Applications of AI in Reliability: Prognostics and Systems Health Management (Fall 2025 Graduate Course)

Prognostics and health management (PHM) is an enabling discipline consisting of technologies and methods to assess the reliability of a product in its actual life cycle conditions to determine the advent of failure and mitigate system risk. In recent years, PHM has emerged as a key technology that provides an early warning of failure, forecasts maintenance, and assesses the potential for life extensions. In the future, PHM will equip systems with the capability to assess their own real-time performance (self-cognizant health management and diagnostics) under actual usage conditions and adaptively enhance life cycle sustainment with risk-mitigation actions that virtually eliminate unplanned failures.

The application areas of PHM include aerospace structures and avionics, automobiles, civil structures, consumer and industrial products, defense infrastructure and medical equipment, and machine tools.

Some of the topics covered in this course include:

• Fundamentals of Prognostics and Health Management (PHM).
• Internet of Things, Big Data, and Sensors for PHM.
• Data Pre-processing (Data Cleansing, Feature Extraction, Feature Selection, Feature Learning).
• Physics-of-Failure Approach to Prognostics.
• Machine Learning and Artificial Intelligence for Anomaly Detection, Diagnostics, and Prognostics.
• Bayesian Statistics, Uncertainty Interpretation, Quantification, and Management in Prognostics.
• PHM Cost and Return on Investment.
• Valuation and Optimization of PHM-enabled Maintenance Decisions.
• Software Tools for PHM.
• Predictive Maintenance.
• PHM Applications in Industry.
• Challenges and Opportunities in PHM.

Completing this course will give you the fundamental knowledge and skills to develop and implement PHM concepts for aerospace, civil, electrical, electro-mechanical, electronic, and mechanical systems. Specifically, you will have the knowledge needed to:

• Assess methods for damage estimation of components and systems due to field loading conditions.
• Assess the cost and benefits of prognostic implementations.
• Develop algorithms and models for data processing and feature engineering.
• Develop novel methods for in-situ monitoring of products and systems in actual life-cycle conditions.
• Enable condition-based and predictive maintenance.
• Identify and analyze failure precursors based on failure mechanisms.
• Increase system availability through an extension of maintenance cycles and/or timely repair actions.
• Reduce the occurrence of no fault found (NFF).
• Account for the reduction in inspection costs, downtime, and inventory costs in the life-cycle costs of equipment.
• Understand data analytics (machine learning) methods used for anomaly detection, diagnostics, and prognostics.
• Understand the logistics and supply-chain challenges in PHM implementation.

For more information, contact Prof. Michael Pecht and Dr. Michael H. Azarian.

Frequently Asked Questions for Advanced Special Students

1. Criteria for admission:

There are three options to take UMD graduate courses without pursuing a graduate degree: Advanced Special Student Status, Visiting Graduate Student Status, or Golden Identification Cardholder Status (for Senior Citizens). Among these three options, the Advanced Special Student option is the most suitable option for most practicing engineers.

2. Applicants must hold a baccalaureate degree from a regionally accredited institution, with a cumulative 3.0 grade point average, and must satisfy ONE of the following requirements:

• Submit official transcripts covering all credits used in satisfying the baccalaureate degree requirements, OR
• If the applicant holds a master's or doctoral degree from a regionally accredited institution, submit an official transcript showing the award of a master's or doctoral degree, OR
• Achieve a score that places the applicant in the upper 50th percentile of appropriate national standardized aptitude examinations including the Graduate Record Examination Aptitude Test, the Miller Analogies Test, or the Graduate Management Admissions Test, (where different percentiles are possible, the Graduate School will determine which score is acceptable), OR
• Provide a strong letter of support from the Graduate Director of the program in which the applicant plans to take a course.

3. To apply, applicants must:

Submit a completed online application, which includes uploading official transcripts showing a bachelor’s degree from a regionally accredited institution and a personal statement. After successfully submitting the application, please send out an email to the Mechanical Engineering Graduate Office informing them that you have completed the application for taking the class.

4. Other information:

• If the interested prospective student is not a U.S. citizen or permanent resident, please contact International Student and Scholar Services to determine how to apply for Advanced Special Student status. U.S. citizens or permanent residents with international credentials can review the application process on the Non-Degree Admissions page and consult the full checklist here.
• To apply for Advanced Special Student status, international applicants may be required to submit results of English proficiency tests (TOEFL, IELTS or PTE) unless the Advanced Special Student applicant holds a degree from one of the waived countries on this page. If an Advanced Special Student is not a native English speaker and doesn’t have a degree from one of those countries, then he/she MUST submit an English proficiency score to be considered for admission.
• The DC Consortium students can also enroll in the class.

5. Fall 2025 application deadline (Advanced Special Student): The deadline for application is the first day of classes, September 2nd, 2025.

6. Course Registration:

Advanced Special Students should register to section RE01. If you have any questions, please contact the Mechanical Engineering Graduate Office. (megrad@umd.edu)