Machine learning approaches to modeling and optimization of biodiesel production systems: State of art and future outlook

Energy Conversion and Management X, Journal Year: 2024, Volume and Issue: 23, P. 100669 - 100669

Published: July 1, 2024

One of the main limitations to economic sustainability biodiesel production remains high feedstock cost. Modeling and optimization are crucial steps determine if processes (esterification transesterification) involved in economically viable. Phenomenological or mechanistic models can simulate processes. These methods have been used manage processes, but their broad use has constrained by computational complexity numerical difficulties. Therefore, it is necessary quick, effective, accurate, resilient modeling methodologies regulate such complex systems. Data-driven machine-learning (ML) techniques offer a potential replacement for conventional deal with nonlinear, unpredictable, complex, multivariate nature Artificial neural networks (ANN) adaptive neuro-fuzzy inference systems (ANFIS) most often utilized ML tools research. To effectively attain maximum yield, suitable based on nature-inspired algorithms need be integrated these obtain best possible combination various operating variables. Future research should focus utilizing approaches monitoring managing increase effectiveness promote commercial feasibility. Thus, review discusses optimizing

Language: Английский

---

Hybrid Renewable Energy Systems—A Review of Optimization Approaches and Future Challenges

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1744 - 1744

Published: Feb. 8, 2025

The growing need for sustainable energy solutions has propelled the development of Hybrid Renewable Energy Systems (HRESs), which integrate diverse renewable sources like solar, wind, biomass, geothermal, hydropower and tidal. This review paper focuses on balancing economic, environmental, social technical criteria to enhance system performance resilience. Using comprehensive methodologies, examines state-of-the-art algorithms such as Multi-Objective Particle Swarm Optimization (MOPSO) Non-Dominated Sorting Genetic Algorithm II (NSGA-II), alongside Crow Search (CSA), Grey Wolf Optimizer (GWO), Levy Flight-Salp (LF-SSA), Mixed-Integer Linear Programming (MILP) tools HOMER Pro 3.12–3.16 MATLAB 9.1–9.13, have been instrumental in optimizing HRESs. Key findings highlight role advanced, multi-energy storage technologies stabilizing HRESs addressing intermittency sources. Moreover, integration metaheuristic with machine learning enabled dynamic adaptability predictive optimization, paving way real-time management. HRES configurations cost-effectiveness, environmental sustainability, operational reliability while also emphasizing transformative potential emerging quantum computing are underscored. provides critical insights into evolving landscape offering actionable recommendations future research practical applications achieving global sustainability goals.

Language: Английский

---

A multi-objective optimization of porous sandwich functionally graded plates with graphene nanoplatelet reinforcement using Blood-Sucking leech Optimizer

Composite Structures, Journal Year: 2025, Volume and Issue: unknown, P. 118921 - 118921

Published: Feb. 1, 2025

Language: Английский

---

High performance fake review detection using pretrained DeBERTa optimized with Monarch Butterfly paradigm

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 3, 2025

Abstract In this era of internet, e-commerce has grown tremendously and the customers are increasingly relying on reviews for product information. As these influence purchasing ability future customer, it can give a positive or negative impact businesses. The effectiveness online is compromised by fake that provide false information about product. Fake not only reputation businesses but also involve financial losses. Thus, detection essential to solve problem maintaining integrity reviews. Existing Machine learning models often struggle with deep contextual understanding. Scaling machine while accuracy efficiency becomes challenging as volume continues grow. Hence, research work introduces novel MBO-DeBERTa, neural network Monarch Butterfly Optimizer. proposed model improves capacity differentiate between overlapping characteristics authentic MBO-DeBERTa attained classification 98% detecting framework tested three different datasets such Amazon, Review Deceptive Opinion Spam containing 21000,40000 1600 respectively which publicly available in Kaggle. detects adversarial attacks using Fast Gradient Sign Method (FGSM) thereby evaluating its resistance noise. was unseen data Myntra Amazon verified customer our works efficiently real world data. Thus results show suggested outperforms current showing increased accuracy, precision, recall, F1 score reduced loss rate.

Language: Английский

---

K-means and meta-heuristic algorithms for intrusion detection systems

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(8), P. 10377 - 10419

Published: May 5, 2024

Language: Английский

---

Exploring the Orca Predation Algorithm for Economic Dispatch Optimization in Power Systems

BenchCouncil Transactions on Benchmarks Standards and Evaluations, Journal Year: 2025, Volume and Issue: unknown, P. 100187 - 100187

Published: Jan. 1, 2025

Language: Английский

---

Quantitative identification of wire rope core conveyor belt damage based on GWO-BP

International Journal on Smart Sensing and Intelligent Systems, Journal Year: 2025, Volume and Issue: 18(1)

Published: Jan. 1, 2025

Abstract To address the challenges of detecting internal damage in steel wire rope core conveyors and difficulties quantitative identification, this study proposes an improved backpropagation (BP) neural network identification algorithm based on Grey Wolf Optimization (GWO-BP). The is employed to optimize initial weights thresholds BP network, thereby enhancing its performance stability. A testing apparatus for designed constructed evaluate algorithm's effectiveness feasibility. First, signal data from are extracted normalized facilitate convergence predictive model. Next, optimized issues such as parameter selection randomness, improving model training speed accuracy. Experimental results indicate that achieves average accuracy 96.0%, representing a 5.5% improvement over unoptimized significantly precision identification.

Language: Английский

---

A Bionic Social Learning Strategy Pigeon-Inspired Optimization for Multi-Unmanned Aerial Vehicle Cooperative Path Planning

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(2), P. 910 - 910

Published: Jan. 17, 2025

This paper proposes a bionic social learning strategy pigeon-inspired optimization (BSLSPIO) algorithm to tackle cooperative path planning for multiple unmanned aerial vehicles (UAVs) with detection. Firstly, modified (PIO) is proposed, which incorporates strategy. In this modification, the global best replaced by average of top-ranked solutions in map and compass operator, while center local landmark operator. The also proves algorithm’s convergence provides complexity analysis. Comparison experiments demonstrate that proposed method searches optimal solution guaranteeing fast convergence. Subsequently, path-planning model, detection units’ network cost estimation are constructed. developed BSLSPIO utilized generate feasible paths UAVs, adhering time consistency constraints. simulation results show generates at minimum effectively solves UAVs’ problem.

Language: Английский

---

Integration of Artificial Intelligence and Advanced Optimization Techniques for Continuous Gas Lift under Restricted Gas Supply: A Case Study

Digital Chemical Engineering, Journal Year: 2025, Volume and Issue: 14, P. 100220 - 100220

Published: Feb. 1, 2025

Language: Английский

---

Parameter estimation and validation of cascaded DC-DC boost converters for renewable energy systems using the IGWO optimization algorithm

Electric Power Systems Research, Journal Year: 2025, Volume and Issue: 242, P. 111462 - 111462

Published: Feb. 1, 2025

Language: Английский

---