On the utilization of artificial intelligence for studying and multi-objective optimizing a compressed air energy storage integrated energy system

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 84, P. 110839 - 110839

Published: Feb. 16, 2024

Language: Английский

---

Reassessment of industrial eco-efficiency in China under the sustainable development goals: A meta two-stage parallel entropy dynamic DDF-DEA model

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 447, P. 141275 - 141275

Published: Feb. 14, 2024

Language: Английский

---

Optimizing the Neural Network Loss Function in Electrical Tomography to Increase Energy Efficiency in Industrial Reactors

Energies, Journal Year: 2024, Volume and Issue: 17(3), P. 681 - 681

Published: Jan. 31, 2024

This paper presents innovative machine-learning solutions to enhance energy efficiency in electrical tomography for industrial reactors. Addressing the key challenge of optimizing neural model’s loss function, a classifier tailored precisely recommend optimal functions based on measurement data is designed. recommends which model, equipped with given functions, should be used ensure best reconstruction quality. The novelty this study lies adjustment function specific vector, allows better reconstructions than that by traditional models trained constant function. methodology enabling development an determine model and datasets. approach eliminates randomness inherent methods, leading more accurate reliable reconstructions. In order achieve set goal, four simple LSTM network structure were first trained, each connected various functions: HMSE (half mean squared error), Huber, l1loss (L1 regression tasks—mean absolute l2loss (L2 error). training results obtained support vector machines. quality was evaluated using three image indicators: PSNR, ICC, MSE. When applied simulated cases real measurements from Netrix S.A. laboratory, demonstrated effective performance, consistently recommending produced closely resembled objects. Such can significantly optimize use EIT reactors increasing accuracy imaging, resulting improved management efficiency.

Language: Английский

---

Macroeconomic Determinants of Economic Development and Growth in Ukraine: Logistic Regression Analysis

Lecture notes on data engineering and communications technologies, Journal Year: 2023, Volume and Issue: unknown, P. 358 - 368

Published: Jan. 1, 2023

Language: Английский

---

Energy consumption forecast model of CNC machine tools based on support vector regression optimized by improved artificial hummingbird algorithm

Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering, Journal Year: 2024, Volume and Issue: 238(10), P. 1857 - 1871

Published: May 23, 2024

With the development of manufacturing industry, energy consumption is growing rapidly, which makes crisis and environmental problems become more serious. CNC machine tools play an essential role are primary devices in industry. The accurate prediction tool can provide support for production plans reduce waste. This paper proposes a novel model based on vector regression (SVR) optimized by improved artificial hummingbird algorithm (IAHA). Firstly, as (AHA) may easily get trapped local optimum, AHA chaotic mapping backtracking exploitation strategy proposed. used to initialize individual positions, good maintaining population diversity. employed improve optimization ability. effectiveness feasibility IAHA have been verified through 12 benchmark functions. Then, optimize parameters SVR, IAHA-SVR established. Finally, case study.

Language: Английский

---

The Spatial Spillover Impact and Transmission Mechanisms of Logistics Agglomeration on Eco-Efficiency: A Case Study in China

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

---

Prediction of pollutant emission characteristics in ISO50001 energy management in the Americas: Uni and multivariate machine learning approach

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 949, P. 174797 - 174797

Published: July 20, 2024

Language: Английский

---

Prediction of Pollutant Emission Characteristics in Iso50001 Energy Management in the Americas: UNI and Multivariate Machine Learning Approach

Published: Jan. 1, 2024

The American continent is experiencing significant economic and industrial development driven by sustainability principles. In this context, discussions on improving energy consumption have become increasingly frequent dynamic across various sectors of civil society, including the implementation efficiency measures as advocated ISO50001 management standard. However, there a pressing need to investigate which socioeconomic aspects are responsible for issuance certification in Americas how these factors relate characteristic emissions, especially particulate matter. This study aims evaluate influencing standard adjusted correlate with matter 2.5μm 10μm dimensions. To achieve this, machine learning techniques were employed, considering complex nature risk data overfitting. Model fitting was performed through multiple lasso regression, relationship between examined cross-correlation analysis. analyses indicate strong correlation macroeconomic indicators, PM2.5, suggesting an association cardiorespiratory problems methane-related origins. work great relevance academia it proposes new concepts regarding interaction standards For sector, provide guidance while also helping mitigate health issues. Additionally, government, results can assist formulating policies address specific related area.

Language: Английский

---

A New Fuzzy-Logic Methodology for Industrial Energy Efficiency Assessment

Published: Jan. 1, 2024

Language: Английский

---

A novel technology-explicit framework for predicting the efficiency of industrial device retrofits in stock turnover models with a case study of the pulp and paper sector

Energy Efficiency, Journal Year: 2023, Volume and Issue: 16(7)

Published: Aug. 22, 2023

Language: Английский

---