Numbers, please! Energy efficiency is measurable

Energy is cheapest and most environmentally friendly if we do not consume it in the first place. Therefore, energy efficiency makes a significant contribution to the energy transition, and we have already tapped into savings potential in many areas: LEDs are now standard and energy-intensive devices like old refrigerators or water heaters have either been replaced or switched off. At CONTACT, we have initiated a project to optimize energy efficiency in office buildings. It is surprising how much saving potential still exists, even though employees are already conscientious in their resource usage. By replacing electrical devices and air conditioning in the server room, as well as turning off and merging old servers, energy consumption has been reduced by 50 %. This is not only ecologically sensible but also economically beneficial. A lot can be achieved with little effort, provided consumption data can be logged and visualized.

Energy efficiency is not possible without software

The German government’s report on “Energy Efficiency in Numbers” provides an overview of the final energy consumption in Germany for sectors such as industry, transportation, private households, and commerce/trade/services.

Nearly a third of Germany’s final energy consumption comes from industrial processes. To achieve efficiency improvements here, it is essential to examine them more closely. A significant portion of energy (about two-thirds) is attributed to process heat, which is used, for example, in the production of products. To identify which facilities and machines in the production hall have saving potential, monitoring and controlling are necessary. Our software platform, Elements for IoT, provides companies with the ability to monitor, graphically represent, and analyze their consumption data. Data from metering points, such as those measuring power consumption, can be assigned to individual machines and production processes. Additionally, it is possible to process sensor values and machine control states and merge them into a digital twin of the machine. For the specific requirements of energy management, we have developed a new module that represents a continuous improvement process of energy performance indicators (according to ISO 50001). Starting from energy consumption, broken down by different energy types such as electricity or compressed air for a machine on the shopfloor, consumption values can be calculated down to a manufactured unit of the product. This also provides the opportunity to calculate the CO2 footprint of the manufactured product. The following example of a dashboard for a production facility shows a summary of a shift and provides information on energy consumption for the production process, as well as the average consumption for each manufactured unit from that shift.

Energy efficiency in production

Energy performance indicators can be used in various ways and are particularly important for audits according to ISO 50001. These audits require proof of a continuous improvement process. In addition to implementing sustainability concepts, this simultaneously saves resources such as electricity or gas.

Furthermore, energy information can be used to calculate the CO2 footprint, which can then be exchanged across supply chains. In the context of this data exchange, we implement the concept of the Asset Administration Shell to integrate the submodel for the CO2 footprint into our IoT platform.

Energy consumption data can also be useful in the manufacturing industry to optimize production processes. By assigning energy consumption data to the processes happening simultaneously, analyses show which sections are particularly energy intensive. Often, the usual metering interval of 15 minutes is not sufficient and higher time resolution data is required. Smart meters allow for sampling rates in the minutes or even seconds range, facilitating analyses that help optimize production processes.

AI-based forecasts for energy consumption

Interestingly, machines on the shopfloor are often found in standby mode, waiting for the next production order, even when there are no orders for the next few hours or the upcoming weekend. Optimized machine shutdowns which consider ramp-up times can directly save energy costs. A specific example of this is the implementation of an alarm mechanism that informs machine operators based on planned tool changes, services, or manufacturing orders about when it is advisable to shut down the machine. Additionally, the machine dashboard displays when the next order is due. Historical data studies have shown that for machines equipped this way, electricity cost savings can amount to about 23%. In the dashboard shown below, the shutdown recommendation is visualized by the red traffic light. It also indicates by how many kilowatt-hours the predicted value deviates from the actual measured power consumption.

The forecast of electricity consumption is based on decision trees and directly implemented in the platform. Consumption data is accessed through the digital twin of the machine. The forecast’s inference model uses data from planned manufacturing orders, including time data and information on the material to be produced, to calculate the expected electricity consumption in kilowatt-hours. If the actual measured value deviates from the forecast by a fixed limit, the system informs the responsible person(s) with a red traffic light on the dashboard.

Furthermore, peak management uses forecasts to avoid load peaks. If multiple machines or systems are in operation simultaneously at a production site, this can lead to overlapping peaks in energy demand, resulting in higher fees. Based on forecasts of the electricity consumption, it is often possible to optimize execution times and machine occupancy to evenly distribute energy consumption and prevent expensive penalty payments.

Developer Experience – from intuitive to complex

It sounds like an exciting vision of the future: users from every discipline can use ready-made program modules to quickly and easily create simulations, optimization tasks or analyses using artificial intelligence (AI). This can then also be implemented by departments whose employees do not have knowledge of a high-level programming language. That’s the idea. Of course, developers must first create these program modules so business users can assemble a solution that meets their requirements.

