Wear-Resistant Metals and Composites

Aramide, BP; Popoola, A. P. I.; Sadiku, Emmanuel Rotimi; Aramide, Fatai Olufemi; Tamba, J.; Pityana, Sisa

doi:10.1007/978-3-030-36268-3_177

Cited by 8 publications

(7 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Erosion due to high-velocity particle impingement continues to be a topic of pressing concern due to its deleterious effects in a variety of energy and technological industries. For example, erosion results in irreversible mechanical wear of materials/components in petroleum refining, aircraft rotor/engine blades, , and pipelines in coal-fired power plants. , Recent studies have estimated that the financial loss due to erosion can reach up to several billions of US dollars in industrialized nations . To mitigate these effects, computational fluid dynamics (CFD) is commonly used to solve the Navier–Stokes equations for fluid and particle dynamics to shed insight into the specific mechanisms involved in these erosion processes.…”

Section: Introductionmentioning

confidence: 99%

FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion

Yang,

Ali,

Wong

2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The deleterious impact of erosion due to high-velocity particle impingement adversely affects a variety of engineering and industrial systems, resulting in irreversible mechanical wear of materials/components. Brute force computational fluid dynamics (CFD) calculations are commonly used to predict surface erosion by directly solving the Navier–Stokes equations for fluid and particle dynamics; however, these numerical approaches often require significant computational resources. In contrast, recent data-driven approaches using machine learning (ML) have shown immense promise for more efficient and accurate predictions to sidestep computationally demanding CFD calculations. To this end, we have developed FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer), a new hybrid ML architecture for accurately predicting particle trajectories and erosion on an industrial-scale steam header geometry. Our FLUID-GPT approach utilizes a Generative Pre-Trained Transformer 2 (GPT-2) with a convolutional neural network (CNN) for the first time to predict surface erosion using only information from five initial conditions: particle size, main-inlet speed, main-inlet pressure, subinlet speed, and subinlet pressure. Compared to the bidirectional long- and short-term memory (BiLSTM) ML techniques used in previous work, our FLUID-GPT model is much more accurate (a 54% decrease in the mean squared error) and efficient (70% less training time). Our work demonstrates that FLUID-GPT is an accurate and efficient ML approach for predicting time-series trajectories and their subsequent spatial erosion patterns in these complex dynamic systems.

show abstract

Section: Introductionmentioning

confidence: 99%

FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion

Yang,

Ali,

Wong

2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…[ 31 ] For other tribotechnical materials such as hard metals or hard composites, nonferrous alloys or polymeric materials, please refer to further literature. [ 32–38 ] Protective coatings, for example, applied through vacuum deposition or thermal spraying, lead to a reduction of wear and friction. [ 39 ] Recently research focused on multilayer coating with individual layer thicknesses in the nanometer range, showing improvements for low‐friction and high‐wear resistance.…”

Section: Introductionmentioning

confidence: 99%

Wear of Tailored Forming Steels

et al. 2023

View full text Add to dashboard Cite

This study investigates the wear behavior of additively welded cladding layers on less wear‐resistant base materials using plasma‐transferred arc welding and laser hot‐wire cladding. The cladding layers are made from atomized AISI 52100, AISI 5140, and a stainless steel with (0.52 wt% C, 0.9 wt% Si, 14 wt% Cr, 0.4 wt% Mo, 1.8 wt% Ni, 1.2 wt% V, bal. Fe) on unalloyed steel AISI 1022M as the base material. The specimens' microstructure and surface hardness are comparable with conventional specimens of monolithic AISI 52100 and AISI 4140, which is used as a reference. Tribometer tests are carried out in ball‐on‐disk configuration to investigate the wear resistance of the specimen. The multimaterial specimens show comparable wear behavior to their monolithic counterparts, and a good performance of the stainless specimen in pure sliding is proven. These findings suggest that additive manufacturing processes can be used to clad less wear‐resistant base materials and achieve high wear resistance, making it possible to exploit the advantages of surface coatings under severe wear conditions.

show abstract

“…3 Mitigating these deleterious effects is particularly crucial since the financial loss due to erosion is estimated to cost 1−4% of the gross national product in industrialized nations. 4 Since these erosion processes depend on a multitude of control variables, the in situ investigation of these processes is impractical since the number of experiments is typically immense. Computational fluid dynamics (CFD) can shed insight into these erosion processes by direct solution of the Reynolds-averaged Navier−Stokes (RANS) equations; 5 however, these numerical approaches can be computationally expensive.…”

Section: Introductionmentioning

confidence: 99%

“…This process causes perpetual wear of critical components in various energy and technological industries, such as those used in petroleum refining, helicopter rotor blades, aircraft engine blades, and pipelines in coal power plants . Mitigating these deleterious effects is particularly crucial since the financial loss due to erosion is estimated to cost 1–4% of the gross national product in industrialized nations . Since these erosion processes depend on a multitude of control variables, the in situ investigation of these processes is impractical since the number of experiments is typically immense.…”

Section: Introductionmentioning

confidence: 99%

Predicting Complex Erosion Profiles in Steam Distribution Headers with Convolutional and Recurrent Neural Networks

Yang

Ali

Kwon

et al. 2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The effects of erosion due to particle impingement continue to be of immense concern in various energy and technology industries. Brute force computational fluid dynamics (CFD) approaches allow accurate predictions of complex erosion processes; however, these large-scale calculations can be very computationally expensive. Specifically, when different initial conditions are required to analyze the system, the CFD simulations must be restarted de novo without recourse to previously converged cases. To address these issues, we harness convolutional neural network (CNN) and long-and short-term memory (LSTM) machine learning approaches to predict complex surface erosion profiles in steam distribution headers for the first time. We show that this hybrid machine learning approach can accurately predict entire particle trajectories and surface erosion profiles when only initial positions and velocities are inputted into the algorithm. Most importantly, our approach is 600 times faster than conventional CFD calculations and gives impressive R 2 scores of 0.91 and 0.71 for particle trajectories and surface erosion profiles, respectively. Taken together, our hybrid machine learning approach is a promising technique for accurately predicting surface erosion rates but with a significantly reduced computational cost.

show abstract

Wear-Resistant Metals and Composites

Cited by 8 publications

References 69 publications

FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion

FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion

Wear of Tailored Forming Steels

Predicting Complex Erosion Profiles in Steam Distribution Headers with Convolutional and Recurrent Neural Networks

Contact Info

Product

Resources

About