A fully autonomous kernel-based online learning neural network model and its application to building cooling load prediction

Abstract

Building cooling load prediction is critical to the success of energy-saving measures.While many of the computational models currently available in the industry have been developed for this purpose, most require extensive computer resources and involve lengthy computational processes. Artificial neural networks (ANNs) have recently been adopted for prediction, and pioneering works have confirmed the feasibility of this approach. However, users are required to predetermine an ANN model's parameters.This hinders the applicability of the ANN approach in actual engineering problems, as most engineers may be unfamiliar with soft computing. This paper proposes a fully autonomous kernel-based neural network (AKNN) model for noisy data regression prediction. No part of the model's mechanism requires human intervention; rather, it self-organises its structure according to the training samples presented. Unlike the other existing autonomous models, the AKNN model is an online learning model. It is particularly suitable for online steps-ahead prediction. In this paper, we benchmark the AKNN model's performance according to other ANN models. It is also successfully E.W.M. Lee () • I.

Analysis of Workflow Variability and Its Impacts on Productivity and Performance in Construction of Multistory Buildings

“…The application of a mixed methodology, in which both mathematical and simulation modeling are conducted, provides a robust research approach in the field of construction engineering and management (AbouRizk and Hague 2009, Lee, Fung et al 2013). Simulation has been used as a decision support tool in the construction engineering literature (Back andBell 1995, Min andBjornsson 2008).…”

Autonomous production tracking for augmenting output in off-site construction

“…Due to the ubiquitous presence of variability in both construction processes and market demand, actual production (Ap) in OSP always fluctuates. Hence, it is necessary to smooth past data to adjust capacity parameters so that they are not excessively sensitive to noise [56,57]. Exponential smoothing can be used to provide an updated estimate of production parameters using real-time data.…”

Optimization of process integration and multi-skilled resource utilization in off-site construction

“…11 shows a snapshot of the SIMAN coding window for this purpose. Interested readers can refer to [39] and [40] for further details about simulation in the SIMAN environment. In order to impose different levels of capacity imbalance, different system designs with 1, 2 and 4 bottlenecks were investigated.…”