A survey of semiconductor supply chain models Part II: demand planning, inventory management, and capacity planning

Uzsoy, Reha; Fowler, John W.; Mönch, Lars

doi:10.1080/00207543.2018.1424363

Cited by 52 publications

(12 citation statements)

References 121 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We formulate the problem of finding the best augmentation policy as a discrete search problem. The operations we searched were rotation (5,10,15,20,25,30,35,40,45), flipping (horizontal and vertical), shifting (width and height), shearing range (horizontal and vertical), and zooming (1%-20%). In total, we have 46 operations in the search space.…”

Section: ) Policy Searchmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Pre-Training of Imbalanced Data for Identification of Wafer Map Defect Patterns

et al. 2021

View full text Add to dashboard Cite

Visual defect inspection and classification are significant steps of most manufacturing processes in the semiconductor and electronics industries. Known and unknown defects on wafer maps tend to cluster, and these spatial patterns provide valuable process information for supporting manufacturing in determining the root causes of abnormal processes. In previous studies, data augmentation-based deep learning (DL) techniques were most commonly used for the identification of wafer map defect patterns (WMDP). Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations were manually designed for the WMDP problem. In this study, we propose a DL-based method with automatic data augmentation for the WMDP task. Basically, it focuses on learning effective discriminative features, from wafer maps, through a deep network structure. The network consists of a convolution-based variational autoencoder (CVAE) sequentially. First, we pre-trained the CVAE on large training data in an unsupervised manner. Second, we fine-tuned the encoder of the CVAE, which was followed by a neural network (NN) classifier, in a supervised manner. Additionally, we describe a simple procedure for automatically searching for improved data augmentation policies. The policy mainly consists of five image processing functions: rotation, flipping, shifting, shearing range, and zooming. The effectiveness of the proposed method was demonstrated through experimental results obtained from a simulation dataset and a real-world wafer map dataset (WM-811K). This study provides guidance for the application of deep learning in semiconductor manufacturing processes to improve product quality and yield.INDEX TERMS Classification, convolutional variational autoencoder, deep learning, imbalanced data, neural network, unsupervised pre-training, variational autoencoder, wafer map defect patterns.

show abstract

Section: ) Policy Searchmentioning

confidence: 99%

“…In conjunction with the fourth industrial revolution, the semiconductor market has been expanding rapidly [1][2][3]. Semiconductor demand has been exploding in areas such as smartphones, virtual reality, automobiles, wearable devices, internet of things (IoT), and robotics [4][5][6]. Many diverse products are in demand.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Pre-Training of Imbalanced Data for Identification of Wafer Map Defect Patterns

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Most of the existing business model frameworks categorize it under a general category of “key activities” or “resources” (Osterwalder et al , 2015). However, operational feasibility is much more technical involving cost-efficiencies, supplier relationships (Murthy and Paul, 2017), quality standards (Andrade et al , 2017), capacity planning (Uzsoy et al , 2018) and management of operational risks (McConnell and Blacker, 2013; Slack et al , 2015). These specific measures have not been adequately captured in the existing business model frameworks.…”

Section: Literature Review and Hypothesis Developmentmentioning

confidence: 99%

SECURE – a new business model framework for measuring start-up performance

Arshi

Rao

Islam

et al. 2020

JEEE

View full text Add to dashboard Cite

Purpose Existing business model frameworks show weak conceptual unification, a paucity of measurement focus and limitations when applied in emerging economies. The study proposes a new business model framework – “Start-up Evaluation Calculus Using Research Evidence” (SECURE). The purpose of this study is to allow the measurement of the impact of business model design on start-up performance in emerging economies. Design/methodology/approach Data collected from 713 entrepreneurs in select cities of India, Oman and the United Arab Emirates is analyzed through structural equation modeling. The study uses measurement and structural models to examine the validity of measures and additionally tests the five hypothesized relationships proposed in the study. Findings The SECURE’s components comprising desirability, marketability, feasibility, scalability and viability showed validity and reliability. They synergistically demonstrated a statistically significant effect on a mix of financial and non-financial start-up performance outcomes. An alternative structural relationship that examined the impact of SECURE on only financial performance outcomes showed a weaker model fit. The findings indicate that a business model framework is useful when its ex ante measures show a positive causal effect on the desired performance outcomes. Practical implications The scores obtained by the SECURE framework serve as an evaluative tool that informs entrepreneurs and start-ups on the readiness of their proposed, incubated or existing start-ups. Originality/value Replacing subjective judgments with objective assessment criteria, SECURE is one of the first quantitative and performance-driven business model frameworks that contain measures from all functional domains of a start-up business. Start-ups can evaluate their business models against the SECURE model’s research-driven quantitative criteria and assess their impact on start-up performance.

show abstract

“…3) Successes and opportunities in modelling and integrating planning, scheduling, equipment configuration and fab capability assessment [76], [77]; 4) E-markets and SC collaboration [78], and 5) Strategic SC network design and SC simulation models [79], [80], [80]. According to [81] and [79], one future direction of semiconductor industry would be global SC simulation models based on a marketing-operations perspective which leads another research direction in the area of operations management such as production planning and demand fulfillment, inventory control, capacity and demand planning, and marketing and sales models.…”

Section: A Semiconductor Supply Chain Managementmentioning

confidence: 99%

Development of Smart Semiconductor Manufacturing: Operations Research and Data Science Perspectives

Khakifirooz

Fathi

2019

IEEE Access

View full text Add to dashboard Cite

With advances in information and telecommunication technologies and data-enabled decision making, smart manufacturing can be an essential component of sustainable development. In the era of the smart world, semiconductor industry is one of the few global industries that are in a growth mode to smartness, due to worldwide demand. The important opportunities that can boost the cost reduction of productivity and improve quality in wafer fabrication are based on the simulations of actual environment in Cyber-Physical Space and integrate them with decentralized decision-making systems. However, this integration faced the industry with novel unique challenges. The stream of the data from sensors, robots, and Cyber-Physical Space can aid to make the manufacturing smart. Therefore, it would be an increased need for modeling, optimization, and simulation for the value delivery from manufacturing data. This paper aims to review the success story of smart manufacturing in semiconductor industry with the focus on data-enabled decision making and optimization applications based on operations research and data science perspective. In addition, we will discuss future research directions and new challenges for this industry.

show abstract

A survey of semiconductor supply chain models Part II: demand planning, inventory management, and capacity planning

Cited by 52 publications

References 121 publications

Unsupervised Pre-Training of Imbalanced Data for Identification of Wafer Map Defect Patterns

Unsupervised Pre-Training of Imbalanced Data for Identification of Wafer Map Defect Patterns

SECURE – a new business model framework for measuring start-up performance

Development of Smart Semiconductor Manufacturing: Operations Research and Data Science Perspectives

Contact Info

Product

Resources

About