This study utilizes neural networks to detect and locate thermal anomalies in low-pressure steam turbines, some of which experienced a drop in efficiency. Standard approaches relying on expert knowledge or statistical methods struggled to identify the anomalous steam line due to difficulty in capturing nonlinear and weak relations in the presence of linear and strong ones. In this research, some inputs that linearly relate to outputs have been intentionally neglected. The remaining inputs have been used to train shallow feedforward or long short-term memory neural networks using measured data. The resulting models have been analyzed by Shapley additive explanations, which can determine the impact of individual inputs or model features on outputs. This analysis identified unexpected relations between lines that should not be connected. Subsequently, during periodic plant shutdown, a leak was discovered in the indicated line.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11014054 | PMC |
| http://dx.doi.org/10.3390/s24072056 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Improved enzymatic hydrolysis of corn stover by a low-temperature and low-pressure holding post-treatment.
J Environ Manage
December 2024
Key Laboratory of Photoelectric Conversion and Utilization of Solar Energy, Qingdao New Energy Shandong Laboratory, Shandong Energy Institute, Qingdao Institute of Bioenergy and Bioprocess Technology, Chinese Academy of Sciences, Qingdao, Shandong, 266101, China; University of Chinese Academy of Sciences, Beijing, 100080, China. Electronic address:
Lignocellulose is one of the world's most abundant and underutilized biomass resources, and its proper treatment and utilization are critical to environmental issues and sustainable development. However, lignocellulose's inherently compact and intricate structure reduces enzymatic hydrolysis's efficiency, which is still an obstacle to overcome. A new pretreatment method with relatively low-temperature and low-pressure holding (LTLPH) after the traditional extrusion, pulp refining instrument (PFI), and instant catapult steam explosion (ICSE) was proposed to obtain a better output of corn stover saccharification.
View Article and Find Full Text PDFIntegrated chemical analysis, metabolic profiling, network pharmacology, molecular docking and toxicity prediction to reveal the active ingredients and their safety of raw and prepared rhubarbs in the treatment of gastric ulcers.
Front Pharmacol
November 2024
Department of Pharmacy, Shanghai Fourth People's Hospital Affiliated to Tongji University School of Medicine, Shanghai, China.
Article Synopsis
- Rhubarb, including raw and processed forms, is commonly used for treating gastric ulcers, but the active ingredients, mechanisms, and safety are not well understood.
- A study identified 183, 120, and 115 compounds in raw, steamed, and carbonized rhubarb, respectively, and found key active constituents and therapeutic targets for gastric ulcer treatment through network pharmacology and molecular docking.
- The research revealed potential effective compounds along with their targets and signaling pathways, but also highlighted concerns about liver injury associated with some of these compounds.
Study of cracks in the last-stage rotor blade of a steam turbine and the corrosion fatigue properties of its materials.
Heliyon
September 2024
School of Marine Equipment and Mechanical Engineering, Jimei University, Xiamen, 361000, Fujian, PR China.
In this study, to clarify the failure mechanism of the last-stage rotor blade in the low-pressure cylinder of a steam turbine, the peculiarities of crack initiation and propagation on the inlet side of the last-stage rotor blade at a distance of 125-165 mm were analyzed, along with the corrosion fatigue properties of its materials. The results showed that crack initiation occurred at the tip of the pit due to a combination of factors: stress concentration at the tip of the pit, corrosion of the Cr-poor area near the prior austenite grain boundary, centrifugal tensile stress, and steam bending stress. The crack propagation could be divided into the initial intergranular and late transgranular propagation stages.
View Article and Find Full Text PDFAn Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling.
Sensors (Basel)
March 2024
Research and Testing Institute Plzen, Tylova 1581/46, 301 00 Plzen, Czech Republic.
This study utilizes neural networks to detect and locate thermal anomalies in low-pressure steam turbines, some of which experienced a drop in efficiency. Standard approaches relying on expert knowledge or statistical methods struggled to identify the anomalous steam line due to difficulty in capturing nonlinear and weak relations in the presence of linear and strong ones. In this research, some inputs that linearly relate to outputs have been intentionally neglected.
View Article and Find Full Text PDFResearch on Thermodynamic Characteristics of the Saturated Flue Gas Waste Heat Recovery to Reduce Turbine Extraction Steam.
ACS Omega
December 2023
China Energy Longyuan Environmental Protection Co., Ltd., Beijing 100039, China.
The saturated flue gas is difficult to recover and use as low-grade waste heat in a coal-fired power plant. The absorption heat pump is important equipment for recovering low-grade waste heat. In this article, the saturated flue gas waste heat is recovered to reduce the turbine extraction steam of low-pressure heaters.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!