Time-series signal analysis of sustainable process intensification: Characterization method development of gas-solid fluidized bed hydrodynamics towards AI-enhanced algorithms
Sustainable manufacturing is pivotal to promoting societal advancements that balance the progressive growth of human needs with the gradual exhaustion of natural resources and the environmental impact of current manufacturing technologies. Gas-solid fluidization, a key process intensification techni...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-06-01
|
| Series: | Green Energy and Resources |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949720525000153 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Sustainable manufacturing is pivotal to promoting societal advancements that balance the progressive growth of human needs with the gradual exhaustion of natural resources and the environmental impact of current manufacturing technologies. Gas-solid fluidization, a key process intensification technique, has advanced sustainability for over a century. The complex nature of these systems has led to numerous analysis algorithms for assessing time-series signals critical to observe the fluidization hydrodynamics. This work reviews widely used signal analysis methods for processing the commonly-measured time-series signals for fluidization, specifically focusing on pressure drop and optical signals. Despite their widespread implementation, these methods have limited potential due to the limited visibility of optical signals and the inability of pressure signals to provide localized fluidization system information. Veritably, the traditional algorithms cannot consider all influencing factors and handle flawed, large-scale signals.Artificial intelligence (AI) has emerged as a promising solution to overcome these limitations. Nevertheless, AI-enhanced methods for fluidization signal analysis are still nascent. This work emphasizes the potential of AI to enhance understanding of complex fluidization behavior, particularly heterogeneous agglomerations, through reviewing signal analysis methods from traditional numerical methods to AI-driven approaches. Furthermore, this study highlights the future steps necessary to adequately expand upon machine learning-based analysis methodologies and extends a call to arms for future research establishment within this field. These advancements will support the development of sustainable manufacturing technologies that balance industrial progress with environmental responsibility. |
|---|---|
| ISSN: | 2949-7205 |