Active Learning For Repairable Hardware Systems With Partial Coverage

2025-03-20

AI Summary

Inferring reliability parameters for repairable hardware systems is challenging under constrained budgets and maintenance cycles, incomplete diagnostic test coverage, and subsystem aging. Method: This paper proposes the first active learning framework based on relaxed Mixed-Integer Semidefinite Programming (MISDP) tailored to partial-coverage scenarios. It jointly models Diagnostic Coverage (DC) and the geometric structure of the Fisher Information Matrix (FIM), enabling simultaneous optimization of diagnostic utility and statistical information gain. A simulation-based active learning evaluation paradigm is introduced. Results: Across 6,000 experiments, the framework achieves top average rank in AUC (area under the ATEER/MSE curve), significantly outperforming entropy-based and multiple heuristic acquisition functions (Friedman test, α = 0.05). It provides a scalable, interpretable solution for hardware reliability inference under resource constraints.

Technology Category

• Machine Learning: Active Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Identifying the optimal diagnostic test and hardware system instance to infer reliability characteristics using field data is challenging, especially when constrained by fixed budgets and minimal maintenance cycles. Active Learning (AL) has shown promise for parameter inference with limited data and budget constraints in machine learning/deep learning tasks. However, AL for reliability model parameter inference remains underexplored for repairable hardware systems. It requires specialized AL Acquisition Functions (AFs) that consider hardware aging and the fact that a hardware system consists of multiple sub-systems, which may undergo only partial testing during a given diagnostic test. To address these challenges, we propose a relaxed Mixed Integer Semidefinite Program (MISDP) AL AF that incorporates Diagnostic Coverage (DC), Fisher Information Matrices (FIMs), and diagnostic testing budgets. Furthermore, we design empirical-based simulation experiments focusing on two diagnostic testing scenarios: (1) partial tests of a hardware system with overlapping subsystem coverage, and (2) partial tests where one diagnostic test fully subsumes the subsystem coverage of another. We evaluate our proposed approach against the most widely used AL AF in the literature (entropy), as well as several intuitive AL AFs tailored for reliability model parameter inference. Our proposed AF ranked best on average among the alternative AFs across 6,000 experimental configurations, with respect to Area Under the Curve (AUC) of the Absolute Total Expected Event Error (ATEER) and Mean Squared Error (MSE) curves, with statistical significance calculated at a 0.05 alpha level using a Friedman hypothesis test.

Problem

• Optimizing diagnostic tests for repairable hardware systems with partial coverage.
• Developing Active Learning methods for reliability model parameter inference.
• Evaluating new Acquisition Functions against traditional methods in reliability testing.

Innovation

• Relaxed Mixed Integer Semidefinite Program AL AF
• Incorporates Diagnostic Coverage and Fisher Information
• Empirical simulation for partial diagnostic testing scenarios