With its IIoT platform Moneo, Ifm takes a practical approach to getting started with digitalization projects: quick integration, intuitive operation, and clear added value for customers. In an exclusive interview, Mohamed Al Kadari, Vice President of Industrial IIoT at Ifm, explains how no-code, AI modules, and cloud technologies complement each other. He also explains which use cases focus on and where typical challenges must be overcome for IIoT projects to succeed in practice. In conversation with our Editor-in-Chief Susanne Woggon, the passionate amateur marathon runner also shared why he usually knows, even before the start of a race, what finishing time he can expect at the finish line.
Mr. Al Kadari, you joined Ifm in 2023 after seven years at Google. What attracted you to your new company?
Although Ifm is a significantly smaller company, it is technologically very sophisticated. We are currently going through various phases of transformation, not only in our business model but also in our organization. That’s why it’s very exciting for me to come from a company like Google, where everything has been digitized since its inception, and to join a company over 50 years old that is currently undergoing this process of change. For me, it was a cultural shift, but also a refreshing change of perspective.
How would you describe the Ifm IIoT platform Moneo in one sentence?
Moneo is the simplest and, at the same time, most innovative IIoT platform on the market.
How easy is it to use Moneo without programming skills or IIoT experience?
The platform is consistently designed as a no-code application. Users can integrate sensors, manage devices, visualize process data, and configure alarms without having to program anything themselves. While in traditional approaches, sensor integration is often a complex process involving various tools or IT systems, Moneo guides the user through the individual steps in a structured manner.
Step-by-step wizards play a central role in this process. They guide users through typical tasks such as sensor onboarding, parameterization, or the creation of visualizations. This is supplemented by training courses and demo content that make getting started easier.
Ifm’s goal is to extend the intuitive usability known from its hardware to the software as well. Much like a sensor, the platform should be usable without extensive training. That is why it is based on user interfaces familiar to users from everyday life, such as smartphone apps.
What role does AI play in your IIoT platform, and what specific benefits does it offer?
Our IIoT platform utilizes AI functionalities from the Microsoft Azure environment and integrates them specifically into our own platform. One example of this is the “Moneo Assistant.” This is a voice-based interface based on technologies similar to “Microsoft Copilot” that facilitates interaction with the platform.
In addition, various specialized AI modules are integrated into “Moneo Insights.” These include, for example, a “Lifetime Estimator,” which can be used to predict the remaining service life of components or materials. Another example is the “Smart Limit Watcher,” which, similar to a lane-keeping assistant in a car, enables dynamic thresholds. Unlike traditional, static thresholds, these adapt to changing operating conditions.
Especially in industrial applications with fluctuating loads or changing environmental conditions, rigid limits quickly reach their limits. AI-supported models allow for a more nuanced assessment and help detect anomalies more reliably. The added value is particularly evident where simple visualization and alarms are no longer sufficient to map complex relationships.
For which applications and industries is the IIoT platform particularly well-suited?
Today, Moneo is primarily used in discrete manufacturing and the process industry, such as in food production. In addition, the platform also plays a role in mechanical engineering, particularly in areas such as remote maintenance or on-site condition monitoring of machinery.
Typical use cases include the monitoring of pumps, fans, conveyor systems, or material storage units. The basic principle is often similar: First, it is determined which data is relevant for the respective use case and whether this data can be captured via sensors. Monitoring and alarm functions are then set up.
One example is the monitoring of a material storage bin. In addition to simply measuring the fill level, AI modules can also be used to forecast the remaining service life. Especially under varying production conditions, such as fluctuating utilization rates throughout the week—this enables significantly more accurate planning and helps prevent unplanned downtime.
How quickly can systems be connected and initial results achieved?
For brownfield projects, rapid implementation is a key advantage of the platform. Many companies operate with legacy system structures that lack modern interfaces. Here, Moneo enables a relatively straightforward retrofit.
In many cases, machines can be connected in less than 30 minutes. This also applies to older systems such as CNC machines where direct access to the control system is no longer possible. Nevertheless, relevant operational data can be collected via sensors and edge gateways and transmitted to the platform.
Initial insights, for example regarding runtime, downtime, or temperature behavior, are often available within a day. For more in-depth analyses, such as predicting failures or maintenance needs, observing a full operating cycle is generally required. Depending on the application, this can take several weeks—typically eight to twelve weeks.
How do you address issues such as data security, data sovereignty, and cloud usage?
Moneo is primarily operated as Software-as-a-Service (SaaS) on Microsoft Azure. This architecture offers advantages in terms of scalability, maintenance, and the rapid integration of new features. At the same time, options for on-premises solutions remain available, for example for existing customers or in cases of special requirements.
In practice, issues such as data sovereignty and cybersecurity are closely coordinated with the customers’ IT departments. Typical questions concern the location of the data, encryption concepts, or the security of the hardware used.
A key principle of the platform is read-only access to machines. There is no active intervention in control systems; instead, data is collected exclusively. This so-called “Y-principle” reduces potential risks and simplifies approval by IT and OT managers.
In addition, established security mechanisms are used both at the cloud level and on the edge. These include encrypted communication, secure gateways, and alignment with common cybersecurity frameworks.
Why do IIoT projects fail in practice?
The biggest challenges lie less in the technology itself and more in organizational and structural aspects. For a long time, IIoT and Industry 4.0 were associated with high expectations that have not always been immediately fulfilled in practice. Consequently, there is a certain degree of caution in many companies.
Added to this are typical bottlenecks, particularly in small and medium-sized enterprises: limited human resources, lack of time, and insufficient capacity for complex implementation projects. Coordination issues between IT, maintenance, and external partners can also impact project success.
However, practical experience shows that projects rarely fail due to the technical solution itself. More often than not, the issues stem from communication problems, unclear requirements, or a lack of shared understanding. A clearly structured approach with concrete use cases and quickly visible added value is therefore crucial.
What trends are shaping the further development of the IIoT platform?
A key driver is the increasing use of generative AI. The goal is to further simplify the use of the platform, for example through voice-based interaction, automated dashboard creation, or intelligent support for alarm configuration.
In addition, concepts such as the digital twin are increasingly coming into focus. In the future, machines and processes could be virtually modeled to simulate their behavior under changing conditions. On this basis, for example, thresholds could be optimized or scenarios tested in advance. Cloud architecture plays a crucial role here. It enables the relatively rapid integration of new technologies and innovations, such as those from the Microsoft ecosystem, into the platform and their delivery to users.
Do data-driven analyses also play a role in your personal life?
More and more people in my personal circle are using data-driven applications. One example of this is the use of wearables in sports. I have been an amateur marathon runner for many years. Modern systems today enable very precise predictions of marathon finishing times based on training data, weather conditions, and individual performance parameters. This development demonstrates the potential inherent in the intelligent analysis of data. It is a principle that can also be applied to industrial applications.
