Semiconductor Manufacturing Final Test Yield Optimization and Wafer Acceptance Test Parameter Inverse Design Using Multi-Objective Optimization Algorithms

Jiang, Dan; Wan, Lin; Raghavan, Nagarajan

doi:10.1109/access.2021.3117576

Cited by 6 publications

(5 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A lot of papers, 2,4,6,11,[13][14][15][16][17][18][19][20][21][22][23] however, investigate yield prediction with supervised regression models. They are summarised in Table 2.…”

Section: Regression Modelsmentioning

confidence: 99%

“…It is interesting to look at the performance of the methods in relation to the underlying data. A number of authors 4,11,13,14,17,19,20,23,26 work with Wafer Test data/ Wafer Acceptance Test(WAT) which is also refered to Process Control Monitoring(PCM) data. Jiang et al 13,14 and Kim 20 et al had results above 0.9 for R 2 values.…”

Section: Regression Modelsmentioning

confidence: 99%

“…A number of authors 4,11,13,14,17,19,20,23,26 work with Wafer Test data/ Wafer Acceptance Test(WAT) which is also refered to Process Control Monitoring(PCM) data. Jiang et al 13,14 and Kim 20 et al had results above 0.9 for R 2 values. Xu 23 et al (R 2 = 0.85) and Lenhard et al 19 (MAE =1.08) also obtained good results.…”

Section: Regression Modelsmentioning

confidence: 99%

“…A small number of authors 13,14,23,25 worked on unsupervised learning methods for the wafer yield prediction. While Jiang et al 13,14,25 used unsupervised learning to find suitable classes, they predicted yield with supervised learning. Xu et al 23 used unsupervised learning to find the best parameters for prediction.…”

Section: Unsupervised Learning Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Wafer yield prediction using AI: potentials and pitfalls

Busch

Wahl

Choubey

2023

Metrology, Inspection, and Process Control XXXVII

View full text Add to dashboard Cite

Yield prediction is highly beneficial in semiconductor manufacturing and hence has attracted significant research interest. A number of recent techniques to do so have utilized machine-learning techniques to improve prediction accuracy. However, the diversity of algorithms used in the wide application domains of semiconductors fabrication make it difficult to compare them as well as to identify key models to use in future. In this paper, we navigate this diversity by conducting an extensive literature research with the aspects of the different data used and the different algorithms applied. Various ML algorithms have their unique strengths and weaknesses, which makes them differently suited for different aspects of yield prediction. In addition, we also consider whether regression analyses or classification analyses are used to nd potentials and pitfalls in this area. We will analyse the type of data being used and various pre-processing techniques proposed. In addition, we will also analyse the practical implementation of these models. A lot has already been achieved on yield prediction, but every future improvement that enables significant cost saving by making it easier to optimally coordinate the individual processes and perhaps detect errors earlier is more than welcome. This review paper provides a foundation for model and data selection for yield prediction based on current state of the art.

show abstract

“…A lot of papers, 2,4,6,11,[13][14][15][16][17][18][19][20][21][22][23] however, investigate yield prediction with supervised regression models. They are summarised in Table 2.…”

Section: Regression Modelsmentioning

confidence: 99%

Section: Regression Modelsmentioning

confidence: 99%

Section: Regression Modelsmentioning

confidence: 99%

Section: Unsupervised Learning Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Wafer yield prediction using AI: potentials and pitfalls

Busch

Wahl

Choubey

2023

Metrology, Inspection, and Process Control XXXVII

View full text Add to dashboard Cite

show abstract

“…The semiconductor industry has been experiencing growth and advancement in chip development, but the shortage has highlighted the need for strategies to address the crisis. The optimization of manufacturing yield has become crucial in semiconductor operations due to the increasing cost of fabrication and global supply shortage situations(Jiang et al, 2021). In response to the shortage, strategies include adopting innovative strategies to mitigate supply chain disruptions, such as using data analytics for operational risk management and developing innovative manufacturing focusing on big data.…”

mentioning

confidence: 99%

Supply Chain Resilience Meets Quality Management

Albalushi,

Mishra,

Abebe

2023

J. Professional Business Review

View full text Add to dashboard Cite

Purpose: This study is aimed at supply chain resilience and quality management, which are critical in today's volatile global economy marked by various disruptions. The focus is on how these traditionally separate disciplines can be combined to enhance organizational performance. Theoretical framework: The theoretical framework revolves around the concepts of supply chain resilience, which includes elements like proactive risk assessment, adaptability, collaborative networks, strategic redundancies, and quality management principles. The research scrutinizes their interplay, revealing significant overlap and implications for organizational outcomes. Design/Methodology/Approach: An exploratory case study approach forms the core methodology, primarily utilizing secondary data to gain insights into real-world scenarios. This approach enables a deep understanding of the critical factors influencing supply chain resilience and the impact of quality management concepts on customer satisfaction and product/service quality in supply chain processes. The questionnaire is distributed to get insights into the company's practices. Findings: The findings indicate that integrating supply chain resilience with quality management leads to more sustained and improved organizational outcomes. A resilient supply chain is quicker to recover from disruptions, minimizing financial impacts. Concurrently, a steadfast focus on quality ensures customer satisfaction and loyalty. This integration offers synergistic benefits, contributing to operational efficiency, market competitiveness, and a more substantial brand reputation. Research, Practical & Social implications: The study provides insights into critical factors of supply chain resilience and their interconnections with quality management concepts. These insights can inform strategies for enhancing resilience and quality management in supply chains. Practically, the study offers a guide for organizations to adopt a unified approach that optimizes supply chain resilience and quality management. This approach is particularly relevant for organizations seeking to improve operational efficiency and customer satisfaction through better risk management and quality assurance processes. Socially, the study highlights the importance of resilient and high-quality supply chains in today’s business landscape by maintaining Sustainable Developmental Goals. Originality/Value: This research highlights how resilience, characterized by adaptability and robust recovery in disruptive scenarios, and stringent quality management, crucial for meeting customer expectations, are fundamental in modern supply chains. The study emphasizes the importance of a risk management culture and the role of digital technologies in enhancing supply chain resilience, underscoring their vital contributions during crises like the COVID-19 pandemic. Thus, this work offers valuable insights into achieving more resilient and high-quality supply chains in today's challenging business environment through the integration of Quality Management Tools.

show abstract