Kalman Filter for Predictive Maintenance and Anomaly Detection

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review


There are various strategies in optimization of anomaly detection problem on sensor data. This paper describes a Gaussian Mixture Model (GMM) and Kalman filter to detect outliers within the sensor data of wire bonding. With limitation on data samples and high dimensional parameters, Principal Component Analysis (PCA) helped to reduce dimensionality without losing important information. The Expectation-Maximization algorithm for estimating Gaussian distribution parameters of GMM provided us a clustering model to fit our data. A weighted distance from the cluster center in the employed GMM model is applied to tune noise variances on measurement errors. The proposed method is validated using real measurements in the context of a manufacturing system.

Original languageEnglish
Title of host publication22nd International Carpathian Control Conference, ICCC 2021
Number of pages6
Place of PublicationPiscataway
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date31.05.2021
Article number9454654
ISBN (print)978-1-7281-8610-8
ISBN (electronic)978-1-7281-8609-2
Publication statusPublished - 31.05.2021
Event22nd International Carpathian Control Conference, ICCC 2021 - Online, Virtual, Velke Karlovice, Czech Republic
Duration: 31.05.202101.06.2021
Conference number: 22

Bibliographical note

Funding Information:
The authors acknowledge FCT (Fundacao para a Ciencia e a Tecnologia), Lisbon, through the 3 Quadro Comunitrio de Apoio, the POCTI and FEDER programs, and the grant PTDC-EME-PME-108859-2008 (through IDMEC) and UID/CTM/50025/2013 (through IPC), and the SFRH/BD/74027/2010 PhD schollarship within POPH/FSE (Programa Operacional Potencial Humano/ Fundo Social Europeu).

Publisher Copyright:
© 2021 IEEE.

    Research areas

  • Error Detection, Gaussian Mixture Model, Kalman Filter, Manufacturing, Predictive Maintenance, Simulation
  • Engineering