Memuat
Memuat
Watch every step above performed live, with English narration.
0 plays
Class book
Page 1 / 6
Cover: Class Classification of Power Quality Disturbances Wavelet #1: Types of Power Quality Disturbances: Sag, Swell, Harmonics, Transient, Flicker
Click a page or use ◀ ▶ to turn · swipe on mobile · to enlarge
Want to go deeper?
Join one of our courses or ask us directly on WhatsApp.
Picked from the software, topic, and level of “Class Classification of Power Quality Disturbances Wavelet #1: Types of Power Quality Disturbances: Sag, Swell, Harmonics, Transient, Flicker”.
Other ways we can help with Python.
Learn with a mentor
Scheduled Simulation & Engineering courses with live guidance and a certificate.

Course/Training Ansys ~ Heat Transfer and Heat Flux Analysis
★ 5.0 (10)

Course/Training MATLAB — MATLAB App Design: The Ultimate Guide to MATLAB Apps
★ 5.0 (10)

Course/Training Ansys — Airflow Simulation of a Car Radiator with ANSYS
★ 5.0 (9)
Have it built for you
No time to learn Python? Our team can do the project for you.

Matlab Development Service — Complete Neural Signal Processing and Analysis Zero to Hero
★ 5.0 (59)

Ansys Maxwell Development Service
★ 5.0 (50)

Petrel Development Service
★ 5.0 (14)
Get notified about new Python classes
At most one email a week. Unfollow anytime with one click.
The full narration of this video. The current sentence is highlighted while the video plays; click any sentence to jump there.
Here is the final result, 9 voltage waveforms, from normal to disturbances such as Sag, Swell, Harmonic, Transient, Flicker, and Knock, complete with RMS values per cycle. At the end of this series, the machine will recognize everything with an accuracy above 98%. Let's get started. Hello, welcome to the tutorial series on research, detection, and classification of power quality disturbances using Wavelet Transform and Machine Learning. Poor power quality causes industrial machines to shut down suddenly, data centers to fail, and equipment to break quickly. To address this, we must automatically identify the type of disturbance from voltage recordings. In this 6-episode series, we will build everything. Disturbance models, IEEE 1159 compliant datasets, Wavelet Transform, feature extraction, classification with SVM, Random Forest, and XGBoost, up to testing against NICE. In the first episode, we will learn about the types of disturbances.
We open the terminal through the terminal menu, new terminal, then install numpy, matplotlib, pywavelet for Wavelet Transform, scikit-learn, and XGBoost. This series does not require a downloaded dataset, as all signals are generated itself in a controlled manner, a common method used in power quality papers.
Create a file named signal_underscore_peki.py Voltage signal at 50 Hz, 10 cycles, sampled at 3.2 kHz, so 64 samples per cycle and 640 samples per signal. The event function creates a disturbance time window that starts and lasts randomly. Sag is a voltage drop of 10-90%, swell is a voltage rise of 10-80%, and interruption is voltage loss over 90%, all lasting 1-6 cycles. The next disturbance changes the waveform shape.
Harmonics add components at multiples of 3, 5, and 7 with amplitudes of 5-15%. Transient oscillation is a 300-900 Hz wave that decays, like when a capacitor bank is connected. Flicker is an amplitude modulation of 8-25 Hz that causes lights to flicker. Knock is a periodic flicker caused by power electronic converters. There is also a combination of sag and harmonics. The add noise function will be used in the final episode, create a file named type_underscore_disturbance.py.
The RMS per cycle function calculates the effective value per cycle in per unit, where 1 means nominal voltage. Run. Sag in this example drops to 0.26 per unit, interruption drops to 0.17, and swell rises to 1.3. Interestingly, harmonics, transients, and knock almost do not change RMS, even though the waveform is distorted. So RMS alone is not enough.
Let's look at the nine waveforms. The red line is RMS per cycle. Sec, swell, and interruptions are clearly visible from the red line going down or up. Harmonics make the waveform no longer smooth sine wave, transients introduce fast decaying oscillations, flicker makes the amplitude slowly wave, and knock is just a small spike that is hard to see. For waveform disturbances, we need wave-flat.
Done. We have now learned the nine types of power quality disturbances, modeled them with Python, and seen that RMS per cycle is only sufficient for magnitude disturbances. In the next episode, we will generate a dataset of 2700 signals with random parameters according to IEEE-1159. Currently working on a thesis, dissertation, or research in the field of power quality and signal processing? Cerdas Inovasi Digital helps with the implementation of machine learning, from generating disturbance signals according to IEEE-1159, wave-flat transformation, feature extraction, up to classification with SVM, Random Forest, and XGBoost, as well as opening Python programming courses for electrical engineering. Want to master the entire series, from synthetic signals to AIS testing? All 6 episodes, complete with PDF step-by-step guides and source code, are available for premium tutorial subscribers. Subscribe starting at Rp69.000 per month, save 28% with the 12-month package, or pay once Rp999.000 for lifetime access. Want just one class? Buy a single class with lifetime access. Subscribe now at the premium page cerdasinovasidigital.com Contact us via WhatsApp, or visit cerdasinovasidigital.com Thank you for watching, see you in the next episode.
Type a question or keyword; we find the part of this episode that explains it and jump the video there.
Notes are saved with the current video time and are only visible to you.
Stuck on a step? Ask here; the instructor and other learners can answer.
No questions yet.

Cerdas Inovasi Digital Team
Software developers, BIM & 3D engineers, and AI practitioners
We build software, BIM models, games and AI automations for clients every day, and turn that hands-on work into step-by-step classes: every step is shown on screen and comes with a PDF guide you can keep.
See our clients →