Artificial neural network infused quasi oppositional learning partial reinforcement algorithm for structural design optimization of vehicle suspension components

Materials Testing, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 30, 2024

Abstract This paper introduces and investigates an enhanced Partial Reinforcement Optimization Algorithm (E-PROA), a novel evolutionary algorithm inspired by partial reinforcement theory to efficiently solve complex engineering optimization problems. The proposed combines the (PROA) with quasi-oppositional learning approach improve performance of pure PROA. E-PROA was applied five distinct design components: speed reducer design, step-cone pulley weight optimization, economic cantilever beams, coupling bolted rim vehicle suspension arm An artificial neural network as metamodeling is used obtain equations for shape optimization. Comparative analyses other benchmark algorithms, such ship rescue algorithm, mountain gazelle optimizer, cheetah demonstrated superior in terms convergence rate, solution quality, computational efficiency. results indicate that holds excellent promise technique addressing

Language: Английский

---

Experimental and numerical investigation of crash performances of additively manufactured novel multi-cell crash box made with CF15PET, PLA, and ABS

Materials Testing, Journal Year: 2024, Volume and Issue: 66(9), P. 1510 - 1518

Published: Aug. 13, 2024

Abstract In this study, a novel multi-cell crash box was designed and produced using 15 % short carbon fiber reinforced polyethylene terephthalate (CF15PET), polylactic acid (PLA), acrylonitrile butadiene styrene (ABS) filaments one of the additive manufacturing methods, melt deposition method (FDM). All structures’ maximum force energy absorption performances have been investigated. As result test, it determined that box, which best meets high folding properties, expected features in boxes, has parts manufactured ABS CF15PET materials. According to test result, found is 11 higher than approximately 4.5 PLA. It response value 5 12 materials can be used boxes form an idea about design by designing analyzing finite element programs.

Language: Английский

---

The application of project management methodology in the training of college students' innovation and entrepreneurship ability under sustainable education

Systems and Soft Computing, Journal Year: 2024, Volume and Issue: 6, P. 200073 - 200073

Published: Jan. 25, 2024

With the rapid development of society and rise knowledge economy, cultivating innovation entrepreneurship abilities college students has gradually become an important task higher education. However, in current educational environment, cultivation among faces a series issues, such as disconnect between practice, singularity training methods. To address these analysis existing education was conducted using project management method. A combination model for constructed Analytic Hierarchy Process (AHP) entropy Considering that talent belongs to complex nonlinear solving problem, advanced ABC-BP adopted handle linear data problem model. Among them, Back Propagation (BP) used train refine parameters model, explore optimal factors. BP is prone local convergence parameterization problems, Artificial Bee Colony (ABC) algorithm optimized improved effect enhanced application abilities. In test compared with classic Particle Swarm Optimization (PSO) proposed had lower overall RMSE, greater optimization precision faster speed terms results. Compared PSO increased by 14%. The selected solve According solution results, highest comprehensive score scheme 1 0.57, finally best training. This study reference significance innovative entrepreneurial talents China. Through AHP methods, effectiveness can be improved, more cultivated meet needs rapidly developing economy.

Language: Английский

---

A spherical evolution algorithm with two-stage search for global optimization and real-world problems

Information Sciences, Journal Year: 2024, Volume and Issue: 665, P. 120424 - 120424

Published: March 6, 2024

Language: Английский

---

Marathon runner algorithm: theory and application in mathematical, mechanical and structural optimization problems

Materials Testing, Journal Year: 2024, Volume and Issue: 66(8), P. 1267 - 1291

Published: May 22, 2024

Abstract This study proposes a novel human-inspired metaheuristic search algorithm called marathon runner algorithm. method mimics competitive behaviors observed in real runners through mathematical modeling. Unlike classical elitist algorithms that prioritize position of the best agent, introduces concept vision point. point considers quality entire population, not just leader. By guiding population towards point, risk getting trapped local optima is reduced. A two-part evaluation was conducted to thoroughly assess capabilities First, it tested against set unconstrained benchmark functions and algorithm’s quantitative attributes, such as complexity, accuracy, stability, diversity, sensitivity, convergence rate are analyzed. Subsequently, applied mechanical structural optimization problems with both continuous discrete variables. application demonstrated effectiveness solving practical engineering challenges constraints. The outcomes compared those obtained by six other well-established techniques. results indicate yields promising solutions for mathematical, mechanical, problems.

Language: Английский

---

Expected lifetime prediction for time- and space-dependent structural systems based on active learning surrogate model

Computer Methods in Applied Mechanics and Engineering, Journal Year: 2024, Volume and Issue: 429, P. 117150 - 117150

Published: June 19, 2024

Language: Английский

---

A force neural network framework for structural optimization

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 143, P. 109991 - 109991

Published: Jan. 11, 2025

Language: Английский

---

A Gaussian mixture distribution-based adaptive sampling method for physics-informed neural networks

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 135, P. 108770 - 108770

Published: June 18, 2024

Language: Английский

---

Enhancing the performance of a additive manufactured battery holder using a coupled artificial neural network with a hybrid flood algorithm and water wave algorithm

Materials Testing, Journal Year: 2024, Volume and Issue: 66(10), P. 1557 - 1563

Published: Aug. 8, 2024

Abstract This research is the first attempt in literature to combine design for additive manufacturing and hybrid flood algorithms optimal of battery holders an electric vehicle. article uses a recent metaheuristic explore optimization holder A polylactic acid (PLA) material preferred during manufacturing. Specifically, both algorithm (FLA-SA) water wave optimizer (WWO) are utilized generate holder. The hybridized with simulated annealing algorithm. An artificial neural network employed acquire meta-model, enhancing efficiency. results underscore robustness achieving designs car components, suggesting its potential applicability various product development processes.

Language: Английский

---

Deep Learning Perspective on the Construction of SPOC Teaching Model of Music and Dance in Colleges and Universities

Systems and Soft Computing, Journal Year: 2024, Volume and Issue: 6, P. 200137 - 200137

Published: Aug. 23, 2024

Language: Английский

---