skip to main content

Title: Physics-Informed Machine Learning for Accelerated Testing of Roll-to-Roll Printed Sensors
Roll-to-roll printing has significantly shortened the time from design to production of sensors and IoT devices, while being cost-effective for mass production. But due to less manufacturing tolerance controls available, properties such as sensor thickness, composition, roughness, etc., cannot be precisely controlled. Since these properties likely affect the sensor behavior, roll-to-roll printed sensors require validation testing before they can be deployed in the field. In this work, we improve the testing of Nitrate sensors that need to be calibrated in a solution of known Nitrate concentration for around 1–2 days. To accelerate this process, we observe the initial behavior of the sensors for a few hours, and use a physics-informed machine learning method to predict their measurements 24 hours in the future, thus saving valuable time and testing resources. Due to the variability in roll-to-roll printing, this prediction task requires models that are robust to changes in properties of the new test sensors. We show that existing methods fail at this task and describe a physics-informed machine learning method that improves the prediction robustness to different testing conditions (≈ 1.7× lower in real-world data and ≈ 5× lower in synthetic data when compared with the current state-of-the-art physics-informed machine learning method).  more » « less
Award ID(s):
1943364 1918483
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Date Published:
Journal Name:
International Manufacturing Science and Engineering Conference
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    In the modern industrial setting, there is an increasing demand for all types of sensors. The demand for both the quantity and quality of sensors is increasing annually. Our research focuses on thin-film nitrate sensors in particular, and it seeks to provide a robust method to monitor the quality of the sensors while reducing the cost of production.

    We are researching an image-based machine learning method to allow for real-time quality assessment of every sensor in the manufacturing pipeline. It opens up the possibility of real-time production parameter adjustments to enhance sensor performance. This technology has the potential to significantly reduce the cost of quality control and improve sensor quality at the same time. Previous research has proven that the texture of the topical layer (ion-selective membrane (ISM) layer) of the sensor directly correlates with the performance of the sensor. Our method seeks to use the correlation so established to train a learning-based system to predict the performance of any given sensor from a still photo of the sensor active region, i.e. the ISM. This will allow for the real-time assessment of every sensor instead of sample testing. Random sample testing is both costly in time and labor, and therefore, it does not account for all of the individual sensors.

    Sensor measurement is a crucial portion of the data collection process. To measure the performance of the sensors, the sensors are taken to a specialized lab to be measured for performance. During the measurement process, noise and error are unavoidable; therefore, we generated credibility data based on the performance data to show the reliability of each sensor performance signal at each sample time.

    In this paper, we propose a machine learning based method to predict sensor performance using image features extracted from the non-contact sensor images guided by the credibility data. This will eliminate the need to test every sensor as it is manufactured, which is not practical in a high-speed roll-to-roll setting, thus truely enabling a certify as built framework.

    more » « less
  2. Abstract

    Roll-to-Roll (R2R) printing techniques are promising for high-volume continuous production of substrate-based products, as opposed to sheet-to-sheet (S2S) approach suited for low-volume work. However, meeting the tight alignment tolerance requirements of additive multi-layer printed electronics specified by device resolution that is usually at micrometer scale has become a major challenge in R2R flexible electronics printing, preventing the fabrication technology from being transferred from conventional S2S to high-speed R2R production. Print registration in a R2R process is to align successive print patterns on the flexible substrate and to ensure quality printed devices through effective control of various process variables. Conventional model-based control methods require an accurate web-handling dynamic model and real-time tension measurements to ensure control laws can be faithfully derived. For complex multistage R2R systems, physics-based state-space models are difficult to derive, and real-time tension measurements are not always acquirable. In this paper, we present a novel data-driven model predictive control (DD-MPC) method to minimize the multistage register errors effectively. We show that the DD-MPC can handle multi-input and multi-output systems and obtain the plant model from sensor data via an Eigensystem Realization Algorithm (ERA) and Observer Kalman filter identification (OKID) system identification method. In addition, the proposed control scheme works for systems with partially measurable system states.

    more » « less
  3. Concrete exhibits time-dependent long-term behavior driven by creep and shrinkage. These rheological effects are difficult to predict due to their stochastic nature and dependence on loading history. Existing empirical models used to predict rheological effects are fitted to databases composed largely of laboratory tests of limited time span and that do not capture differential rheological effects. A numerical model is typically required for application of empirical constitutive models to real structures. Notwithstanding this, the optimal parameters for the laboratory databases are not necessarily ideal for a specific structure. Data-driven approaches using structural health monitoring data have shown promise towards accurate prediction of long-term time-dependent behavior in concrete structures, but current approaches require different model parameters for each sensor and do not leverage geometry and loading. In this work, a physics-informed data-driven approach for long-term prediction of 2D normal strain field in prestressed concrete structures is introduced. The method employs a simplified analytical model of the structure, a data-driven model for prediction of the temperature field, and embedding of neural networks into rheological time-functions. In contrast to previous approaches, the model is trained on multiple sensors at once and enables the estimation of the strain evolution at any point of interest in the longitudinal section of the structure, capturing differential rheological effects. 
    more » « less
  4. null (Ed.)
    Modern digital manufacturing processes, such as additive manufacturing, are cyber-physical in nature and utilize complex, process-specific simulations for both design and manufacturing. Although computational simulations can be used to optimize these complex processes, they can take hours or days--an unreasonable cost for engineering teams leveraging iterative design processes. Hence, more rapid computational methods are necessary in areas where computation time presents a limiting factor. When existing data from historical examples is plentiful and reliable, supervised machine learning can be used to create surrogate models that can be evaluated orders of magnitude more rapidly than comparable finite element approaches. However, for applications that necessitate computationally- intensive simulations, even generating the training data necessary to train a supervised machine learning model can pose a significant barrier. Unsupervised methods, such as physics- informed neural networks, offer a shortcut in cases where training data is scarce or prohibitive. These novel neural networks are trained without the use of potentially expensive labels. Instead, physical principles are encoded directly into the loss function. This method substantially reduces the time required to develop a training dataset, while still achieving the evaluation speed that is typical of supervised machine learning surrogate models. We propose a new method for stochastically training and testing a convolutional physics-informed neural network using the transient 3D heat equation- to model temperature throughout a solid object over time. We demonstrate this approach by applying it to a transient thermal analysis model of the powder bed fusion manufacturing process. 
    more » « less
  5. Paper-based analytical devices (PADs) offer a low-cost, user-friendly platform for rapid point-of-use testing. Without scalable fabrication methods, however, few PADs make it out of the academic laboratory and into the hands of end users. Previously, wax printing was considered an ideal PAD fabrication method, but given that wax printers are no longer commercially available, alternatives are needed. Here, we present one such alternative: the air-gap PAD. Air-gap PADs consist of hydrophilic paper test zones, separated by “air gaps” and affixed to a hydrophobic backing with double-sided adhesive. The primary appeal of this design is its compatibility with roll-to-roll equipment for large-scale manufacturing. In this study, we examine design considerations for air-gap PADs, compare the performance of wax-printed and air-gap PADs, and report on a pilot-scale roll-to-roll production run of air-gap PADs in partnership with a commercial test-strip manufacturer. Air-gap devices performed comparably to their wax-printed counterparts in Washburn flow experiments, a paper-based titration, and a 12-lane pharmaceutical screening device. Using roll-to-roll manufacturing, we produced 2700 feet of air-gap PADs for as little as $0.03 per PAD. 
    more » « less