Chevron Left
Retour à Battery State-of-Charge (SOC) Estimation

Avis et commentaires pour d'étudiants pour Battery State-of-Charge (SOC) Estimation par Université du Colorado à Boulder

4.8
étoiles
135 évaluations
29 avis

À propos du cours

This course can also be taken for academic credit as ECEA 5732, part of CU Boulder’s Master of Science in Electrical Engineering degree. In this course, you will learn how to implement different state-of-charge estimation methods and to evaluate their relative merits. By the end of the course, you will be able to: - Implement simple voltage-based and current-based state-of-charge estimators and understand their limitations - Explain the purpose of each step in the sequential-probabilistic-inference solution - Execute provided Octave/MATLAB script for a linear Kalman filter and evaluate results - Execute provided Octave/MATLAB script for state-of-charge estimation using an extended Kalman filter on lab-test data and evaluate results - Execute provided Octave/MATLAB script for state-of-charge estimation using a sigma-point Kalman filter on lab-test data and evaluate results - Implement method to detect and discard faulty voltage-sensor measurements...

Meilleurs avis

NB
12 août 2021

As an electrical engineer, I firmly state that this course is the best for anyone who would like to embark on this journey of battery energy storage. Well structured\n\nWith an excellent instructor

BS
10 août 2020

Good and a very challenging course. Really makes you work to understand even the basic concepts. Challenging theoretical and practical assignments. Lot of learning obtained from this course

Filtrer par :

1 - 25 sur 29 Avis pour Battery State-of-Charge (SOC) Estimation

par John W

17 mai 2019

Overall, I good introductory course into Kalman Filtering for SOC estimation. However, the final project was a little bit to easy. In addition to tuning the initial covariance states, maybe add a different part 2 (other than tuning initial parameters) for developing to understand the kalman filter algorithm relating to battery estimation.

par M. E

8 janv. 2020

The course was well planned and organised! There is flexibility in the course deadline which is appreciable and suitable for students, Working professionals, faculties.

par Vigneshwaran T

29 août 2021

D​on't give up if you are intimidated by the abstract mathematics at the beginning of this course, which is challenging, but after the end of week #2 everything will make sense and the subsequent course content gets much easier. I am a computational chemist and I never even heard of sequential probabilistic inference prior to this course, and I am not that good at mathematics as well. So, believe me Prof. Gregory Plett has done an excellent job on explaining these complicated concepts, turst him and stick with the course until the end. I got everthing I hoped for from this course. I thank Prof. Gregory Plett and Coursera for offering this course.

par Albert S

2 mars 2020

This course is comprehensive introduction into the matter. The course explains in detail mathematical concepts behind Kalman filters (and can therefore serve very well for general understanding of estimation theory and Kalman filters), than it shift gently to Kalman filter approaches to state-of-charge. Even with minimum pre-knowledge, after the course ends, one is fully equipped to deal with ECM-based state-of-charges. This course requires dilligent work at home as well. I would recommend it to anyone dealing with battery control algorithms, both at the university, as well as in the private sector.

par Davide C

1 mai 2020

This course deeply explains about linear Kalman filter and its non-linear externsion: Estended KF and Sigma Point KF. The course also explains how to apply these powerful tools to battery cells State of Charge estimation, a physical quantity which cannot be measured directly and therefore has to be estimated indirectly based on electrical current, voltage, and temperature. The professor was capable to explain in a simple way such complex mathematics behind Kalman filters theory. I am looking forward to use this new knowledge at work.

par Kharan S

23 août 2020

The course explains the Kalman filter in detail. The highlight of this course is that the professor explains all the complicated mathematics in small advancements that you can easily understand rather than putting a lot in front and confusing a lot.

par Nicolas B

13 août 2021

​As an electrical engineer, I firmly state that this course is the best for anyone who would like to embark on this journey of battery energy storage. Well structured

With an excellent instructor

par Bhargav S

11 août 2020

Good and a very challenging course. Really makes you work to understand even the basic concepts. Challenging theoretical and practical assignments. Lot of learning obtained from this course

par Ameya K

3 mai 2020

The concepts taught were absolutely crucial for the later parts of this specialization and they were explained properly.

par Shovan R S

16 sept. 2020

Great course!!! I got hands on experience with all types of kalman filter for battery state estimation.

par HAFIZ A A

29 nov. 2020

Sir Gregory plett is an excellent Professor Ever and thanks to Coursera for such valuable plateform.

par J S V S K

15 sept. 2020

Nice Explanation and programming also easily understandable

par Nikhil B

10 juil. 2020

A great explanation of SOC estimation using EKF and SPKF.

par Piotr M

1 nov. 2021

Great knowledge to go deeper into battery world

par Nagapoornima S

27 mars 2021

The course was challenging.

par 2019BTEEL00034 M S S

12 avr. 2021

good course to start upon

par Thang N

20 août 2020

I like this course!

par Oscar D S B

25 oct. 2020

Excellent course.

par VASUPALLI M

25 sept. 2020

Excellent course

par Ryosuke I

9 oct. 2020

とてもいい勉強になりました

par YE Z

3 juin 2020

Good course.

par BHARADWAZ B

6 juin 2020

.

par BHARADWAZ B

6 juin 2020

.

par varun k

17 mai 2020

Overall it was good course with detail explanation about state estimation using kalman filter, EKM and SPKF. Superb explanation of topics with optimum pace and trainer was expectionally good in presenting such complex topics.

But the final project was too easy. There was less challenge. A small variation could have been introduced in the project where one actually learns how to program Kalman filters. For the level of mathematical complexity involve during derivations, the final project is not a match. Keep challenging problems as projects it would be great!

par Mario E

22 avr. 2021

Content wise very interesting but the math was really a challenge this time. So it takes really some energy to go through and solve all the quizes. Taking a break in between and listen to some of the lessons a second time helped me at the end.