What if monitoring Vibration alone does not solve predictive maintenance on complex assets? In this case we need to understand the overall picture about the process and everything else connected to the asset. All parameters (e.g. temperature, flow, vibration, power consumption) needs to be collected and looked at to make a better and more informed decision on predicting the health of the equipment. With the help of AI and AutoML (Machine Learning) methods, a mathematical model is trained from historical data, which serves as a permanent target-actual comparison between measured and predicted target variable. Through the additional calculation of dynamic expectation ranges (confidence bands) for the target variable, the measured behaviour of the target variable can be permanently evaluated and deviations can be output automatically. Ifm will be sharing a real case study of how AI and Vibration data assisted in predicting pump efficiency to help solve pump scheduling and in return saved energy. Then predicting when to do maintenance on assets.
Associated for close to a decade with ifm efector a German Family owned company, one of the world’s largest sensor and automation companies. Freddie has had numerous roles at ifm, 8 years with Industrial Networking and Control. Freddie was chosen to Manage, lead and grow the new IO-Link technology within Australia for the last 4 years.
In the last years, Freddie was chosen to lead the IoT team in Australia with regards to Industry 4.0 in various fields.
Freddie is focusing on the digital strategy, to better understand the value at stake from digital transformation and shape targeted strategies.
Freddie work to configure organizations so they can achieve rapid improvements in customer experience, innovation, revenue, and costs. He will help leaders translate their digital vision into a prioritized set of value-rich opportunities and help determine how organizations can be set up for success in a digital world with their Digital Transformation.