Neural network-based surrogate modeling and optimization of a multigeneration system

Applied Energy, Journal Year: 2024, Volume and Issue: 364, P. 123130 - 123130

Published: April 5, 2024

Multi-Objective Optimization (MOO) poses a computational challenge, particularly when applied to physics-based models. As result, only up three objectives are typically involved in simulation-based optimization. To go beyond this number, Surrogate Models (SMs) need replace such high-fidelity In exploratory study, the perform comprehensive regression surrogate modeling and conduct MOO for Multi-Generation System (MGS). The most suitable SM was chosen among four neural-network models: Artificial Neural Network (ANN), Convolutional (CNN), Long-Short Term Memory (LSTM), an ensemble model developed through brute-force search using aforementioned final found be superior others, achieving R2 values ranging from 0.9830 0.9999. Next, optimization problem with six conflicting defined performed at distinct of Direct Normal Irradiation (DNI), time-dependent feature. This aimed provide multi-criteria decision-making information based on atmospheric transparency. new understandings were gained: (I) exergy efficiency, production cost, freshwater rate highly influenced by DNI, (II) critical range operation observed within DNI interval 100 400 W/m2. Furthermore, we compared result six-objective that bi-objective obtained our study all showed improvements 1.9% 12.7%. Finally, findings present some practical recommendations put forward applying proposed methodology similar MGSs.

Language: Английский

---

Biomass: A Versatile Resource for Biofuel, Industrial, and Environmental Solution

International Journal on Advanced Science Engineering and Information Technology, Journal Year: 2024, Volume and Issue: 14(1), P. 268 - 286

Published: Feb. 24, 2024

Biomass, noted for its adaptability, has various applications in biofuel generation, industrial use, and environmental cleaning. This study looks into the multiple roles of biomass as a renewable energy source, with particular emphasis on vital contribution to production. Through thorough evaluation different conversion routes—thermal, biological, physical—the emphasizes thermochemical processes' efficiency, cost-effectiveness, adaptability. Notably, technologies like gasification quick pyrolysis are thoroughly investigated, followed by in-depth discussions reactor optimization strategies enhance performance output. The complex structure biomass, which is dominated high-molecular-weight polysaccharides such cellulose hemicelluloses, demonstrates significant potential generation. Furthermore, categorizes content, origin, processes, resulting comprehensive inventory available resources. Biomass from agriculture forestry industries, starch, sugar, lignocellulose, organic wastes, rigorously analyzed processing techniques, including thermochemical, biochemical, physicochemical conversions, carefully tested real-world ensure their efficacy viability. Beyond importance production, article underlines biomass' versatility satisfying needs contributing cleanup initiatives. lays groundwork informed decision-making innovative solutions industries providing understanding biomass's benefits applications, provision, ecological restoration.

Language: Английский

---

A novel computational paradigm for scheduling of hybrid energy networks considering renewable uncertainty limitations

Energy Reports, Journal Year: 2024, Volume and Issue: 11, P. 1959 - 1978

Published: Jan. 31, 2024

Numerous developing countries are currently grappling with energy crises due to the current surge in global fossil fuels prices. This situation has prompted policymakers and cities administrator urgently seek alternative power sources. Scientists worldwide actively working on innovative computational methods address coordination challenges faced by hybrid systems. Their objective is optimize utilization of environmentally friendly sources, such as clean sources (CESs) like wind solar power, within framework traditional hydro-thermal coordination. research aims examine how integrating CESs into conventional delivering model can minimize significant costs associated production. The proposed approach involves constructing a probabilistic represent problem. To handle uncertainties related CESs, technique known point estimation employed. employs Weibull Beta distribution functions uncertain input variables power. present study an optimization paradigm that integrates black widow (BWO) algorithm radial basis function neural network (RBFNN). not only considers system but also adapts its parameters attain optimum balance among exploration well exploitation phase. Within context advancing transition outcomes our simulations demonstrate achievement. incorporation problem yields substantial 10 percent reduction operational impressive 64 decline emissions. convergence curves scheme reveal presented computing quickly converges optimal solution, attaining best solution. Three case studies have been conducted, Case Study-I, attained cost emissions $3.6e4/day 2.8e4 lb/day, respectively, photovoltaic at $1148/day $3055/day, respectively. For Study-II, complex function, 15887.42 lb/day production $26072.89/day achieved. Study-III, $26558/day 12932 acquired using approach. valuable contribution holds particular significance for economic empowerment nations. By diminishing their reliance imported generation, it paves way enhanced self-sufficiency. Moreover, findings provide well-defined pathway towards fostering sustainable urban settings. Additionally, highlights from fuel-dependent industries establishment economies.

