A comparison of linear and neural network ARX models applied to a prediction of the indoor temperature of a building

Mechaqrane, Abdellah; Zouak, M.

doi:10.1007/s00521-004-0401-8

Cited by 87 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2. There have been studies regarding an ANN-based NARX model, but a model generation guide or performance comparison between structures had not been given [11]- [13]. In this research, the performance of various feedforward neural network (FNN) structures are compared to each other in a statistic way, and model generation steps are suggested based on the results.…”

Section: Introductionmentioning

confidence: 99%

Temperature Estimation of PMSM Using a Difference-Estimating Feedforward Neural Network

Lee

Park

2020

IEEE Access

View full text Add to dashboard Cite

Keeping the temperature of a permanent magnet synchronous machine (PMSM) in a safe range is essential for maintaining machine performance. In this paper, a feedforward neural network (FNN) for the temperature estimation of a PMSM is proposed. An FNN obtains the past temperature and operating condition values and gives the temperatures information at the next moment. Similar to a thermal-circuit-based model, the proposed model estimates the temperatures of multiple parts of interest with a heat point of view. The proposed FNN estimates the temperature differences, rather than the temperatures, and can enhance the learning and estimation performance of the FNN. Various FNN structures are compared, and the model generation steps are presented. For the experiments performed, where the temperature of the PMSM changes from 20 to 130 °C, the best FNN-based model showed closed-loop estimation errors less than 4.5 °C for the side of the permanent magnet and four parts on the winding, even in 2 hours of closed-loop estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

Temperature Estimation of PMSM Using a Difference-Estimating Feedforward Neural Network

Lee

Park

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To overcome this problem, several approaches have been employed to identify simplified building models which can be used in the MPC framework. A number of articles discuss the use of resistance-capacitance (RC) network models [8], data-driven methods such as neural network models [9], or the identification of linear state-space models based on data obtained from detailed simulation software [10]. Although these models are convenient for MPC implementation, they may be inaccurate when the operating conditions deviate from those used during the identification process.…”

Section: Introductionmentioning

confidence: 99%

Model reduction and model predictive control of energy-efficient buildings for electrical heating load shifting

Robillart

Schalbart

Chaplais

et al. 2019

Journal of Process Control

View full text Add to dashboard Cite

In France, buildings account for a significant portion of the electricity consumption (around 68 %), due to an important use of electrical heating systems. This results in high peak load in winter and causes tensions on the production-consumption balance. In view of reducing such fluctuations, advanced control systems (including the Model Predictive Control framework) have been developed to shift heating load while maintaining indoor comfort and taking advantage of the building thermal mass. In this paper, a framework for developing optimisationbased control strategies to shift the heating load in buildings is introduced. The balanced truncation method and a time-continuous optimisation method were used to develop a real-time control of the heating power. These two methods are well suited for control problems and yield precise results. The novelty of the approach is to use reduced models derived from advanced building simulation software. A simulation case study demonstrates the controller performance in the synthesis of a predictive model-based optimal energy management strategy for a single-zone test building of the "INCAS" platform built in Le Bourget-du-Lac, France, by the National Solar Energy Institute (INES).The controller exhibits excellent performance, reaching between 6 and 13 % cost reduction, and can easily be applied in real-time.

show abstract

“…Ben-Nakhi and Mahmood (2004) used ANN to investigate the feasibility of this technology to optimize HVAC thermal energy storage in public and office buildings. Indoor temperature of a residential building was predicted with auto regressive with exogenous input neural networks in a research by Mechaqrane and Zouak (2004). Aydinalp et al (2004) used an ANN method to model residential energy consumption.…”

Section: Introductionmentioning

confidence: 99%

An Insulation Thickness Optimization Methodology for School Buildings Rehabilitation Combining Artificial Neural Networks and Life Cycle Cost

Almeida

Freitas

2016

Journal of Civil Engineering and Management

View full text Add to dashboard Cite

The energy efficiency of buildings, including public buildings, is a major concern for all European governments,since they are responsible for a large share of the total energy bill of the states. School buildings play an importantrole in these costs. The best strategy for reversing this scenario includes efforts on buildings retrofit, seeking tooptimize their energy efficiency and indoor environmental quality. However, in the unfavourable economic climate weare experiencing, which requires great prudence when it comes to public investment, special attention should be givento this multi-objective optimization process. In this research, a methodology to optimize the insulation thickness of theexternal walls and roof on school buildings retrofit is proposed. The procedure includes the optimization of the buildingperformance considering the following objectives: the minimization of the annual heating load; the minimization of thediscomfort in the classrooms due to overheating; and the minimization of the life cycle cost of retrofitting external wallsand roof. This methodology was applied to two Portuguese school buildings.

show abstract

A comparison of linear and neural network ARX models applied to a prediction of the indoor temperature of a building

Cited by 87 publications

References 13 publications

Temperature Estimation of PMSM Using a Difference-Estimating Feedforward Neural Network

Temperature Estimation of PMSM Using a Difference-Estimating Feedforward Neural Network

Model reduction and model predictive control of energy-efficient buildings for electrical heating load shifting

An Insulation Thickness Optimization Methodology for School Buildings Rehabilitation Combining Artificial Neural Networks and Life Cycle Cost

Contact Info

Product

Resources

About