| 1. |
- Feng, Kailun, 1991-, et al.
(författare)
-
Embedding ensemble learning into simulation-based optimisation : a learning-based optimisation approach for construction planning
- 2023
-
Ingår i: Engineering Construction and Architectural Management. - : Emerald Group Publishing Limited. - 0969-9988 .- 1365-232X. ; 30:1, s. 259-295
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose - Simulation-based optimisation (SO) is a popular optimisation approach for building and civil engineering construction planning. However, in the framework of SO, the simulation is continuously invoked during the optimisation trajectory, which increases the computational loads to levels unrealistic for timely construction decisions. Modification on the optimisation settings such as reducing searching ability is a popular method to address this challenge, but the quality measurement of the obtained optimal decisions, also termed as optimisation quality, is also reduced by this setting. Therefore, this study aims to develop an optimisation approach for construction planning that reduces the high computational loads of SO and provides reliable optimisation quality simultaneously.Design/methodology/approach - This study proposes the optimisation approach by modifying the SO framework through establishing an embedded connection between simulation and optimisation technologies. This approach reduces the computational loads and ensures the optimisation quality associated with the conventional SO approach by accurately learning the knowledge from construction simulations using embedded ensemble learning algorithms, which automatically provides efficient and reliable fitness evaluations for optimisation iterations.Findings - A large-scale project application shows that the proposed approach was able to reduce computational loads of SO by approximately 90%. Meanwhile, the proposed approach outperformed SO in terms of optimisation quality when the optimisation has limited searching ability.Originality/value - The core contribution of this research is to provide an innovative method that improves efficiency and ensures effectiveness, simultaneously, of the well-known SO approach in construction applications. The proposed method is an alternative approach to SO that can run on standard computing platforms and support nearly real-time construction on-site decision-making.
|
|
| 2. |
- Xiong, Fangzhu, et al.
(författare)
-
Transfer-free rapid growth of 2-inch wafer-scale patterned graphene as transparent conductive electrodes and heat spreaders for GaN LEDs
- 2023
-
Ingår i: npj 2D Materials and Applications. - 2397-7132. ; 7:1
-
Tidskriftsartikel (refereegranskat)abstract
- A technique for the transfer-free growth of 2-inch wafer-scale patterned graphene directly on GaN LED epilayers is introduced. High-quality graphene as transparent electrodes and heat spreaders is synthesized directly on GaN by PECVD at only 600 °C deposition temperature and within 3 min growth time. Co acts as both the catalyst for graphene growth and the dry etching mask for GaN mesas, which greatly improves the efficiency of the semiconductor device process. Elegantly, the graphene growth is in accordance with the shape of Co, which offers a lithography-free patterning technique of the graphene. Afterward, using our penetration etching method through the PMMA and graphene layers, the Co is peacefully removed, and in-situ Ohmic contact is achieved between the graphene and p-GaN where the contact resistivity is only 0.421 Ω cm2. The graphene sheet resistance is as low as 631.2 Ω sq−1. The device is also superior to the counterpart graphene-free LED in terms of heat spreading behavior, as evidenced by the lower junction temperature and thermal resistance. Most importantly, the developed technique produces graphene with excellent performance and is intrinsically more scalable, controllable, and semiconductor industry compatible than traditionally transferred graphene.
|
|
