Developing and Multi-Objective Optimization of a Combined Energy Absorber Structure Using Polynomial Neural Networks and Evolutionary Algorithms

Najibi, Amir; Shojaeefard, Mohammad Hassan; Yeganeh, M. S.

doi:10.1590/1679-78252797

Cited by 11 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…95 All these parameters could be studied in a future work. Najibi et al 96,97 proved that Multi-objective optimization with Pareto fronts is effective for crashworthiness analysis. Therefore, this method will be adapted in future studies to analyze the crushing of GFRP perforated tubes.…”

Section: Future Workmentioning

confidence: 99%

Multi-response optimization of crashworthy performance of perforated thin walled tubes

Alshahrani

Sebaey

Allah

et al. 2023

Journal of Composite Materials

View full text Add to dashboard Cite

It is advised to add cuts as circular holes to constructions’ walls for technical requirements such as the assembly and to reduce the weight. Since these induced cutouts have a substantial influence on crashworthiness and failure mechanisms, the size, location, and number of these cutouts should be carefully selected for energy absorption components. This research concentrates on the optimization of process parameters for the crushing performance of perforated thin-walled glass/epoxy (GFRP) square tubes. Taguchi model was adapted to formulate the design of the experiment while desirability function analysis (DFA) was used for process parameters optimization in terms of crashworthiness indicators. Test specimens were fabricated via wet warping by hand lay-up technique and tested under quasi-static axial crushing. Finally, the specimen yielding the optimum process parameter combination was compared with the intact sample. GFRP samples with circular holes exhibit optimum initial peak force ([Formula: see text]) and total absorbed energy [Formula: see text] with values of 38.35 and 4.47 % which are smaller than those of the intact samples. On contrary, the optimum specific absorbed energy [Formula: see text] and crush force efficiency ([Formula: see text]) present, respectively, 31.08 and 80.28 % greater than those of intact one. The considered process parameters were noticed to be of substantial influences on the crush behavior of perforated GFRP tubes exposed to axial compression.

show abstract

Section: Future Workmentioning

confidence: 99%

Multi-response optimization of crashworthy performance of perforated thin walled tubes

Alshahrani

Sebaey

Allah

et al. 2023

Journal of Composite Materials

View full text Add to dashboard Cite

show abstract

“…Also, the proposed hybrid network was compared with the well-known traditional machine learning methods, such as k-NN [66], RF [33], and GBM [44]. Additionally, one of the earliest deep learning methods, namely, the group method of data handling (GMDH) [67][68][69], was used for comparison. Each experiment was repeated ten times to alleviate the impact of randomization, and the mean values were reported.…”

Section: Prediction Performance Comparison Of Different Neural Networ...mentioning

confidence: 99%

Remaining Useful Life Estimation of Turbofan Engines with Deep Learning Using Change-Point Detection Based Labeling and Feature Engineering

Ensarioğlu,

İnkaya,

Emel

2023

Applied Sciences

View full text Add to dashboard Cite

Accurate remaining useful life (RUL) prediction is one of the most challenging problems in the prognostics of turbofan engines. Recently, RUL prediction methods for turbofan engines mainly involve data-driven models. Preprocessing the sensor data is essential for the performance of the prognostic models. Most studies on turbofan engines use piecewise linear (PwL) labeling, which starts with a constant initial RUL value in normal/healthy operating time. In this study, we designed a prognostic procedure that includes difference-based feature construction, change-point-detection-based PwL labeling, and a 1D-CNN-LSTM (one-dimensional–convolutional neural network–long short-term memory) hybrid neural network model for RUL prediction. The procedure was evaluated on the subset FD001 of the C-MAPSS dataset. The proposed procedure was compared with machine learning and deep learning models with and without the new difference feature. Also, the results were compared with the studies that used similar labeling approaches. Our analysis of the numerical results underscores the clear superiority of the proposed 1D-CNN-LSTM model with the difference feature in RUL prediction, with a score of 437.2 and an RMSE value of 16.1. This result illustrates the superior predictive capability of the 1D-CNN-LSTM model, which outperformed traditional machine learning methods and one of the earliest deep learning methods. These findings emphasize the superior predictive capability of the 1D-CNN-LSTM model and underline the potential of the feature engineering process for more accurate and robust RUL prediction in the context of turbofan engine prognostics.

show abstract

“…For applying the friction between the components in the simulation, the penalty friction formulations were used. The contact interactions between the bottom substrate and rigid support, and between the top substrate and punch, were modeled as the "surface-to-surface" contact was defined with the friction coefficient of 0.25 [26][27][28][29]. A "self-contact" interface was also selected to simulate the collapse of the specimens when the elements of the lattice core contacted each other.…”

Section: Numerical Simulationmentioning

confidence: 99%

Axial crushing and transverse bending responses of sandwich structures with lattice core

Taghipoor

Nouri

2018

Jnl of Sandwich Structures & Materials

View full text Add to dashboard Cite

The performance of sandwich structure with expanded metal sheets as the core was studied under axial crushing and transverse impact bending. Relationships between the force and displacement at the mid-span of the sandwich beams were obtained from the experiments. Numerical simulations were carried out using ABAQUS/EXPLICIT and the results were thoroughly compared with the experimental results. Then, the influence of the cell orientation and size of the cell were investigated. It was shown that the cell orientation was a critical parameter affecting the failure mode and energy absorption capability, leading to the increase in the peak load and specific energy absorption during the axial crushing tests. Specific energy absorption of the sandwich beams with lattice core under axial crushing ranges from 117 to 2934 J/kg, which is higher than that of beams under transverse bending. The results showed that the increase in cell angle up to ϴ = 90 increased the energy absorption by 624.4%. It was found that effects of the cell size and cell orientation on the energy absorption were dependent on each other governing the low-velocity impact response of the sandwich beams with lattice cores.

show abstract

Developing and Multi-Objective Optimization of a Combined Energy Absorber Structure Using Polynomial Neural Networks and Evolutionary Algorithms

Cited by 11 publications

References 23 publications

Multi-response optimization of crashworthy performance of perforated thin walled tubes

Multi-response optimization of crashworthy performance of perforated thin walled tubes

Remaining Useful Life Estimation of Turbofan Engines with Deep Learning Using Change-Point Detection Based Labeling and Feature Engineering

Axial crushing and transverse bending responses of sandwich structures with lattice core

Contact Info

Product

Resources

About