Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word

Zhang, Chao; Yella, Jaswanth; Huang, Yu; Qian, Xiaoye; Петров, Сергей Александрович; Rzhetsky, Andrey; Bom, Sthitie

doi:10.1109/bigdata52589.2021.9671925

Cited by 16 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…New transformer models have been developed, such as the Soft Sensing Transformer Model [ 24 ], which aims to transform sensor readings into structured formats in the same way that sentences are structured in natural language, thus providing a novel method to handle sensor data in industrial settings. Although this model demonstrates the potential of machine learning techniques in interpreting and structuring sensor data, they do not consider end users and their information needs.…”

Section: Related Workmentioning

confidence: 99%

Using Large Language Models to Enhance the Reusability of Sensor Data

Berenguer,

Morejón,

Tomás

et al. 2024

Sensors

View full text Add to dashboard Cite

The Internet of Things generates vast data volumes via diverse sensors, yet its potential remains unexploited for innovative data-driven products and services. Limitations arise from sensor-dependent data handling by manufacturers and user companies, hindering third-party access and comprehension. Initiatives like the European Data Act aim to enable high-quality access to sensor-generated data by regulating accuracy, completeness, and relevance while respecting intellectual property rights. Despite data availability, interoperability challenges impede sensor data reusability. For instance, sensor data shared in HTML formats requires an intricate, time-consuming processing to attain reusable formats like JSON or XML. This study introduces a methodology aimed at converting raw sensor data extracted from web portals into structured formats, thereby enhancing data reusability. The approach utilises large language models to derive structured formats from sensor data initially presented in non-interoperable formats. The effectiveness of these language models was assessed through quantitative and qualitative evaluations in a use case involving meteorological data. In the proposed experiments, GPT-4, the best performing LLM tested, demonstrated the feasibility of this methodology, achieving a precision of 93.51% and a recall of 85.33% in converting HTML to JSON/XML, thus confirming its potential in obtaining reusable sensor data.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Large Language Models to Enhance the Reusability of Sensor Data

Berenguer,

Morejón,

Tomás

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…One task similar to ours is soft sensing classification. Soft Sensing Transformer (SST) [20] demonstrates the similarities between sensor readings and text data, and applies Transformer encoder [3] into this task. ConFormer [21] integrates the structures of both CNN and Transformer.…”

Section: Related Workmentioning

confidence: 99%

Soft Sensing Regression Model: from Sensor to Wafer Metrology Forecasting

Fan¹,

Huang²,

Fei³

et al. 2023

Preprint

View full text Add to dashboard Cite

The semiconductor industry is one of the most technology-evolving and capital-intensive market sectors. Effective inspection and metrology are necessary to improve product yield, increase product quality and reduce costs. In recent years, many semiconductor manufacturing equipments are equipped with sensors to facilitate real-time monitoring of the production process. These production-state and equipment-state sensor data provide an opportunity to practice machine-learning technologies in various domains, such as anomaly/fault detection, maintenance scheduling, quality prediction, etc. In this work, we focus on the task of soft sensing regression, which uses sensor data to predict impending inspection measurements that used to be measured in wafer inspection and metrology systems. We proposed an LSTM-based regressor and designed two loss functions for model training. Although engineers may look at our prediction errors in a subjective manner, a new piece-wise evaluation metric was proposed for assessing model accuracy in a mathematical way. The experimental results demonstrated that the proposed model can achieve accurate and early prediction of various types of inspections in complicated manufacturing processes.

show abstract

“…In the wafer manufacturing setting, advancements in state-of-the-art soft-sensing models have recently been made, but with a focus on classification, which is distinct from our soft-sensing regression problem. One such model, Soft-sensing Transformer (SST) [21], utilizes a Transformer encoder [3] to demonstrate the similarities between sensor readings and text data. Another model, ConFormer [22], leverages multi-head convolution modules to achieve fast and lightweight operations while still being able to learn robust representations through multi-head design, similar to transformers.…”

Section: Related Workmentioning

confidence: 99%

Soft-Sensing Regression Model: From Sensor to Wafer Metrology Forecasting

Fan,

Huang,

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The semiconductor industry is one of the most technology-evolving and capital-intensive market sectors. Effective inspection and metrology are necessary to improve product yield, increase product quality and reduce costs. In recent years, many types of semiconductor manufacturing equipments have been equipped with sensors to facilitate real-time monitoring of the production processes. These production-state and equipment-state sensor data provide an opportunity to practice machine-learning technologies in various domains, such as anomaly/fault detection, maintenance scheduling, quality prediction, etc. In this work, we focus on the soft-sensing regression problem in metrology systems, which uses sensor data collected during wafer processing steps to predict impending inspection measurements that used to be measured in wafer inspection and metrology systems. We proposed a regressor based on Long Short-term Memory network and devised two distinct loss functions for the purpose of the training model. Although the assessment of our prediction errors by engineers is subjective, a novel piece-wise evaluation metric was introduced to evaluate model accuracy in a mathematical way. Our experimental results showcased that the proposed model is capable of achieving both accurate and early prediction across various types of inspections in complicated manufacturing processes.

show abstract

Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word

Cited by 16 publications

References 17 publications

Using Large Language Models to Enhance the Reusability of Sensor Data

Using Large Language Models to Enhance the Reusability of Sensor Data

Soft Sensing Regression Model: from Sensor to Wafer Metrology Forecasting

Soft-Sensing Regression Model: From Sensor to Wafer Metrology Forecasting

Contact Info

Product

Resources

About