At Diram we are always looking to innovate and help our clients to solve the problems that afflict them in their daily lives in an effective way, always relying on the latest technology available.
Learn below how with the help of our new methodology based on Machine Learning we managed to solve one of the most common problems in the industry.
It is necessary to perform measurements when industrial users have power quality problems. In these cases, the root cause of such problems can be evaluated based on the level and type of contamination (harmonic distortion) present in the user's power supply.
It is important to mention that it is not customary to question whether the measured pollution comes from the power grid or is caused by the operation of the industrial user. Although there are different reasons, there are two main ones to highlight:
1.- Performing such an analysis is relatively complex.
2.- In the past, most of the technology for electric power generation did not tend to generate this type of power quality problems.
For the two reasons mentioned above, it is usually automatically assumed that such contamination is generated by the industrial user, and the solution is designed based on that assumption.
However, currently, despite having many advantages over its predecessors, power generation technology has a clear tendency to generate this type of power quality problems. Therefore, there are segments of the network where the typically implemented solution may not be adequate, causing equipment failures, when if the correct premise had been considered, the specification of the solution would have been ideal and therefore the objectives would have been achieved.
In Diram we developed a tool based on Machine Learning (Artificial Intelligence) that allows the user to know with certainty when the pollution comes from the network and when it comes from the load center.
In our paper we will talk about:
Reach out to our technical specialists to learn more about this methodology and how we can implement it in your facility to help you have reliable measurements.
Sign up with your email address to receive monthly news and updates.
To begin with, it is vital that we understand a basic but essential distinction: the differences between linear and nonlinear loads.View more