Brett Sicard
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Brett Sicard has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Stephen Andrew Gadsden
Department of Mechanical Engineering, McMaster University, Hamilton, ON, Canada
5 shared publications - Yuandi Wu
Intelligent and Cognitive Engineering Laboratory, McMaster University, Hamilton, ON L8S 4L8, Canada
3 shared publications - Alex McCafferty-Leroux
Department of Mechanical Engineering, McMaster University, Hamilton, ON, Canada
1 shared publication - Ethan Hughey
Global Manufacturing Engineering, Ford Motor Company, Livonia, MI, USA
1 shared publication - Mohammad Al-Shabi
University of Sharjah
1 shared publication - Patrick Kosierb
McMaster University, 1280 Main Street West
1 shared publication
Latest Publications
- 30 January 2025
- Published by Springer Nature
- p. 165-181
Parameter Identification in Magnetorheological Dampers via Physics-Informed Neural Networks
- 30 January 2025
- Published by Springer Nature
- p. 165-181
Parameter Identification in Magnetorheological Dampers via Physics-Informed Neural Networks
- 25 January 2025
- Published by Springer Nature
- p. 539-555
Robust Estimation Strategies for a Nonlinear Satellite System
- 25 January 2025
- Published by Springer Nature
- p. 539-555
Robust Estimation Strategies for a Nonlinear Satellite System
- Top Cited PapersOpen Access
- 5 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Physics-informed machine learning: A comprehensive review on applications in anomaly detection and condition monitoring
- 5 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Top Cited PapersOpen AccessPhysics-informed machine learning: A comprehensive review on applications in anomaly detection and condition monitoring
- Open Access
A Review of Physics-Informed Machine Learning Methods with Applications to Condition Monitoring and Anomaly Detection
This study presents a comprehensive overview of PIML techniques in the context of condition monitoring. The central concept driving PIML is the incorporation of known physical laws and constraints into machine learning algorithms, enabling them to learn from available data while remaining consistent with physical principles. Through fusing domain knowledge with data-driven learning, PIML methods offer enhanced accuracy and interpretability in comparison to purely data-driven approaches. In this comprehensive survey, detailed examinations are performed with regard to the methodology by which known physical principles are integrated within machine learning frameworks, as well as their suitability for specific tasks within condition monitoring. Incorporation of physical knowledge into the ML model may be realized in a variety of methods, with each having its unique advantages and drawbacks. The distinct advantages and limitations of each methodology for the integration of physics within data-driven models are detailed, considering factors such as computational efficiency, model interpretability, and generalizability to different systems in condition monitoring and fault detection. Several case studies and works of literature utilizing this emerging concept are presented to demonstrate the efficacy of PIML in condition monitoring applications. From the literature reviewed, the versatility and potential of PIML in condition monitoring may be demonstrated. Novel PIML methods offer an innovative solution for addressing the complexities of condition monitoring and associated challenges. This comprehensive survey helps form the foundation for future work in the field. As the technology continues to advance, PIML is expected to play a crucial role in enhancing maintenance strategies, system reliability, and overall operational efficiency in engineering systems.
Open AccessA Review of Physics-Informed Machine Learning Methods with Applications to Condition Monitoring and Anomaly Detection
This study presents a comprehensive overview of PIML techniques in the context of condition monitoring. The central concept driving PIML is the incorporation of known physical laws and constraints into machine learning algorithms, enabling them to learn from available data while remaining consistent with physical principles. Through fusing domain knowledge with data-driven learning, PIML methods offer enhanced accuracy and interpretability in comparison to purely data-driven approaches. In this comprehensive survey, detailed examinations are performed with regard to the methodology by which known physical principles are integrated within machine learning frameworks, as well as their suitability for specific tasks within condition monitoring. Incorporation of physical knowledge into the ML model may be realized in a variety of methods, with each having its unique advantages and drawbacks. The distinct advantages and limitations of each methodology for the integration of physics within data-driven models are detailed, considering factors such as computational efficiency, model interpretability, and generalizability to different systems in condition monitoring and fault detection. Several case studies and works of literature utilizing this emerging concept are presented to demonstrate the efficacy of PIML in condition monitoring applications. From the literature reviewed, the versatility and potential of PIML in condition monitoring may be demonstrated. Novel PIML methods offer an innovative solution for addressing the complexities of condition monitoring and associated challenges. This comprehensive survey helps form the foundation for future work in the field. As the technology continues to advance, PIML is expected to play a crucial role in enhancing maintenance strategies, system reliability, and overall operational efficiency in engineering systems.
- Open Access
- 4 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Instrumentation and Measurement
- Vol. 2, 1-12
Preload Loss Detection in a Ball Screw System Using Interacting Models
Ball screw preload is an important factor in maintaining repeatably, rigidity, and in reducing or eliminating backlash in feed drive systems. Ball screw feeds drives are used in computer numerical control (CNC) machine tools to manufacture high quality, precision parts. Many fault detection and condition monitoring methods have been proposed for measuring and detecting loss of preload, however, most of these methods require external sensors. Ideally, sensors, measurements, and methods integral to a CNC machine tool could be used to eliminate the extra cost and complexity of external sensors. A sensor-less method of estimating levels of preload using the mode probability of interacting multiple models (IMM) is proposed. This method calculates a weighted sum which utilizes the mode probability of models representing different levels of preload, along with an activation function and weighing factor, to estimate the current level of preload. Unlike many other methods used for detecting levels of preload, this method requires only a system model and data collected by the CNC systems, while requiring no external sensors. The proposed method was shown to be robust and able to accurately and quickly predict preload levels under many different testing conditions. This method demonstrated a high degree of prediction accuracy (95%) which is comparable to, or better than other methods in the literature. In addition to being a novel method for preload detection, this work is also a novel implementation of IMM for fault detection, as it has not yet been applied to fault detection in feed drives.
- 4 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Instrumentation and Measurement
- Vol. 2, 1-12
Open AccessPreload Loss Detection in a Ball Screw System Using Interacting Models
Ball screw preload is an important factor in maintaining repeatably, rigidity, and in reducing or eliminating backlash in feed drive systems. Ball screw feeds drives are used in computer numerical control (CNC) machine tools to manufacture high quality, precision parts. Many fault detection and condition monitoring methods have been proposed for measuring and detecting loss of preload, however, most of these methods require external sensors. Ideally, sensors, measurements, and methods integral to a CNC machine tool could be used to eliminate the extra cost and complexity of external sensors. A sensor-less method of estimating levels of preload using the mode probability of interacting multiple models (IMM) is proposed. This method calculates a weighted sum which utilizes the mode probability of models representing different levels of preload, along with an activation function and weighing factor, to estimate the current level of preload. Unlike many other methods used for detecting levels of preload, this method requires only a system model and data collected by the CNC systems, while requiring no external sensors. The proposed method was shown to be robust and able to accurately and quickly predict preload levels under many different testing conditions. This method demonstrated a high degree of prediction accuracy (95%) which is comparable to, or better than other methods in the literature. In addition to being a novel method for preload detection, this work is also a novel implementation of IMM for fault detection, as it has not yet been applied to fault detection in feed drives.