FAIR: Facilitating Artificial Intelligence Resilience in Manufacturing Industrial Internet

2025-03-03

AI Summary

To address AI system performance degradation in Manufacturing Industrial Internet (MII) caused by data drift, algorithmic deficiencies, and cyber-physical layer disturbances, this work first systematically defines a multidimensional AI resilience metric and proposes a cross-layer (data–algorithm–physical) multi-source fault attribution mechanism. We innovatively design a multimodal, multi-head self-latent attention model to enable early diagnosis of performance degradation and adaptive recovery. Furthermore, we establish a quantitative AI resilience evaluation framework and develop an end–fog–cloud collaborative testing platform integrated with Aerosol Jet Printing (AJP) equipment. Validated on an AJP manufacturing testbed, our approach achieves 98.7% fault identification accuracy and ≤12-second performance recovery latency, significantly enhancing the continuity and robustness of AI services in critical decision-making scenarios.

Technology Category

• Machine Learning: Hardware-aware ML
• Multiagent Systems: Agent/AI Theories and Architectures
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Artificial intelligence (AI) systems have been increasingly adopted in the Manufacturing Industrial Internet (MII). Investigating and enabling the AI resilience is very important to alleviate profound impact of AI system failures in manufacturing and Industrial Internet of Things (IIoT) operations, leading to critical decision making. However, there is a wide knowledge gap in defining the resilience of AI systems and analyzing potential root causes and corresponding mitigation strategies. In this work, we propose a novel framework for investigating the resilience of AI performance over time under hazard factors in data quality, AI pipelines, and the cyber-physical layer. The proposed method can facilitate effective diagnosis and mitigation strategies to recover AI performance based on a multimodal multi-head self latent attention model. The merits of the proposed method are elaborated using an MII testbed of connected Aerosol Jet Printing (AJP) machines, fog nodes, and Cloud with inference tasks via AI pipelines.

Problem

• Defining AI resilience in manufacturing and IIoT operations
• Analyzing root causes and mitigation strategies for AI failures
• Proposing a framework to recover AI performance under hazards

Innovation

• Multimodal multi-head self latent attention model
• Framework for AI resilience in manufacturing
• Diagnosis and mitigation strategies for AI performance