Predictive modeling for corrective maintenance of imaging devices from machine logs

Abstract

In the cost sensitive healthcare industry, an unplanned downtime of diagnostic and therapy imaging devices can be a burden on the financials of both the hospitals as well as the original equipment manufacturers (OEMs). In the current era of connectivity, it is easier to get these devices connected to a standard monitoring station. Once the system is connected, OEMs can monitor the health of these devices remotely and take corrective actions by providing preventive maintenance thereby avoiding major unplanned downtime. In this article, we present an overall methodology of predicting failure of these devices well before customer experiences it. We use data-driven approach based on machine learning to predict failures in turn resulting in reduced machine downtime, improved customer satisfaction and cost savings for the OEMs. One of the use-case of predicting component failure of PHILIPS iXR system is explained in this article.

Decision support for multi-component systems: visualizing interdependencies for predictive maintenance

“…On the other hand, the stacked-area approach seems to be the more offensive approach, which could be helpful in more sensitive settings [43]. Usually, offensive approaches are appropriate in sensitive settings, where breakdown should be prevented due to safety or economic costs.…”

An integrated deep learning-based approach for automobile maintenance prediction with GIS data

“…In order to reduce the machine downtime, a data-driven approach was proposed to predict failures of healthcare machine. In this study, raw system log information including time, id and description were extracted and then used to establish an SVM model for failure classification [23]. In order to address the data imbalance issue in log data, Dangut et al (2021) [24] proposed a hybrid approach based on natural language processing techniques and ensemble learning to predict the aircraft component failure.…”

Predictive Maintenance with Sensor Data Analytics on a Raspberry Pi-Based Experimental Platform

“…Patil et al [21] predicted device failures by presenting the log information of a device using a data-driven approach based on machine learning. It reduced machines breakdown, improved customer satisfaction, and also reduced the cost for the original equipment manufacturers.…”