Hybrid Optimisation Studies on the Microstructural Properties and Wear Resistance of Maraging Steel 1.2709 Parts Produced by Laser Powder Bed Fusion

Maodzeka, Divine Kudakwashe; Olakanmi, Eyitayo Olatunde; Mosalagae, Mosalagae; Hagedorn-Hansen, Devon; Pityana, Sisa

doi:10.2139/ssrn.4192936

Cited by 2 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The regression plot of the chosen model in Figure 10 consists of an R-value of (0.95068) for training, (0.99603) for validation, (0.96855) for testing, and an overall R-value of (0.96318) for the recommended model to give the ideal match throughout all the data sets. Trainlm training functions update weight and bias values based on the Levernberg-Marquartdt, expressed as [18], [19].…”

Section: Figure 7: Model Training Validation and Testing Mse Performa...mentioning

confidence: 99%

Comparison of RSM, ANN, and ANFIS in predicting the weld strength of Laser transmission welds of oak wood powder-reinforced polypropylene absorbent part.

Kapuyanyika,

Ude,

Chinnasamy

2024

Preprint

View full text Add to dashboard Cite

This study examines the feasibility of Laser transmission welding(LTW) of a 100% homo-polypropylene transparent part joined to an absorbent part composed of 15% wt white oak wood fiber reinforced homo-polypropylene doped with 0.2% carbon black in lap-joint configuration. Focus is given to investigating the influence of process parameters, namely laser power, welding speed, stand-off distance, and clamp pressure on the laser welded joints of polypropylene joined to plant-based polypropylene composite and the feasibility of weld strength prediction using Response Surface Method (RSM), Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS). Results showed that stand-off distance was the most crucial factor affecting weld strength, followed by welding speed. Laser power and clamp pressure had insignificant effects on weld strength in the design space studied in this paper. The coefficient of determination (R2) was (0.90), (0.93), and (0.99) for the RSM model, the ANN model, and the ANFIS model, respectively. All the prediction models exhibited acceptable mean absolute error percentages and root-mean-square errors. The results suggested a satisfactory performance in predicting weld strength for the specified materials in this study's specified parameter design space. The ANFIS model showed the best predictions, followed by the ANN and RSM models.

show abstract

Section: Figure 7: Model Training Validation and Testing Mse Performa...mentioning

confidence: 99%

Comparison of RSM, ANN, and ANFIS in predicting the weld strength of Laser transmission welds of oak wood powder-reinforced polypropylene absorbent part.

Kapuyanyika,

Ude,

Chinnasamy

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Figure 10: model training, validation, and testing MSE performance (a), Regression plot of the ANN model (b).The hidden layer had the tan-sigmoid transfer function while the output layer consisted of the linear transfer function. The regression plot of the chosen model is shown in Figure(10) which consists of an R-value of (0.95068) training, (0.99603) validation, (0.96855) testing, and an overall R-value of (0.96318) for the recommended model to give the ideal match throughout all the data set.Trainlm training function updates weight and biases values based on the Levernberg-Marquartdt which is expressed as[18],[19] …”

mentioning

confidence: 99%

Prediction of weld strength of LTW of Natural plant-based fiber reinforced Polypropylene using RSM, ANN, and ANFIS - a comparative study

Kapuyanyika,

Ude,

Chinnasamy

2024

Preprint

View full text Add to dashboard Cite

During Laser Transmission welding (LTW) of thermoplastics reinforced with natural fibers, the constituents of the composite materials affect the properties of the material which relates to the appropriate design of operating parameters for attaining good-quality welds. Material composition affects the amount of laser energy absorbed, thermal properties, and optical properties. All these attributes greatly influence the properties and quality of weld joints formed from the LTW process. Given the wide range of LTW operating parameters that are feasible for joining thermoplastics, it is important to understand the effect of each parameter on important weld attributes such as weld strength and weld width track in a specific parameter design space for a given composite material and be able to predict vital weld properties such as weld strength. In this research paper, the comparison of the predicted weld strength of the LTW of Pure Polypropylene as the transparent part joined to Polypropylene doped with 0.2wt% of carbon black and reinforced with 15wt% oak wood short fibers using an empirical model based on Response Surface Method (RSM) central composite design, Artificial Neural Network (ANN) model and Adaptive Neuro-Fuzzy Inference System (ANFIS) model was done. The coefficient of determination (R2) was (0.90), (0.93), and (0.99) for the RSM model, ANN model, and the ANFIS model respectively. All the prediction models exhibited acceptable mean absolute error percentage and root-mean-square error. The results suggested a good performance in predicting weld strength for the specified materials in the specified parameter design space in this study. ANFIS model was found to give the best performance followed by the ANN model and lastly the RSM model.

show abstract

Hybrid Optimisation Studies on the Microstructural Properties and Wear Resistance of Maraging Steel 1.2709 Parts Produced by Laser Powder Bed Fusion

Cited by 2 publications

References 23 publications

Comparison of RSM, ANN, and ANFIS in predicting the weld strength of Laser transmission welds of oak wood powder-reinforced polypropylene absorbent part.

Comparison of RSM, ANN, and ANFIS in predicting the weld strength of Laser transmission welds of oak wood powder-reinforced polypropylene absorbent part.

Prediction of weld strength of LTW of Natural plant-based fiber reinforced Polypropylene using RSM, ANN, and ANFIS - a comparative study

Contact Info

Product

Resources

About