Performance Comparison of Non-Aqueous Fire-Resistant Hydraulic Fluids

Rea, Susana Paola Arredondo; Barker, D. C.

doi:10.1520/stp157320130101

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is expected that artificial intelligence will have a broad development prospect in oil monitoring status recognition, but there are some challenges in obtaining a specific scale of oil monitoring data training samples with status labels. BP neural network is good at mapping high-dimensional input to low dimensional or one-dimensional output when the computer can realize the black box type conversion by mighty computing power [14], [15]. BP neural network has been proved to be capable of classification and prediction without specific model construction [16], [17].…”

Section: Introductionmentioning

confidence: 99%

Equipment Pattern Recognition of Unbalanced Fuel Consumption Data Based on Grouping Multi-BP Neural Network

2022

View full text Add to dashboard Cite

Artificial intelligence technology provides an unprecedented opportunity to assess the state of large-scale equipment with oil monitoring data. One of the key challenges in analyzing HFC (Hydraulic Fluid Composition) data is constructing a small sample classification, identifying abnormal equipment subgroups, and finding the significant impact indicators in unbalanced equipment. We propose GMBPN, a monitoring framework to identify the abnormal state and the order of influence index through multiple BP neural networks with group sampling. In order to improve the accuracy of small sample classification caused by the unbalanced number of samples, the classification model of small sample training is established by the quantitative grouping index. For the optimal classification model, the contribution order of each feature is compared by increased information gain. When GMBPN is applied to HFC data, it successfully captures the representative characteristics of abnormal equipment and impactors and shows its advantages over classical K-means and BP neural models in accuracy, classification consistency, and sampling methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Equipment Pattern Recognition of Unbalanced Fuel Consumption Data Based on Grouping Multi-BP Neural Network

2022

View full text Add to dashboard Cite

show abstract

Improved Phosphate Ester Condition Monitoring Using Membrane Patch Colorimetry

Hobbs¹,

Dufresne²

2022

Standard Guides and Practices That Support the Lubricant Condition Monitoring Industry

View full text Add to dashboard Cite

Electrohydraulic control (EHC) systems are critical steam turbine components that use a series of high-precision servo valves to control steam flow and, ultimately, turbine output. Because of the high temperatures involved, fire-resistant triarylphosphate ester-based lubricants have become the control fluid of choice in EHC systems. Despite their critical nature, many EHC condition monitoring programs fail to detect the fine semisoluble and insoluble contaminants that are responsible for costly valve-related downtime and failures. Although it was originally developed for gas turbine lube oils, the membrane patch colorimetry (MPC) standard test method (ASTM D7843) was recently shown to be suitable for use in phosphate ester applications. The chemically distinct nature of phosphate esters and lube oils, however, requires that certain parameters within the ASTM D7843 method be reevaluated (solvent, patch material, sample preparation, etc.). Chief among these is the test output: MPC ΔE. In lube oils, ΔE highlights the presence of varnish; however, ΔE detects both varnish and thermolysis products in phosphate esters. The latter typically originate from microdieseling events that are more commonplace in EHC applications. The accurate differentiation of these breakdown products is imperative so that phosphate ester users can apply appropriate corrective actions. This requires that MPC a and b measurements be reported in addition to MPC ΔE. The mass of the contaminants isolated on membrane patches has also been shown to provide an effective means of quantifying varnish and other breakdown products present in in-service EHC fluids. By using the information provided by a, b, and patch weight, MPC analysis can be exploited to its full potential, allowing for the identification of application-specific problems such as varnishing and dieseling in addition to quantifying their severity. Once these previously hidden problems have been identified, effective maintenance practices can be developed to ensure steam turbine performance and reliability.

show abstract

Performance Comparison of Non-Aqueous Fire-Resistant Hydraulic Fluids

Cited by 2 publications

References 3 publications

Equipment Pattern Recognition of Unbalanced Fuel Consumption Data Based on Grouping Multi-BP Neural Network

Equipment Pattern Recognition of Unbalanced Fuel Consumption Data Based on Grouping Multi-BP Neural Network

Improved Phosphate Ester Condition Monitoring Using Membrane Patch Colorimetry

Contact Info

Product

Resources

About