Summary of Validation Of Artificial Neural Networks to Model the Acoustic Behaviour Of Induction Motors, by F.j. Jimenez-romero et al.
Validation of artificial neural networks to model the acoustic behaviour of induction motors
by F.J. Jimenez-Romero, D. Guijo-Rubio, F.R. Lara-Raya, A. Ruiz-Gonzalez, C. Hervas-Martinez
First submitted to arxiv on: 27 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper investigates the application of multitask artificial neural networks to predict psychoacoustic parameters of electric induction motors, aiming to minimize their noise impact on the population. The approach uses electrical magnitudes and number of poles as inputs, rather than separating motor noise from environmental noise. Two topologies are proposed: simple models for interpretability and complex models for higher accuracy at the cost of hidden relationships. Simple product unit neural networks achieved the best results, using only 10 input variables and demonstrating an effective transfer mechanism to extract common features across multiple tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper looks into ways to reduce the noise from electric induction motors that can cause discomfort for people. It uses special kinds of computer programs called artificial neural networks to predict how loud or unpleasant the noise is. The program takes in information about the motor’s power and number of parts, rather than trying to separate the motor’s noise from other noises around it. Two types of programs are tested: simple ones that are easy to understand and complex ones that can get better results but hide what’s really happening. The simple program worked best, using just 10 pieces of information and showing how well it can figure out common patterns in different tasks. |
