A feedforward deep neural network for predicting the state-of-charge of lithium-ion battery in electric vehicles

Decision Analytics Journal, Journal Year: 2023, Volume and Issue: 8, P. 100255 - 100255

Published: June 1, 2023

This study proposes a feedforward deep neural network to predict the parameters of lithium-ion battery in electric vehicles. Correlation analysis is used select candidate for proposed model with no categorical variable. A direct artificial developed battery's charge state and develop inverse model. The predicted state-of-charge combined four virtual functions form input variables Furthermore, are incorporated enhance predicting capability function multi-output speed, mileage, voltage, velocity, state-of-charge. superior previously literature because its multiple output capabilities. Also, makes decision-making easier when design simulation than single-output networks, which only. mean square error as metric accurate measurement. During by (with functions), accuracy was 44.43 times higher traditional Redefined were verify findings result suggests that incorporating into model's can improve vehicle parameter predictions.

Language: Английский

---

Predicting and managing risk interactions and systemic risks in infrastructure projects using machine learning

Automation in Construction, Journal Year: 2024, Volume and Issue: 168, P. 105836 - 105836

Published: Nov. 10, 2024

Language: Английский

---

An integration of intelligent approaches and economic criteria for predictive analytics of occupational accidents

Decision Analytics Journal, Journal Year: 2023, Volume and Issue: 9, P. 100357 - 100357

Published: Nov. 7, 2023

Occupational accidents are a significant concern, resulting in human suffering, economic crises, and social issues. Despite ongoing efforts to comprehend their causes predict occurrences, the use of machine learning models this domain remains limited. This study aims address gap by investigating intelligent approaches that incorporate criteria occupational accidents. Four algorithms, Random Forest (RF), Support Vector Machine (SVM), Multivariate Adaptive Regression Spline (MARS), M5 Tree Model (M5), were employed accidents, considering three criteria: basic income (BI), inflation index (II), price (PI). The focuses on identifying most suitable model for predicting frequency (FOA) determining with greatest influence. results reveal RF accurately predicts across all levels. Additionally, among criteria, II had impact findings suggest reduction FOA is unlikely coming years due increasing growth PI, coupled slight annual increase BI. Implementing appropriate countermeasures enhance workers' welfare, particularly low-income employees, crucial reducing research underscores potential preventing while highlighting critical role factors. It contributes valuable insights scholars, practitioners, policymakers develop effective strategies interventions improve workplace safety well-being.

Language: Английский

---

Optimal Design of Interior Permanent Magnet Synchronous Motor Considering Various Sources of Uncertainty

World Electric Vehicle Journal, Journal Year: 2025, Volume and Issue: 16(2), P. 79 - 79

Published: Feb. 5, 2025

The automotive industry is experiencing a period of transition from traditional internal combustion engine (ICE) vehicles to electric vehicles. Although machines have always been used in many applications, they are generally designed neglecting the sources uncertainty, even such uncertainty can lead significant deterioration motor performance. aim this paper compare results obtained multi-objective optimization an interior permanent magnet synchronous (IPMSM) using robust approach versus deterministic one. Unlike other studies literature, research simultaneously considers different as geometric parameters, properties, and operating temperature, assess variability Different designs 48 slot–8 pole simulated with finite element analysis, then outputs train artificial neural networks that employed find optimal design approaches. method incorporates innovative use network-based variance estimation (NNVE) technique efficiently calculate standard deviation objective functions. Finally, compared those optimization. Due small margin improvement robustness, both methods similar results.

Language: Английский

---

Machine learning and optimization strategies for infrastructure projects risk management

Construction Management and Economics, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 26

Published: April 20, 2025

Language: Английский

---

Data-Driven Assessment of Complexity-Induced Risks in Infrastructure Projects

Journal of Construction Engineering and Management, Journal Year: 2025, Volume and Issue: 151(7)

Published: April 23, 2025

Language: Английский

---

Harnessing the Power of Artificial Intelligence to Forecast Startup Success: An Empirical Evaluation of the SECURE AI Model

Published: Aug. 29, 2023

This pioneering study employs machine learning to predict startup success, addressing the long-standing challenge of deciphering entrepreneurial outcomes amidst uncertainty. Integrating multidimensional SECURE framework for holistic opportunity evaluation with AI's pattern recognition prowess, research puts forth a novel analytics-enabled approach illuminate success determinants. Rigorously constructed predictive models demonstrate remarkable accuracy in forecasting likelihood, validated through comprehensive statistical analysis. The findings reveal AI’s immense potential bringing evidence-based objectivity complex process assessment. On theoretical front, enriches entrepreneurship literature by bridging knowledge gap at intersection structured tools and data science. practical it empowers entrepreneurs an analytical compass decision-making helps investors make prudent funding choices. also informs policymakers optimize conditions entrepreneurship. Overall, lays foundation new frontier AI-enabled, data-driven practice. However, acknowledging limitations, synthesis underscores persistent relevance human creativity alongside data-backed insights. With high performance multifaceted implications, SECURE-AI model represents significant stride toward analytics-empowered paradigm management.

Language: Английский

---

A novel adjusted learning algorithm for online portfolio selection using peak price tracking approach

Decision Analytics Journal, Journal Year: 2023, Volume and Issue: 7, P. 100256 - 100256

Published: June 1, 2023

Online Portfolio Selection (OLPS) has attracted extensive interest in recent years. Accurate prediction of future prices and determining the optimal portfolio selection strategy based on estimated return is a challenging topic machine learning. We propose novel adjusted learning algorithm peak price tracking for OLPS to tackle this challenge. The an aggressive with residual information transaction costs. first online using Peak Price Tracking Approach (PPTA) improve accuracy by introducing λ adjust impact term predicted price. then build Net Profit Maximization (NPM) model Finally, we integrate PPTA NPM algorithms into new called PPTA-NPM maximize cumulative return. Extensive benchmark data experiment results statistical analysis show that significantly improves predicting price, integrated superior multiple classic algorithms.

Language: Английский

---

Estimation of ultimate bearing capacity of circular footing resting on recycled construction and demolition waste overlaying on loose sand

Journal of Building Pathology and Rehabilitation, Journal Year: 2024, Volume and Issue: 9(1)

Published: Jan. 10, 2024

Language: Английский

---

Prediction of the Nominal Side Resistance of Drilled Shafts in Dominantly Cohesive Soils using ANN

Transportation Research Record Journal of the Transportation Research Board, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 29, 2024

The conventional methods used in the design of drilled shafts might not fully consider multiple sources uncertainty soil such as geometric and mechanical variability and/or construction methods. These uncertainties can introduce nonlinearity to analysis, leading underestimation or overestimation resistance, which be translated into expensive even unsafe projects. Because this, machine learning techniques artificial neural networks (ANNs), proven effective solving nonlinear problems, are becoming popular civil engineering problems. Therefore, objective this preliminary study is evaluate a concept for predicting nominal side resistance with improved accuracy, using ANN. In study, 45 load tests were collected from extended version Nevada Deep Foundation Load Test Database divided 85% training 15% testing. Then 1,638 ANN models trained determine optimum model root-mean-squared error 2,058 kips an R-squared ( R 2 ) on unseen tests. was then benchmarked against AASHTO predicted average overall improvement prediction accuracy 23%. This paper demonstrates that could developed, improved, industry at early stage limited data supplemental tools help optimize designs regard safety, time, cost.

Language: Английский

---