Electric Motors 4.0: How They Work in the Industrial Internet of Things

Internet-enabled electric motors? Just a few years ago, this seemed like utopia. Today, maintenance and operation via connected sensors are a reality. Three-phase and low-voltage motors have become “smart motors” thanks to developments in the fields of sensors, microservices, IoT platforms, edge computing and the cloud.

It is now straightforward to measure the performance of engines in real time and detect deviations immediately. In most cases, sensors are attached to the machine to detect temperature, vibration or overload. Making machines smarter is one factor. However, the Industrial Internet of Things offers many more possibilities: Thanks to the cloud, entire motor fleets can be connected, and vast volumes of data can be collected, which in turn enables continuous condition monitoring. Engineers can then respond immediately to pattern deviations.

In general, today’s production plants consist of machinery powered by electric motors. Now, companies benefit from a wide range of opportunities to optimize their engines and systems. Machines can be upgraded, and maintenance intervals improved. If a reliable predictive maintenance solution is to be created based on real-time analyses, it is necessary to consider various issues in advance. This is where edge computing including the cloud, platforms, microservices and sensors come into play.­

A platform should primarily be chosen based on the desired application as well as the intended expansion plans: Are specific interfaces required for edge computing? What about data hygiene mechanisms that cleanse and unify data? Should predictive maintenance be implemented with the help of certain machine learning algorithms? For a bottling line, to name an example, the Amazon platform AWS is an excellent choice, as its reliability is very high. A factor that is extremely important, because processes in bottling plants must run quickly and smoothly. Scalability of the platform is also crucial so that it can be adopted as requirements grow. It is particularly advantageous if computing power and data memory can be activated with the push of a button. Large cloud platforms such as Amazon AWS, Microsoft Azure and Google Cloud Platform with edge computing operating system, machine learning algorithms, MapReduce implementations, etc. offer a broad set of tools for a perfect start. In recent months, AWS has been continually adding new features such as local cloud modules or new machine interfaces to its IIoT platform. Do you want to operate your IIoT platform yourself? The up-and-coming German platform ADAMOS might be worth considering by your company.­­­­­­

Microservices are currently a significant development. Collectively, they form a software architecture consisting of many small, self-contained services. These part-modules provide freedom from specific technologies and platforms. This is of particular importance in the IIoT sector as only a few standards or platforms have established themselves to date. Companies need to respond to developments flexibly and independently. Microservice applications are incredibly diverse: some can take over authentication and authorization services to manage users and rights for all services across the system. Another micro-program, in turn, might manage the gateway service. It collects and aggregates the machine data and transfers them into the data lake. The data can then be retrieved and structured in a data warehouse to make them available; a process that is realized by yet another microservice. Predictive maintenance, in particular, requires applications that analyze data continuously (partly in real time) detecting deviations from previous patterns. In this way, malfunctions can be forecast at an early stage. Such information should then be communicated via a specific interface, such as that of a smartphone, for which GUI services are required. All in all, this scenario shows that a modular concept with microservices can deliver high-speed applications.­­­­­­­­­

All required values are measured and recorded by sensors. In most cases, however, these useful data collectors are not yet installed on the machines. The good news: temperature, vibration and light sensors can easily be retrofitted to existing electric motors. These are mounted externally and analyzed on a Raspberry Pi via edge computing. The degree of complexity depends on the application or the information required. A motor manufacturer who is solely responsible for design and development can easily integrate sensors directly into its products. In the previous example of a filling system, light barriers could be retrofitted to measure the throughput at specific points.­­­­

Getting started with IIoT can be quick and straightforward. Predictive maintenance applications and the associated machine learning are common topics that can be immediately started based on the collected data. Pattern recognition, as mentioned above, enables early detection of malfunctions leading to dynamic maintenance cycles. They allow you to predict when an engine will fail instead of its preventive replacement. But before an organization embarks on this process, those responsible must put together fast and flexible teams in which Industry 4.0 is tackled in an agile manner. The vital thing here is to work with manageable goals, for example by starting with only one machine. Vigorous teamwork is also crucial to be able to outpace potential competitors quickly. Particularly in the field of e-motors, numerous applications can yield lasting benefits for the operation and maintenance of machines. So start small but be quick — then you can win high with your technological advantage.

[TV1]source: assume colon missing

Executive Board Member elunic AG // Industry 4.0 & IIoT Solution Firm

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store