability. The harvesting problem is formulated as a Markov decision process model with knowledge states that summarize the posterior distributions and hence incorporate the model risk in decision-making. Our case studies at MSD Animal Health demonstrate that the proposed model and solution approach improve the harvesting decisions in real life by achieving substantially higher average output from a fermentation batch along with lower batch-to-batch variability.

stat.ML↗

arXiv2020

Algorithms for slate bandits with non-separable reward functions

In this paper, we study a slate bandit problem where the function that determines the slate-level reward is non-separable: the optimal value of the function cannot be determined by learning the optimal action for each slot. We are mainly concerned with cases where the number of slates is large relative to the time horizon, so that trying each slate as a separate arm in a traditional multi-armed bandit, would not be feasible. Our main contribution is the design of algorithms that still have sub-linear regret with respect to the time horizon, despite the large number of slates. Experimental results on simulated data and real-world data show that our proposed method outperforms popular benchmark bandit algorithms.

stat.ML↗

arXiv2020

Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning

Recent works using deep learning to solve the Traveling Salesman Problem (TSP) have focused on learning construction heuristics. Such approaches find TSP solutions of good quality but require additional procedures such as beam search and sampling to improve solutions and achieve state-of-the-art performance. However, few studies have focused on improvement heuristics, where a given solution is improved until reaching a near-optimal one. In this work, we propose to learn a local search heuristic based on 2-opt operators via deep reinforcement learning. We propose a policy gradient algorithm to learn a stochastic policy that selects 2-opt operations given a current solution. Moreover, we introduce a policy neural network that leverages a pointing attention mechanism, which unlike previous works, can be easily extended to more general k-opt moves. Our results show that the learned policies can improve even over random initial solutions and approach near-optimal solutions at a faster rate than previous state-of-the-art deep learning methods.

cs.LG↗

arXiv2019

Remaining Useful Lifetime Prediction via Deep Domain Adaptation

In Prognostics and Health Management (PHM) sufficient prior observed degradation data is usually critical for Remaining Useful Lifetime (RUL) prediction. Most previous data-driven prediction methods assume that training (source) and testing (target) condition monitoring data have similar distributions. However, due to different operating conditions, fault modes, noise and equipment updates distribution shift exists across different data domains. This shift reduces the performance of predictive models previously built to specific conditions when no observed run-to-failure data is available for retraining. To address this issue, this paper proposes a new data-driven approach for domain adaptation in prognostics using Long Short-Term Neural Networks (LSTM). We use a time window approach to extract temporal information from time-series data in a source domain with observed RUL values and a target domain containing only sensor information. We propose a Domain Adversarial Neural Network (DANN) approach to learn domain-invariant features that can be used to predict the RUL in the target domain. The experimental results show that the proposed method can provide more reliable RUL predictions under datasets with different operating conditions and fault modes. These results suggest that the proposed method offers a promising approach to performing domain adaptation in practical PHM applications.

cs.LG↗