by Howard Penrose, Ph.D., CMRP | Oct 3, 2021 | Asset Management, Electrical Reliability
Among the challenges of aging electrical-transmission and -distribution infrastructure in the United States is the shortage of all transformer types. In addition, the use of traditional, complex monitoring methods for trending and prognostics in existing equipment...
by Howard Penrose, Ph.D., CMRP | Sep 26, 2021 | Asset Management, Electrical Reliability
Considerable attention has been given to the application of Electrical and Motor Current Signature Analyses (ESA and MCSA) in motors and generators. But little in the way of research has been published on the use of ESA with transformers. From an operational...
by Howard Penrose, Ph.D., CMRP | Sep 19, 2021 | Asset Management, Electrical Reliability
This week’s article concludes our seven-part series. In Parts V and VI (see links below), we developed the classification and Remaining Useful Life (RUL) models that we would use in our Machine Learning project. The final step in developing our tool is to...
by Howard Penrose, Ph.D., CMRP | Sep 12, 2021 | Asset Management, Electrical Reliability
Up until now, we’ve focused on just using raw electric-motor data in this Machine Learning series (see article links to below). That includes moving from working through the information to classifying different types of faults with it. The aim, in effect, has...
by Howard Penrose, Ph.D., CMRP | Sep 5, 2021 | Asset Management, Electrical Reliability
In Part IV of this series (link below), we determined how to pre-process data for our example Machine Learning (ML) project. Here, we discuss development of data representing defective conditions if the real-world type isn’t available. Beware, though: This task...
by Howard Penrose, Ph.D., CMRP | Aug 30, 2021 | Asset Management, Electrical Reliability
Evaluation and pre-processing of data is one of the more time-consuming steps in development of a machine-learning (ML) project. In this step, the data scientist views and manipulates the collected data to see what types of artifacts and patterns emerge, including...
by Howard Penrose, Ph.D., CMRP | Aug 21, 2021 | Asset Management, Electrical Reliability
In Parts I and II of this particular series (see links below), we discussed using raw motor data for Machine Learning (ML); identified an example electric motor; selected an ML language; and explored some available motor data. Now we need to determine what we will be...
by Howard Penrose, Ph.D., CMRP | Aug 15, 2021 | Asset Management, Electrical Reliability
In the first part of this article series (Aug. 8, 2021, see link below), we identified an electric motor and raw data that’s available for performing a Machine Learning (ML) project. We also reviewed the basic steps in the development of an ML system using that...
by Howard Penrose, Ph.D., CMRP | Aug 8, 2021 | Asset Management, Electrical Reliability
The race to Machine Learning (ML) and Artificial Intelligence (AI) for electric machines has primarily focused on the spectral features of those units. As more academic papers are published, though, the focus is taking us further into advanced topics. Those topics are...
by Howard Penrose, Ph.D., CMRP | Jul 31, 2021 | Asset Management, Electrical Reliability
Incorrect settings in a variable-frequency-drive (VFD) application have an impact on the windings of an electric motor. If a drive is not set correctly, or not tuned when straight volts/hertz settings aren’t used, stresses occur between the turns in a winding....
