Modeling failure detection of elevator doors through sensor fusion

Over half of the world’s population currently lives in an urban environment. To facilitate the rapid growth of urbanization further boosted by an ever-growing world population, cities need to grow vertically as well. Although steel and concrete make it possible to build ever higher, it is elevators that make such buildings actually usable. Thus, with elevators forming the core of an ever-increasing number of buildings, their value is largely dependent on their actual performance (i.e., “availability” or “uptime”). Compensating for downtime through adding additional elevator units is not a viable solution. The extended footprint of the elevator shaft(s) reduces the available tenable floorspace, thus decreasing the economic viability of the building. Hence, downtime needs to be mitigated differently. The biggest variable of elevator design is the number of doors needed. With a ratio of ≥1 per floor, the door system is the effort and material multiplier. Door systems are also among the busiest parts of the elevator, typically cycling open and close with each ride. Subsequently, defective door systems generally account for the majority of unplanned elevator downtime. Through means of the Internet of Things (IoT) and by combining different data sources through sensor fusion –i.e. optical sensors, accelerometers, gyroscopes, temperature, humidity, and barometric pressure sensors– it is possible to monitor equipment health at each and every door on a per-floor basis, thereby making it possible to identify where issues may occur and when these need to be addressed.