Keeping PDS running is a full-time business, and demand is increasing every year as new deployments of the door systems spring up pretty fast across the globe. "The typical PDS is a maintenance operation. You install once and you maintain it for many years. Making sure a door system never breaks down requires a lot of data, and it could be important for Customer to turn its attention to the large amounts of untapped information PDS generates each day. Tarento is aiming to support Customer develop a system that knows what repairs need to be carried out before anything breaks and which can advise engineers on what work needs doing during call-outs.
CNIC Information System with Pakdata Cf In Pakistan
Touch IoT with SAP LeonardoMAINTENANCE AND SERVICE MANAGEMENT FOR PEDESTRIAN DOOR SYSTEMS IN A GALLERIA.
1. CUSTOMER - DOOR MAINTENANCE & SERVICING
- AN IOT CONCEPT
-- As a registered SAP Service Partner we distinguish ourselves in our ability to combine expertise in strategy
and business with deep SAP technology understanding, with an attitude of lasting service mindedness..
2. THE BUSINESS CASE
• Keeping Customer’s PDS running smoothly with machine learning and IoT.
− Keeping PDS running is a full-time business, and demand is increasing every year as new deployments of the door systems spring up pretty fast across the
globe. "The typical PDS is a maintenance operation. You install once and you maintain it for many years. Making sure a door system never breaks down
requires a lot of data, and it could be important for Customer to turn its attention to the large amounts of untapped information PDS generates each
day. Tarento is aiming to support Customer develop a system that knows what repairs need to be carried out before anything breaks and which can advise
engineers on what work needs doing during call-outs.
• How the system works
− Modern PDS systems generally use multiple embedded computer systems to help operate. These systems generate an array of data, indicating when
buttons are pressed, when the door opens and closes, how often the motors driving the doors are running and the frequency of open and close operation
etc.
− The PDS systems also generates error or event codes, which can be read by a maintenance engineer during the next routine service and help them work
out what needs attention.
− Aim is to attach devices that collects these codes, alongside other data about the operation of the elevator, and sends them to the Azure platform every
day.
− By monitoring usage in this way customer can plan to target when and where it carries out maintenance. Rather than scheduling a routine service every x
number of months, the frequency and nature of these services would instead be based on how each PDS is functioning. Keeping tabs on their workings
will be the Azure machine learning service, which will monitor details such as how often a PDS door opens or the energy expended to drive the systems.
− The rules used by the machine-learning service to determine when a service is needed, and what work should be done, will be automatically updated
based on feedback from engineers. For example, a door might be scheduled for a service every 10,000 times it opens, but that rule could be altered if
experience dictates that door generally needs attention every 5,000 times.
− For each type of PDS the ruleset might be the same, but the condition for when you need to do something might be different," The system would also
factor in what it had learned about the environment where the building was based.
− For instance, PDS that are in harsh environments conditions could need more frequent servicing.
2
3. HOW COULD WE HELP ?
• Help Customer build a comprehensive IoT platform to handle data flowing from the equipment.
− With focus on building the rules engines and software to support this.
− Devise software to prioritize handling of PDS error codes so the system understands the best course of action.
− Right choice and establishment of sensors, analytics and machine learning platform.
3
5. SENSORS & METRICS RELEVANT TO THE CONCEPT
• To measure
− Rolls and slide
− Rotation
− Temperature
− Environmental factor
− Pressure exerted on door panel
− Existing embedded computers
− Energy extended to rotate / slide the door
5
7. KEY MONITORING METRICS FOR ML
• When and where maintenance were carried out.
• Keeping tabs on their workings will be the Machine Learning service, which will monitor details such as
how often door opens
• Statistics received from door
7
8. LEARNING AND PREDICTIVE ANALYTICS
• With machine learning
− we're going to be given a list saying 'On your next maintenance these are the tasks that you should perform',”
− What all kind of maintenance task has to be performed
− Feedback from engineers on what the actual problem was and how they fixed it will help the system learn
− advises other engineers in future.
8
9. TECHNOLOGIES
• IOT platforms like SAP Cloud Platform and SAP Leonardo.
• IOT application enablement with SAP Leonardo with SAP Connected Goods.
9
10. TOUCH IOT WITH SAP LEONARDO
MAINTENANCE AND SERVICE MANAGEMENT FOR PEDESTRIAN DOOR SYSTEMS IN A GALLERIA.
11. STORY
Pedestrian Door Systems are today deployed pretty much
everywhere in malls, public areas, public and private offices.
Keeping pedestrian door systems running is a full-time business,
and the demand is increasing every year as new deployments of the
door systems spring up fast across the globe.
A typical Pedestrian Door System is a maintenance
operation. You install once and you maintain it for many years.
Making sure a door system never breaks down requires a lot of data,
and it could be important to turn attention to the large amounts of
untapped information PDS generates each day.
This story aims at thinking of a system that knows what
repairs need to be carried out before anything breaks and can
advise a maintenance manager to raise a work order to the service
technicians by having a visual representation of the health of the
PDS in a complex area for which he/she is responsible.