Industrial Automation, Robotics and Industry 4.0Fraunhofer IPA and SICK are developing an ancillary intelligent flow sensor-based leak detection service that saves energy costsThe cumbersome search for leaks in air compressor units could soon be much easier: Together with SICK AG, Fraunhofer IPA is developing an auxiliary leak detection service for an intelligent flow sensor.Self-learning algorithms evaluate the readings and in doing so identify leaks.Under ISO 50001, companies are required to save energy.They should set their own goals that describe how much energy they intend to save in the coming years, and then meet this goal.An area with great potential for energy savings is compressed air, one of the most widespread and expensive energy sources in German industry.There are around 60,000 air compressor units in operation throughout Germany.Together, they consume 16.6 terawatt hours each year, which is equivalent to 7 percent of the total electrical energy consumption in German industry.However, up to 30 percent of the energy consumed is lost through small leaks.Until now, detecting these holes, cracks or leaking connectors has been a laborious task.Christian Dierolf from the Department of Industrial Power Systems at the Fraunhofer Institute for Manufacturing Engineering and Automation IPA says: “Many users feel that the products and methods for detecting leaks are not worth the trouble.They involve the use of an ultrasonic device to detect leaks or the addition of new valves for individual control of pneumatic actuators.”As a result, many businesses end up living on wasted energy.However, in the future, there will be no reason to exhaust compressed air unnecessarily and miss out on energy saving potential.This is because researcher Christian Dierolf, in close collaboration with SICK AG, is developing a leak detection auxiliary service for his intelligent flow sensor.It records continuous pressure, temperature and flow rates and uses them to generate complete curve profiles.These curves will then be evaluated by a self-learning algorithm.Christian Dierolf explains: “The best thing about this is the 'grouping': leaks are shown in profiles of characteristic curves.These are recognized by the algorithm, which sounds the alarm.”Implementation should be easy: The sensor, which Fraunhofer IPA and SICK are developing together from concept to production, does not need to be connected to a compressed air system machine control system or an industrial PC.Instead, the flow sensor has its own small screen and additional interfaces such as MQTT and OPC-UA, which allow automatic notification to the user, who can also access the sensor through a web interface.The algorithm is also self-learning.This unsupervised machine learning means that a human only needs to check whether the algorithm has drawn the correct conclusions from the information available.Thomas Weber, Head of Development in SICK's Industrial Instrumentation department, says: “For us, the results of the entire development project are reason enough to make clustering an intelligent service that is offered to all our customers as standard. in future generations of flow sensors..”However, it will take some time before this can become a reality, as the leak detection auxiliary service for intelligent flow sensors is only a prototype so far.An air compressor demonstration unit was recently built at the company headquarters in Waldkirch and handed over to Fraunhofer IPA in Stuttgart.This contains the sensor prototype that is currently being tested and developed.ABB Ability Digital Powertrain energy assessments will provide valuable insights from operational data to increase the energy efficiency of motorized systemsThis is the potential contribution of automation to production processes that offer results of at least the same quality using less energy and resourcesThe alliance focuses on the development of IIoT solutions for energy management in buildings and large facilities©2022 infoPLC.net Industrial Automation, Robotics and Industry 4.0