Model Predictive Control for AC Motors

Han, Yaofei; Gong, Chao; Gao, Jinqiu

doi:10.1007/978-981-16-8066-3_1

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite all the advantages that predictive control provides, this type of control has only been applied more in recent years. This is due to the fact that, initially, the techniques for this type of control were based on empirical methods or mathematical and statistical methods [10], which were costly and challenging to implement [2]. With the fourth industrial revolution (Industry 4.0), there has been a greater focus on data quality and collection.…”

Section: Predictive Control Using Ai Systemsmentioning

confidence: 99%

Application of Artificial Intelligence Techniques to a Sensorial Module

Pimentel,

Gonçalves,

Pinto

et al. 2024

2024 10th International Conference on Mechatronics and Robotics Engineering (ICMRE)

View full text Add to dashboard Cite

Nowadays, society is in a climate of uncertainty regarding energy and resource sustainability, which is why efforts to combat this problem are made and encouraged daily. This is no different in the industry, where there is a continuous work to improve manufacturing processes in order to achieve utopian zero defect manufacturing. Alongside this, the emergence of new technologies, the development of the computing power of machines and the digitisation of processes in the context of Industry 4.0 have been fundamental to the production of data that feeds and develops artificial intelligence models.This dissertation will address a quality control problem in a welding process in the automotive industry. It is believed that the development of a predictive quality control system using artificial intelligence techniques can solve the problem in question.In order to study the problem, and due to the impossibility of working with the real problem, this work includes a study of the techniques expected to be applied in the final solution. As well as being theoretical, this study of methods has a practical component, applying them to data collected from a testbed. This testbed is a physical prototype with a parameterised process, also developed as part of this dissertation. In addition, a dataset referring to a laser welding process was also analysed to complement the study of the algorithms with data similar to data from the original problem.In this document, the scope of the work is framed within the current state of the art, followed by a theoretical reflection on the subjects covered. It is decided to study and apply the following supervised learning techniques to the data collected: K-Nearest Neighbours, Support Vector Machine, Linear Regression, Ridge Regression, Lasso Regression, Random Forest and Gradient Boosting. This is followed by a description of the test base developed and the methodology for collecting and processing the data.It is concluded that although the models built with the Support Vector Machine algorithms showed satisfactory results for modelling the laser welding process, the data collected from the test base was unreliable, and different models can perform differently in different situations.

show abstract

Section: Predictive Control Using Ai Systemsmentioning

confidence: 99%