(testing signal)

Tag: PredictiveMaintenance

Sensor data acquisition for machine learning and digitization projects – Electronic Products & Technology

The digital transformation market is growing rapidly and is set to reach a volume of one trillion dollars by 2025. Machine learning is also quickly gaining traction and is projected to grow to volumes amounting to trillions of dollars over the next couple of decades. Such market dynamics are resulting in an immense demand for appropriate solutions, and the development of a supply to match.

But the insufficiency of data is one of the main reasons why both machine learning and digitization projects fail. Data starvation puts multimillion dollar investments into digitization projects at risk. The availability of data is often being overestimated, leading to breakdowns in planned processes that were built on estimations and predictions, rather than preliminary analysis during project development.


VelocityEHS Machine Learning Expert Authors Award-Winning Research Highlighting Benefits of Predictive Monitoring Programs

CHICAGO, Aug. 26, 2021 (GLOBE NEWSWIRE) — VelocityEHS, the global leader in cloud-based environmental, health, safety (EHS) and environmental, social, and corporate governance (ESG) software, announced today that Dr. Julia Penfield, Ph.D., principal machine learning scientist at VelocityEHS, has received the Best Paper Award for her work on the application of machine learning in predictive online monitoring for the maintenance of power system assets at the 2021 icSmartGrid conference. The paper, “Machine Learning Based Online Monitoring of Step-Up Transformer Assets in Electrical Generating Stations,” was co-authored by Matt Holland, Maintenance Engineer at BC Hydro and provides evidence of the significant financial and safety benefits of applying machine learning to predictive monitoring programs.


Multivariate Outlier Detection – Data Science Central

I was given 3 GB of Machine Generated data being fed by 120 sensors (5 records every second) in an excel format. The task in hand was to mine out interesting patterns, if any, from the data.

I fed the data in R in my local machine and performed various descriptive and exploratory analysis to have some insights. Customer was also looking for some low cost maintenance mechanisms for their machines. So I  thought if I could study the outliers and provide some information about system health. This could also be monitored real time using dashboards and if possible could forecast at a near future time point for early alarm and predictive maintenance.

So this became a case of outlier detection in 120 dimensional space. Now, as I studied, values in around 90 columns were found to be constant over the entire time period and were contributing nothing towards system noise.