Multi‐model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes

Abstract

Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&DR). A novel SFD&DR algorithm with four types of models including outlier robust Kalman filter, locally weighted partial least squares, predictor‐based subspace identification, and approximate linear dependency‐based kernel recursive least squares is proposed. The residuals are further analyzed by artificial neural networks and a voting algorithm. The performance of the SFD&DR algorithm is illustrated by clinical data from artificial pancreas experiments with people with diabetes. The glucose‐insulin metabolism has time‐varying parameters and nonlinearities, providing a challenging system for fault detection and data reconciliation. Data from 17 clinical experiments collected over 896 h were analyzed; the results indicate that the proposed SFD&DR algorithm is capable of detecting and diagnosing sensor faults and reconciling the erroneous sensor signals with better model‐estimated values. © 2018 American Institute of Chemical Engineers AIChE J, 65: 629–639, 2019

An overview of advancements in closed-loop artificial pancreas system

“…Here, the HOMSED&FR algorithm was constructed by combining the outlier Kalman filter and a locally-weighted partial least squares regression model. Furthermore, the more complex algorithm (smart multiple-model) for detecting CGM error was developed based on four models: Kalman filter, locally-weighted partial least squares regression model, predictor-based subspace identification, and approximate linear dependency-based kernel recursive least square [ 71 ]. In addition, an artificial neural network is used as a voting algorithm to integrate these four different models into one system.…”

A review of internet of medical things (IoMT) - based remote health monitoring through wearable sensors: a case study for diabetic patients

“…The main contribution of the proposed study is to enhance the healthcare living facilities using IoMT for RHM of diabetic patients. Patients with diabetes need 24/7 monitoring [57,58] which can be achived by measuring the blood glucose (BG) level using wearable sensors [59][60][61][62].…”

A review of wearable sensors based monitoring with daily physical activity to manage type 2 diabetes

“…Importantly, diabetes patients critically need 24/7 management [55]. Monitoring the blood glucose (BG) level using wearable sensors has a vital role in diabetes treatment revolution nowadays [56][57][58]. Table 2 shows wearable sensing technologies [59][60][61].…”