Predictive control using a hybrid data-based artificial neural network model: a case study on the construction of massive concrete structures

Abstract

Traditionally, temperature control for massive concrete structures during the construction phase is based on experience instead of using advanced methods such as predictive control method. In this paper, a predictive control method with a hybrid data-based artificial neural network (ANN) model is proposed. The main parameters of the numerical model are identified based on the data measured from the site. Since the limitation of the measured data, a rich dataset is generated by the numerical model with the identified parameters. Finally, a hybrid data-based ANN model for predicting the temperature indicator of massive concrete is developed. A case study in which the temperature control of concrete in a real bridge anchorage foundation construction in Southwestern China is conducted. Results show that the maximum temperature of concrete can be controlled around the target temperature by the proposed method. The average temperature decline rate decreases from 0.19 °C/h to 0.14 °C/h in the period of 120 h (i.e., from 60 h to 180 h after the concrete pouring) at a sudden decrease of 8 °C in environmental temperature, thereby enabling a significant reduction in the risk of concrete cracking.

Keywords:

• Massive concrete
• hybrid data
• bridge anchorage foundation
• predictive control
• temperature control
• artificial neural network
• finite element method
• pipe cooling

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This research was funded by Scientific Research Project of China Power Construction Road and Bridge Group Co., Ltd. (Grant number HHZ-JGY-FW-07).