Digital Equipment Operator: Difference between revisions

Line 26: Line 26:


= WHAT =
= WHAT =
AIoT can support the Digital Equipment Operator in many ways. Smart, connected solutions can help improving OEE through improved visibility, advanced analytics and forecasting. AIoT can help enable OEMs to support Asset-as-a-Service offerings. For the operator this is interesting because it can help shift from Capex to Opex, making innovation investments easier. Asset Performance Management (APM) aims at taking a holistic view at production as well as maintenance, utilizing data and insights generated via AIoT. Process optimization can play a big role, e.g. to improve manufacturing quality and minize scrap rates. Finally, using predictive and preventive maintenance to minimize downtimes can also play an important role.
AIoT can support the Digital Equipment Operator in many ways. Smart, connected solutions can help improving OEE through improved visibility, advanced analytics and forecasting. Asset Performance Management (APM) aims at taking a holistic view at production as well as maintenance, utilizing data and insights generated via AIoT. Process optimization can play a big role, e.g. to improve manufacturing quality and minimize scrap rates. Finally, using predictive and preventive maintenance to minimize down-times can also play an important role.


[[File:0.2.2 What.png|800px|frameless|center|What]]
[[File:0.2.2 What.png|800px|frameless|center|What]]

Revision as of 20:47, 3 August 2021

More...More...More...More...Digital Equipment Operator

The Digital Equipment Operator

The Digital Equipment Operator is utilizing AIoT to optimize how he operates physical assets or equipment. Goals often include asset performance optimization and process improvements. Examples for Digital Equipment Operators include manufacturers, electricity grid operators, railroad operators, and mining companies. This section will introduce the concept of the The Digital Equipment Operator in detail, again following the why, what, how structure from the introduction.

WHY

The motivation to become a Digital Equipment Operator can be manifold. A good starting point is to look at OEE (Overall Equipment Effectiveness), or whatever the equivalent in the specific industry. OEE measures the performance of an asset compared to its full potential. OEE quantifies the utilization of manufacturing resources (including physical assets, time, and materials) and provides an indication of any gaps between actual and ideal performance. OEE is often calculated based on the following three metrics:

  • Availability, e.g. asset up-time
  • Performance, e.g. system speed
  • Quality, e.g. levels of defects

Depending on the industry and asset category, the detailed calculation of OEE might be different. In manufacturing, it will often include planned vs. actual production hours, machine speed, and scrap rates. Each industry has its own, specific ways of looking at availability, performance rate, and quality rate. For a rail operator, a key performance rate indicator will be passenger miles; for a wind turbine operator it will be kWh generated; for a mining operators it will be tonnes of produced ore.

Why

WHAT

AIoT can support the Digital Equipment Operator in many ways. Smart, connected solutions can help improving OEE through improved visibility, advanced analytics and forecasting. Asset Performance Management (APM) aims at taking a holistic view at production as well as maintenance, utilizing data and insights generated via AIoT. Process optimization can play a big role, e.g. to improve manufacturing quality and minimize scrap rates. Finally, using predictive and preventive maintenance to minimize down-times can also play an important role.

What

Example: Escalator operator (railway company)

The first example we want to look at is a railway company which is operating escalators at its train stations. For a large railway company, this can mean a fleet of thousands of escalators in a wide geographic range. Most likely, the escalator fleet will be highly heterogenous, including products from many different vendors. Reducing downtimes will be important for customer satisfaction. In addition, getting improved insights into the escalator´s operational healh status can also help reducing operations and maintenance costs.

For the railcompany, the escalator monitoring has to work for the entire fleet, and must provide a seamless integration with the facility management operations system. Getting all the different suppliers on board to agree on a common solution will be impossible. The logical consequence is to design a solution which can be applied to existing escalators in a retrofit approach, potentially even without support from the escalator vendor/OEM.

A good technical solution in this case is to utilize AI-based sound pattern analysis: Sound sensors attached to the escalator provide data which can be analyzed either using an on-site edge node, or centralized in the cloud. The AI-based sound pattern analysis provides insights into the current state and can even predict the future state of the escalator performance.

Once a problem is identified or forecasted, the train station operations personel or the facility managemnt organization is provided with this information and can take appropriate action.

Example: Escalator operator (railway company)

Example: School bus fleet operator

Another good example for a Digital Equipment Operator is a school bus fleet operator, utilizing AIoT to provide a platform which offers shuttle services for schools. Instead of using a fixed bus network and fixed bus schedule, the service is utilizing AIoT to offer a much more on-demand service to students. Instead of using fixed bus stops, virtual bus stops are introduced which can change during the day, depending on demand. Students are can use a smart phone app to request a ride to and from the school. Shuttle buses are equipped with an on-board unit to provide bus tracking and AI-based in-vehicle monitoring. The platform in the back-end is utilizing AI to optimize the pick-up order and routing of the shuttle buses.

Example: School bus fleet operator

This example will be discussed in more detail in the sourcing chapter. The figure below shows an example how the routes for multiple vehicles can be optimized to support multiple stops on a dynamic route.

UX for School Bus Shuttle

Example: Aircraft fleet operations planning using flight path optimizer

Modern Airlines were amonst the first to become Digital Equipment Operators, first utilizing telematics, m2m and now IoT in combination with advanced analytics and today AI. Managing a large fleet of aircraft is a challenging task. One critical process in this context is flight path planning. The flight path describes the way from one airport to another, including detailed instructions for take-off and landing, as well as the way between the two airports. From the airline´s point of view, the two most important aspects are safety and fuel costs. The latter requires inputs like weather conditions, overflight fees, fuel costs at origin and destination, as well as aircraft performance data. Based on this information, the flight path optimizer optimizer can calculate the optimal route.

Example: Airplane fleet operations planning using flight path optimizer

HOW

There is no one-size-fits all answer to becoming a Digital Equipment Operator. This section is looking at a generic Solution Lifecycle, as well as considerations for execution and delivery - analogous to the previous section.

Solution Lifecycle

For some Digital Equipment Operators, there will be a central AIoT solution which is at the core of their fleet operations. The airline`s fleet planning system might be such a core application. However, very often, Digital Equipment Operators will find that the solutions they require are on the long tail of the AIoT chart (see dicussion on the long tail in the AIoT 101). This means that they are looking at building multiple, specialized solutons, which need to be constantly enhanced and adapted. This can be supported by a measure / analyze / act approach. The AIoT in High-Volume Manufacturing Network case study provides a good example for this approach.

How

Considerations for execution and delivery

For the Digital Equipment Operator, execution and delivery will require a different perspective than for the Digital OEM. While also any investment will have to be justified by a matching business case, the overall business models tend to be much more straight forward. Similarly, leadership and organization are important, but probably not as challenging. Other aspects like sourcing, UX, DevOps, compliance and legal and productization will be less important compared to the Digital OEM. Data strategy, on the other hand, will be key - especially if a multitude of potentially heterogeneous data sources - sensors and enterprise systems - will have to be integrated. Finally, the Digital Equipment Operator will have to focus on fitting the new AIoT solutions into existing business processes. And in order to get there, asset retrofit, site preparation and rollout management will be key prerequisites.

Execution and Delivery aspects