Fault Isolation for the Ink Deposition Process in High-End Industrial Printers

TL;DR

The paper addresses reliable fault diagnosis in ink channels of high-end industrial printers by proposing a hybrid fault detection and isolation (FDI) approach that combines a model-based fault detection filter with data-driven fault isolation classifiers. It models the ink channel dynamics with a four-state system and six fault variants, and designs an FD filter in the Laplace domain that accounts for non-simultaneous actuation and sensing; faults are detected by energy thresholds on a residual $R(s)$. For isolation, offline-trained LR or KNN classifiers operate on the residual to identify the most probable fault, enabling selective mitigation. Experimental validation on Canon printers shows superior fault detection rates and substantially improved fault isolation accuracy compared with a state-of-the-practice, highlighting the method’s practicality in scarce-data scenarios and its robustness to measurement limitations. The approach provides a scalable, physics-informed framework for early fault detection and precise fault isolation in large-scale ink channel networks, with potential impacts on print quality, waste reduction, and maintenance effectiveness.

Abstract

This paper presents a mathematical framework for modeling the dynamic effects of three fault categories and six fault variants in the ink channels of high-end industrial printers. It also introduces a hybrid approach that combines model-based and data-based methods to detect and isolate these faults effectively. A key challenge in these systems is that the same piezo device is used for actuation (generating ink droplets) and for sensing and, as a consequence, sensing is only available when there is no actuation. The proposed Fault Detection (FD) filter, based on the healthy model, uses the piezo self-sensing signal to generate a residual, while taking the above challenge into account. The system is flagged as faulty if the residual energy exceeds a threshold. Fault Isolation (FI) is achieved through linear regression or a k-nearest neighbors approach to identify the most likely fault category and variant. The resulting hybrid Fault Detection and Isolation (FDI) method overcomes traditional limitations of model-based methods by isolating different types of faults affecting the same entries (i.e., equations) in the ink channel dynamics. Moreover, it is shown to outperform purely data-driven methods in fault isolation, especially when data is scarce. Experimental validation demonstrates superior FDI performance compared to state-of-the-art methods.

Figures (6)

• Figure 1: Decomposition of the printer where each component shown is smaller than and inside of the component to its left.
• Figure 2: Typical input (actuation) signal and corresponding output (sensing) signal, with the output starting after the completion of the input at time $t_a$.
• Figure 3: Overview of the proposed FDI scheme.
• Figure 4: Schematic overview of the offline training (design) and online application of the FI filter.
• Figure 5: Examples of sensing signals $y$ for simulated fault categories (here $t_a=0$).