A group of scientists from Novosibirsk State Technical University (NSTU) has created an algorithm that can analyze the operation of lifting mechanisms and identify potential malfunctions in elevators in a timely manner. The technology has already been tested and is ready for implementation.
We have developed and substantiated an algorithm that allows us to determine with high accuracy why the elevator did not turn on at each specific time interval: due to the absence of people in it or due to a malfunction. The algorithm is based on calculating the probability that no one wanted to use the elevator during this period of time. If this probability is very low, then a malfunction of the elevator is recorded.
The researchers also conducted a detailed analysis of elevator usage patterns. It turned out that in residential buildings, the peak of activity occurs in the morning hours, and in shopping centers - in the evening. Interestingly, the load on elevators varies significantly on weekdays, holidays and pre-holidays.
The methodology is based on a statistical analysis of the main drive activation protocols. In addition to identifying defects, the system allows you to rank elevators by level of reliability. The development was tested both on existing devices and on artificially generated data.
According to the Ministry of Construction, 59,000 elevators in Russia have already worked out their service life. By 2030, this figure could almost double. The new technology will not only improve the safety of lifting mechanisms, but also help to significantly reduce the cost of their maintenance.
Read more materials on the topic:
Why are new elevators falling? Dangerous flaws in the design of elevators
Almost 90% of the installed elevators in Russia were produced by domestic enterprises