Language: Английский

---

Physicochemical characterization of briquette fuel produced from cocoa pod husk case of Cameroon

Energy Reports, Journal Year: 2024, Volume and Issue: 11, P. 1580 - 1589

Published: Jan. 21, 2024

This paper aims to prepare and evaluate the physicochemical energetic properties of briquette fuel made from cocoa pod husk. For preparation, husk was dried, carbonised, crushed, mixed using binder, compacted, finally briquettes obtained were dried. The produced characterised by proximate analysis, ultimate infrared spectroscopy, thermogravimetric analysis American Society for Testing Materials (ASTM) European Committee Standardisation (CEN) standards. results proximal (10.5%), (6.5%), (34.7%), (58.8%), respectively, moisture content, ash volatile matter, fixed carbon, are satisfactory values. found 53.2%, 5.2%, 34.4%, hydrogen, oxygen while H/C O/C gave 1.17 0.48, respectively. Higher Heating Value (17.941 MJ/kg) proved high thermal stability, with highest mass loss 32.50% at 361°C due extractive content aromatic structure polymer. presence C-O, CC, CHx, OH groups noticed, value index (FVI) impact resistance (IRI) showed 1104% 125%, These indicated that abundance these residues in landfills could serve as an alternative energy source environmental friendly features contribute economic growth country.

Language: Английский

---

Exploring the Potential of Distillery Vinasses through Upcycling: Pathways to a Circular Economy

Environmental Technology & Innovation, Journal Year: 2025, Volume and Issue: unknown, P. 104072 - 104072

Published: Feb. 1, 2025

Language: Английский

---

Precise prognostics of biochar yield from various biomass sources by Bayesian approach with supervised machine learning and ensemble methods

International Journal of Green Energy, Journal Year: 2023, Volume and Issue: 21(9), P. 2180 - 2204

Published: Dec. 29, 2023

Biomass pyrolysis is a sustainable process for generating biochar from agricultural waste, though it generally energy-intensive and time-consuming. To address this issue, the researchers gathered data published literature on various biomass types employed ensemble methods (LSBoost) supervised machine learning (Gaussian regression) to construct predictive models. The results reveal that both models can predict well, with excellent correlations between expected actual values. In comparison LSBoost model (0.9783 training 0.9879 testing), Gaussian regression (GPR) had higher R values (0.9883) testing (0.9969). Likewise, R2 during (0.9767) (0.9938) were greater in case of GPR than (0.9571 training). Nash-Sutcliffe efficiency (NSE) revealed captured precisely. However, outperformed as well test stages, providing (0.9766 0.9933 testing) outperforms others due superior correlation, improved variability capture, lower errors. These findings offer useful insights utilization provide valuable optimizing operations.

Language: Английский

---

Aspen Plus® Process Simulation Model of the Biomass Ash-Based Treatment of Anaerobic Digestate for Production of Fertilizer and Upgradation of Biogas

Energies, Journal Year: 2023, Volume and Issue: 16(7), P. 3039 - 3039

Published: March 27, 2023

The use of the commercial simulator Aspen Plus® could bring an amelioration in accuracy predictions chemical species composition output streams anaerobic digestion process. Compared to traditionally employed lumped models, which are elaborated from scratch, models implemented have access a broad library thermodynamic and phenomena transport properties. In present investigation, process simulation model for has been prepared by including stoichiometric-equilibria reactor calculate extent ionization molecules digestate. characterizes technical feasibility digestate stabilization, means biomass ash-based treatment, production organic fertilizer potential biogas upgradation with synthesis ammonium carbonate. First all, titration manure hydrochloric acid showed that dose 3.18 mEq/g would be required attain targeted pH zero-point charge, upon addition sewage sludge ash ratio 0.6 ± 0.2%. Secondly, profiles ammonia, carbon dioxide, methane found agree treated enable upgrading NH4HCO3. needs further developed ensure standards attained all stabilized digestate, biomethane, isolated added-value fertilizers.

Language: Английский

---

Characteristics of industrialized hydrothermal cracking solid organic fertilizer and its effects on fresh corn growth

Waste Management, Journal Year: 2024, Volume and Issue: 177, P. 243 - 251

Published: Feb. 13, 2024

Traditional methods of producing organic fertilizers result in significant nutrient loss and greenhouse gas emissions, making it challenging to align with sustainable development the achievement net-zero emissions goals. Hydrothermal cracking, as a novel clean technology for utilization waste into fertilizer, has been extensively studied refined laboratory settings, but its large-scale industrial evaluation remains limited. This study investigates properties field application hydrothermal cracking solid fertilizer (HCSOF) produced at pilot scale an annual output 10,000 tons. The results indicate that matter content total (TN + P2O5 K2O) HCSOF reached 50.6 % 5.46 %, respectively, which are 20.6 1.46 higher than standards China. Additionally, contaminants such pathogens antibiotics product were completely eliminated. Elemental analysis pore size distribution highlighted unique adsorptive attributes HCSOF, showed effect reducing soil ammonium nitrogen. Results from trials complete substitution chemical did not reduce corn yield, remained 9.03 t/ha. Particularly, compared exclusive use fertilizers, treatments resulted 7.03 4.70 decrease fresh lodging disease incidence, respectively. Antibacterial tests further confirmed ability counter pathogens. provides robust evidence scaling up production levels. Future research should focus on multi-batch sampling extended experiments.

Language: Английский

---

Optimizing the Model-prediction of Date Palm Fronds-Derived Producer Gas and Third Generation Biodiesel Powered Dual-fuel engine by Employing Bayesian-Optimized Boosted Regression Trees for Enhanced Prognostics

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 187, P. 1338 - 1353

Published: May 13, 2024

Language: Английский

---

Positional error compensation for aviation drilling robot based on Bayesian linear regression

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 127, P. 107263 - 107263

Published: Oct. 14, 2023

Language: Английский

---