An improved supervised contrastive learning with denoising diffusion probabilistic model for fault detection in industrial processes DOI
Daye Li, Jie Dong, Kaixiang Peng

и другие.

Process Safety and Environmental Protection, Год журнала: 2024, Номер 194, С. 350 - 359

Опубликована: Дек. 10, 2024

Язык: Английский

Dynamics Modeling for Key Performance Indicators in Higher Education Through Optimization Methods DOI

M. Salmina,

Said Munzir,

Intan Syahrini

и другие.

International Journal of Mathematical Engineering and Management Sciences, Год журнала: 2025, Номер 10(1), С. 92 - 112

Опубликована: Янв. 1, 2025

Dynamic models of higher education Key Performance Indicators (KPI) help in understanding how internal and external factors affect future KPI achievement. This study aims to construct a dynamic model university variables estimate parameters value. Several used steps achieve goals are problem definition, variables, formulation, prerequisite estimation, conformity analysis. involves eight KPIs three types funding. Three optimization methods Type I constrained optimization, II unconstrained optimization. The results showed that the percentage graduates getting decent jobs (KPI 1) year is strongly influenced by two KPIs, namely work lecturers 5) programs with international accreditation 8). existence active practitioners 4) opens opportunities for cooperation 6) collaborative learning 7). Significant investment improving quality right allocation funds has proven impact achieving positively.

Язык: Английский

Процитировано

0

Additive Manufacturing Modification by Artificial Intelligence, Machine Learning, and Deep Learning: A Review DOI Creative Commons
Mohsen Soori, Fooad Karimi Ghaleh Jough, Roza Dastres

и другие.

Deleted Journal, Год журнала: 2025, Номер unknown, С. 200198 - 200198

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

AI in Smart Manufacturing DOI
Josué Román Martínez-Mireles, Jazmín Rodriguez-Flores, Marco Antonio García-Márquez

и другие.

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 463 - 494

Опубликована: Март 7, 2025

This chapter provides a comprehensive overview of the integration artificial intelligence (AI) and related technologies in manufacturing sector, detonating Smart Manufacturing. It discusses pivotal role AI enhancing operational efficiency, optimizing production processes, improving product quality through data-driven decision-making, including IoT Big Data integration. All these are applied in. predictive maintenance, control, supply chain optimization, showcasing real-world case studies examples. Additionally, it addresses challenges opportunities associated with implementing interaction of. AI, IoT, Industry 4.0, data manufacturing, emphasizing importance fostering culture innovation continuous improvement. The findings underscore transformative potential driving evolution smart ultimately contributing to increased competitiveness rapidly changing global economy.

Язык: Английский

Процитировано

0

Rolling trajectory generation for autonomous forklifts based on task time constraint DOI Creative Commons
Yizhen Sun, Junyou Yang, Donghui Zhao

и другие.

Advances in Mechanical Engineering, Год журнала: 2025, Номер 17(3)

Опубликована: Март 1, 2025

As the demand for operational efficiency in intelligent factories and logistics systems continues to increase, trajectory planning autonomous forklifts has become a critical technological challenge. In this paper, we propose Task-Time Constrained Trajectory Rolling Planning (TTRP) approach that ensures timely task completion despite unforeseen circumstances. The TTRP method calculates time intervals between waypoints based on constraints forklift’s kinematic dynamic models. By employing cubic spline interpolation, it replans remaining after unplanned stops, ensuring smooth transitions adherence constraints. We validated using ROS-based Gazebo simulation environment. Simulation results indicate significantly improves smoothness stability compared traditional quintic polynomial interpolation methods. Specifically, reduces maximum jerk by up 89.7%, decreases standard deviation of acceleration 88.1%, lowers speed variation 61%. These findings demonstrate efficiently generates smooth, feasible trajectories meet kinematic, dynamic, requirements factory environments.

Язык: Английский

Процитировано

0

An improved supervised contrastive learning with denoising diffusion probabilistic model for fault detection in industrial processes DOI
Daye Li, Jie Dong, Kaixiang Peng

и другие.

Process Safety and Environmental Protection, Год журнала: 2024, Номер 194, С. 350 - 359

Опубликована: Дек. 10, 2024

Язык: Английский

Процитировано

0