Detecting different fault locations on a bearing
We are going to use the popular Bearing Vibration Data Set from Case Western Reserve University as a benchmark to demonstrate how different bearing conditions and faults can be properly correlated to a different operational mode, and ultimately to the automatic identification of healthy and faulty operational conditions.
MultiViz Vibration’s Mode Identification feature is powered by our Automatic Mode Identification (AMI) unsupervised algorithm for multivariate time series analysis. It performs multidimensional data segmentation and clustering in time series data, such as waveform vibration signals. It detects time periods in which the data exhibits a similar behavior and reports these periods as belonging to the same operational mode.
Operational modes are often correlated with typical conditions of an asset, like on/off, load conditions or fault states. Thus, the identification of different modes when the behavior of the machine has remained the same, can point to the appearance of a fault in the machine.
Predictive Monitoring: Gas Turbines Demo
This Factory Is Using AR To Help With A Hiring Crunch
One of the challenges associated with AR has been in trying to turn a complex physical process, such as wiring a component or working a machine, into code that could run on a headset. Taqtile CEO Dirck Schou said the company’s software makes programming for AR glasses simple, and based on my conversation with Tim Lecrone and Beau Wileman of PBC, the software Taqtile developed is easy to use. Once PBC has created a module for training it pays for itself after 1.44 employees train with it according to Wileman.
The cobots help handle processes that are repetitive and free up people to take on different tasks. Given how tough it is to hire people to work in the factory, using them helps reduce the overall staffing load. But the biggest gains so far have been in training and getting employees quickly up to speed. Now PBC can hire a person and get them working on a machine in a few days as opposed to that taking up to six weeks. It also helps reduce the cost of training a cobot and staff. Wileman told me that an intern, which costs $17 an hour, can train a cobot or map out a process in less than four hours, while it might cost around $30,000 for an outside expert to manually train a cobot.
Machine Learning Keeps Rolling Bearings on the Move
Rolling bearings are essential components in automated machinery with rotating elements. They come in many shapes and sizes, but are essentially designed to carry a load while minimizing friction. In general, the design consists of two rings separated by rolling elements (balls or rollers). The rings can rotate can rotate relative to each other with very little friction.
The ability to accurately predict the remaining useful life of the bearings under defect progression could reduce unnecessary maintenance procedures and prematurely discarded parts without risking breakdown, reported scientists from the Institute of Scientific and Industrial Research and NTN Next Generation Research Alliance Laboratories at Osaka University.
The scientists have developed a machine learning method that combines convolutional neural networks and Bayesian hierarchical modeling to predict the remaining useful life of rolling bearings. Their approach is based on the measured vibration spectrum.