info@paripoorna.in    |    +91 44 43626468 / 78 /  88    

Making elevator maintenance service intelligent

Making elevator maintenance service intelligent with Internet of Things

Introduction

By attaching sensors that gather data about the elevator’s usage and passing this information on to cloud, which can then be processed and make accurate predictions as to when maintenance will be required.

Customer Challenges

  • Currently no infrastructure is available to tap the data to make elevator technicians more effective and efficient
  • Balancing routine maintenance along with calls for elevator service was becoming a challenge
  • Remote monitoring and knowledge based systems was required to proactively schedule the maintenance of the elevators

Disrupting the industry's maintenance model

With our real-time cloud based solution, we moved from the primitive model of Corrective Maintenance and Preventive Maintenance to the now Predictive Maintenance.

Our Service model

  • With the remote data monitoring, smart identification and root cause analysis is made possible and thereby providing a precise diagnosis
  • By applying analytics on the data collected over the edge of the network using Azure IoT Edge, the effective analysis of the repair/ maintenance issue is proactively detected and the details are passed on to the technician
  • By continuous monitoring of the device data, the components spare parts can be replaced prior to any failure
  • Vast amounts of data from elevator sensors is monitored, analyzed and displayed in real-time, improving equipment performance, reliability and safety.

Key Technologies

  • Microsoft Azure IOT Hub
  • Azure Service Bus
  • Azure Service Fabric
  • Azure SQL Database
  • Azure Stream Analytics
  • Notification Hub
  • NodeJS
  • MQTT
  • JSON

IOT Hardware

Processor: 

  • AM335x 1GHz ARMCortex-A8
  • SGX530 graphics accelerator
  • NEON floating-point accelerator
  • 2x PRU 32-bit 200MHz microcontrollers

Connectivity: 

  • WiLink 8 WL1835MOD 802.1b/g/n 2.4 GHz WiFi / XBee(Zigbee), Bluetooth and Bluetooth Smart Module
  • USB client: power, debug and device
  • USB host
  • Micro HDMI output
  • Industrial grade InfraRed Sensors based on Range

Memory:

  • 512MB DDR3 800MHz RAM
  • 4GB Embedded eMMC Flash with Debian Distribution
  • MicroSD Card Slot
  • 1.2 Ghz ARM Cortex Processor

Software:

  • Ubuntu Mate & NodeJs

Our Solution

elevator technical diagram

Continuously feed data from devices to the cloud

The data will be securely transferred from the device to a mobile & web app via WIFI. The app will securely transfer the data to IoT Hub through Telemetry. Since the distance is measured using the Industrial grade Infra red sensors, it ensures a very high precision in the measured values.

  • Data

    We first analysed the device data and the current dataflow model of the application. The data included

  • Signals- Signals are collected dynamically. It contains information about the distance travelled, how often the motors driving the lift are running and the weight being carried by the elevator car.
  • Metadata- Metadata contains the component ID
  • Data Ingestion
  • We deployed and configured a local storage in case of stalled communication and Azure IoT Hub to handle the data ingestion.
  • We wrote a nodejs service to store data on the device in the elevator with the purpose of preserving messages and storing those that have not yet been sent to cloud. This acts like a local queue.
  • We defined endpoints in IoT Hub as Azure Service Bus queues.
  • Data Transit
  • The next step was real time monitoring for the maintenance technician. We used Signal-R based website to host it in Azure using App services and invoked the Service Bus queue for presenting the incoming messages to deliver in a real time without any performance degradation.

Optimizing the analytics to provide proactive predication

Stream Analytics processes the ingested data in real time on IoT Hub and streams useful data for analyzing onto SQL Database.

  • Processing and Analytics
  • We deployed Azure Stream Analytics to monitor the incoming data to look at the threshold and enable the workflow capabilities defined in the system. In case the distance travelled, weight carried and duration of the motor running has crossed the configured values, it means the elevator is due for service and then the notification message is pushed to the Azure Service Bus queue which will trigger the notification to maintenance team.
  • This also in addition stores the data in Azure Table storage for MIS reporting at later stages.

Data storage for future use and ensuring data security

SQL Database provides high-end security features that can be easily configured to ensure data security.

Data Rest

  • One of the requirements from solution scalability point of view from the client, predict a failure.
  • Using machine learning, the device can be trained to predict a failure by analysing the past data.
  • To map a queue message to a specific parser we used Message Factory available in Service Fabric SDK. This way the message is classified and parsed by the specialised parsers and stored in Azure DB in JSON format.

Visualizing of the data

Microsoft Power BI brings visualization of the data insight to users.

Business Benefits

  • The accurate alert for equipment outage ensured the quick despatch of the technicians and there by reduced down time for customers
  • Service efficiency improvements and reduced down time for the customers were the solution highlights
  • Real-time monitoring and assured connectivity availability
  • Ability to manage all elevators installed at once from a single point of contact
  • Improved the scheduling of maintenance operations and thereby reduced the cost

The significant design element is that the current application architecture is that the entire IOT architecture and set up is maintained independent of the existing elevator system, hence it will not interfere with the working of the elevator or its maintenance at any point and also, it will be very reliable under all circumstances

Opportunities going forward

Big Data Analysis & Machine Learning – The large amount of untapped data from the elevators can be used to feed data to the Azure cloud platform, using Microsoft's Intelligent Systems Service to help capture that information and its Machine Learning service with an aim to develop a system that knows what repairs need to be carried out before the actual failure and alert the service technicians.

Similar stories

Tell us a little about yourself, and we'll be in touch right away

GET IN TOUCH