Elevator Software Upgrade via Predicted Idle Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional elevator systems lack awareness of idle times, leading to arbitrary software upgrades during operational modes, which can disrupt elevator functioning.
Innovation Solution
A method and system utilizing machine learning on run count performance data to predict idle times and automatically schedule software upgrades for elevators during these times, minimizing downtime and system load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If software upgrade is performed during operational mode, then software can be updated, but elevator functioning is disrupted
Solution Approach 1:
The system performs preliminary actions by predicting future idle times using machine learning on historical run count data before the actual software upgrade is needed. This allows the system to prepare and schedule upgrades in advance during predicted idle periods, ensuring no operational disruption while minimizing downtime through advance planning.
2Extent of automation
If manual software upgrade is performed, then upgrade can be executed, but user awareness and intervention are required
Solution Approach 1:
The system implements self-service by automatically performing software upgrades without user intervention. The machine learning model predicts idle times, schedules upgrades automatically, and executes them during predicted idle periods. This eliminates the need for user awareness or manual intervention while managing complexity through automated algorithms that handle the scheduling and execution processes.
3Productivity
If software upgrade is performed during idle time, then elevator operation is maintained, but idle time prediction is required
Solution Approach 1:
The system uses feedback by continuously collecting historical run count data and operational patterns, then feeding this information into the machine learning model to predict future idle times. This closed-loop approach allows the system to accurately detect and predict idle periods based on past behavior, enabling upgrades during actual idle time while maintaining operational continuity through data-driven predictions.
Data Source
AI summary
A method for automatically updating software of a computing device of a transportation device is provided herein. The method includes performing, by a server device, machine learning on run count performance data of the transportation device to determine a next idle time. The method includes publishing, by the server device, software availability information to the computing device of the transportation device with the next idle time. The method includes causing, by the server device, an automatic upgrade of the software of the computing device of the transportation device at the next idle time.