Learning to Optimize Capacity Planning in Semiconductor Manufacturing

• URL: http://arxiv.org/abs/2509.15767v1
• Date: Fri, 19 Sep 2025 08:51:10 GMT
• Title: Learning to Optimize Capacity Planning in Semiconductor Manufacturing
• Authors: Philipp Andelfinger, Jieyi Bi, Qiuyu Zhu, Jianan Zhou, Bo Zhang, Fei Fei Zhang, Chew Wye Chan, Boon Ping Gan, Wentong Cai, Jie Zhang,
• Abstract summary: In semiconductor manufacturing, capacity planning is the process of allocating production resources in accordance with variable demand.<n>Here, we present a neural network-based model for capacity planning on the level of individual machines, trained using deep reinforcement learning.
• Score: 16.026880823025948
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In manufacturing, capacity planning is the process of allocating production resources in accordance with variable demand. The current industry practice in semiconductor manufacturing typically applies heuristic rules to prioritize actions, such as future change lists that account for incoming machine and recipe dedications. However, while offering interpretability, heuristics cannot easily account for the complex interactions along the process flow that can gradually lead to the formation of bottlenecks. Here, we present a neural network-based model for capacity planning on the level of individual machines, trained using deep reinforcement learning. By representing the policy using a heterogeneous graph neural network, the model directly captures the diverse relationships among machines and processing steps, allowing for proactive decision-making. We describe several measures taken to achieve sufficient scalability to tackle the vast space of possible machine-level actions. Our evaluation results cover Intel's small-scale Minifab model and preliminary experiments using the popular SMT2020 testbed. In the largest tested scenario, our trained policy increases throughput and decreases cycle time by about 1.8% each.

Related papers

• Novel Multi-Agent Action Masked Deep Reinforcement Learning for General Industrial Assembly Lines Balancing Problems [1.8434042562191815]
  This paper introduces a novel mathematical model of a generic industrial assembly line formulated as a Markov Decision Process (MDP)<n>The proposed model is employed to create a virtual environment for training Deep Reinforcement Learning (DRL) agents to optimize task and resource scheduling.
  arXiv  Detail & Related papers  (2025-07-22T14:34:36Z)
• KAT-V1: Kwai-AutoThink Technical Report [50.84483585850113]
  We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks.<n>KAT dynamically switches between reasoning and non-reasoning modes based on task complexity.<n>We also propose Step-SRPO, a reinforcement learning algorithm that incorporates intermediate supervision into the GRPO framework.
  arXiv  Detail & Related papers  (2025-07-11T04:07:10Z)
• MoSE: Skill-by-Skill Mixture-of-Experts Learning for Embodied Autonomous Machines [14.042949333988785]
  We introduce a novel Mixture-of-Expert (MoE) method that significantly boosts reasoning and learning efficiency for embodied AI.<n>General MoE models demand extensive training data and complex optimization, which limits their applicability in embodied AI.<n>We propose a skill-oriented MoE called MoSE, which mimics the human learning and reasoning process skill-by-skill, step-by-step.
  arXiv  Detail & Related papers  (2025-07-10T14:48:08Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Efficient Domain Adaptation of Multimodal Embeddings using Constrastive Learning [0.08192907805418582]
  Current approaches either yield subpar results when using pretrained models without task-specific adaptation, or require substantial computational resources for fine-tuning.<n>We propose a novel method for adapting foundational, multimodal embeddings to downstream tasks, without the need of expensive fine-tuning processes.
  arXiv  Detail & Related papers  (2025-02-04T06:30:12Z)
• The Artificial Neural Twin -- Process Optimization and Continual Learning in Distributed Process Chains [3.79770624632814]
  We propose the Artificial Neural Twin, which combines concepts from model predictive control, deep learning, and sensor networks. Our approach introduces differentiable data fusion to estimate the state of distributed process steps. By treating the interconnected process steps as a quasi neural-network, we can backpropagate loss gradients for process optimization or model fine-tuning to process parameters.
  arXiv  Detail & Related papers  (2024-03-27T08:34:39Z)
• When Parameter-efficient Tuning Meets General-purpose Vision-language Models [65.19127815275307]
  PETAL revolutionizes the training process by requiring only 0.5% of the total parameters, achieved through a unique mode approximation technique. Our experiments reveal that PETAL not only outperforms current state-of-the-art methods in most scenarios but also surpasses full fine-tuning models in effectiveness.
  arXiv  Detail & Related papers  (2023-12-16T17:13:08Z)
• Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic Assembly [20.92328610763089]
  We propose a density-based feasibility learning method that requires only feasible examples. Empirically, the proposed method is demonstrated on robotic assembly use cases and outperforms other single-class baselines.
  arXiv  Detail & Related papers  (2023-07-03T19:43:53Z)
• Unifying Synergies between Self-supervised Learning and Dynamic Computation [53.66628188936682]
  We present a novel perspective on the interplay between SSL and DC paradigms. We show that it is feasible to simultaneously learn a dense and gated sub-network from scratch in a SSL setting. The co-evolution during pre-training of both dense and gated encoder offers a good accuracy-efficiency trade-off.
  arXiv  Detail & Related papers  (2023-01-22T17:12:58Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• A Survey on Large-scale Machine Learning [67.6997613600942]
  Machine learning can provide deep insights into data, allowing machines to make high-quality predictions. Most sophisticated machine learning approaches suffer from huge time costs when operating on large-scale data. Large-scale Machine Learning aims to learn patterns from big data with comparable performance efficiently.
  arXiv  Detail & Related papers  (2020-08-10T06:07:52Z)
• Workload Prediction of Business Processes -- An Approach Based on Process Mining and Recurrent Neural Networks [0.0]
  We propose a process mining approach that reconstructs the historical workload of a company and predicts the workload using neural networks. Our method relies on logs, representing the history of business processes related to manufacturing. An evaluation and illustration of the method is performed on the administrative processes of Heraeus Materials SA.
  arXiv  Detail & Related papers  (2020-02-14T08:19:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.