A fault-tolerant control strategy to estimate and compensate the temperature sensor bias in supermarket refrigeration systems

Patrick Haffmans; Roozbeh Izadi-Zamanabadi; Hossein Ramezani

doi:10.1016/j.isatra.2023.10.033

A fault-tolerant control strategy to estimate and compensate the temperature sensor bias in supermarket refrigeration systems

ISA Trans. 2024 Jan:144:490-500. doi: 10.1016/j.isatra.2023.10.033. Epub 2023 Oct 31.

Authors

Patrick Haffmans¹, Roozbeh Izadi-Zamanabadi², Hossein Ramezani³

Affiliations

¹ University of Southern Denmark, Denmark. Electronic address: pahaf19@student.sdu.dk.
² Department of Electrical Engineering, Aalborg University, Denmark; Department RAD-RC, Technology Center, Danfoss, Denmark. Electronic address: riz@es.aau.dk.
³ University of Southern Denmark, Denmark. Electronic address: ramezani@sdu.dk.

PMID: 37923629
DOI: 10.1016/j.isatra.2023.10.033

Abstract

The paper proposes a data-driven fault-tolerant control (FTC) strategy to construct and accommodate the bias on ambient temperature measurements in supermarket refrigeration systems. The bias, which is caused by direct or indirect exposure of the sensor to the sun, can have a significant impact on the refrigeration system's energy consumption. Based on analysis of the real data a comprehensive model of the bias is developed and then used to generate realistic scenarios for testing the proposed FTC method. The FTC method uses a feed forward Neural Network (NN) as a black box model. The model is trained by active injection of perturbation signals during the night operations. During the Monte-Carlo tests, the strategy was implemented in a Plug & Play manner, demonstrating that substantial energy savings can be achieved during summer periods.

Keywords: Bias; Error estimation; Fault-tolerant control; Neural networks; Supermarket refrigeration systems.