AI-powered analytics for the business department

Together with our partners, we are researching in the AI marketplace project to get closer to this vision. The name-giving goal is to develop AI applications in the field of the product development process and offer them on a central trading platform. The range will also include services such as seminars on selected AI topics or contract development as well as ready-made AI-supported apps and program blocks for very specific tasks. The development and reuse of the apps are currently being tested. The project team is evaluating the benefits and quality of the results at the same time.

Different programming levels for extended use

So that’ s the state of research, but how exactly do we at CONTACT support the development of reusable program modules, the integration of simulation models or AI-supported analysis methods? One example of practical application can be found in the area of predictive maintenance. Predictive maintenance means that maintenance periods do not take place at fixed intervals as before, but are calculated depending on operating data and events at the machine or plant. For such use cases, our Elements for IoT platform provides a solution to analyze operating data directly. The digital twin stores the data of the machine or plant in a unique context. This data can be directly retrieved and easily analyzed using block-based programming. With the no-code functionality of the IoT platform, departments can intuitively create digital twins, define automatic rules and monitor events, and create diagrams and dashboards – without writing a line of code.

In addition, there are applications around the Digital Twin that require more programming expertise. For this, the platform offers analysts the possibility to develop their models themselves in a higher programming language using a Jupyter Notebook or other analysis tools. Especially in the area of prototyping, Python is the language of choice. However, it is also possible to work with a compiler-based programming language such as C++. Continuous calculation of the predictions is then done by automating the models, which are available in a runtime environment. The code is executed either in the company’s own IT infrastructure or directly at the plant or machine in the field (edge).

We call this procedure low-code development, because only the code for developing the models is written. The data connection is made via the Digital Twin and is done configurationally. The piece of program code can then be reused as a program block for various applications, such as digital twins within a fleet.

CONTACT Elements for IoT is thus open to interactions at different levels: from the use of predefined building blocks (no-code), to the possibility of interacting with self-written program code (low-code), to the definition of own business objects and the extension of the platform based on Python.

The Digital Twin at the Center of Renewable Energy

According to the German Wind Energy Association (BWE), the share of wind energy in German electricity production this year is 27 percent, and in 2020 wind energy even represented the most important energy source in the German electricity mix. In total, more than 31,000 turbines have been installed, saving 89 million tons of CO2 equivalent in 2019. Wind power is thus a mainstay of low-CO2 and sustainable energy generation and makes an important contribution to the energy transition. Further increasing yields while reducing maintenance costs is therefore of great importance.

Increasing the efficiency of wind farms with smart systems

Digital Twins are the central element in exploiting the full potential of wind power and maximizing yields. Driven by the vision of creating a data-based development tool for the wind industry, the WIND IO joint project, funded by the German Federal Ministry for Economic Affairs and Energy, started a year and a half ago.

Under the leadership of the Institute for Integrated Product Development BIK at the University of Bremen, we are working with several consortium partners to build research facilities as cyber-physical systems and retrofit them with sensors, electronics and computers known as IoT gateways. This makes it possible to digitally map all the operating information of the real plant and combine it on a digital twin. The operating behavior can be simulated on the basis of the Digital Twin, which in turn provides insights for further optimization of the wind turbine. The Digital Twin not only provides information about the current energy yield, but also offers a comprehensive overall picture of the condition of each individual turbine.

Improved installation, maintenance and overhaul processes

The information obtained can be used, for example, to optimize maintenance and overhaul processes. For example, the data makes the aging process of components transparent at all times and automatically triggers an alarm if defined limit parameters are exceeded. The Digital Twin also uses the operating, environmental and weather data collected to determine a favorable time for maintenance of the plant. Ideally, this should be carried out when there is little wind, so as not to be at the expense of energy generation.

Both statistical methods and Artificial Intelligence (AI) models are used for the calculations. These methods also help to determine the best time to assemble a wind turbine, since the rotor blades can only be installed under certain conditions. For this purpose, in addition to weather data, additional parameters such as the vibration of the tower are included in the calculations.

Digital Twins for a sustainable industry 

The WIND IO project vividly demonstrates the potential of digitization and especially the concept of the Digital Twin. In addition, companies can use their data to simulate entire production and operating cycles. This makes it possible to minimize resource consumption, reduce energy consumption and at the same time coordinate production steps more effectively and optimize transport routes. Concepts such as the Digital Twin and data-intensive analysis methods are thus essential for a gentle and efficient industry.