There is a growing need for low-cost monitoring with online sensing technologies to maintain grid reliability and uptime. Here we present an innovative low-cost, embedded optical sensing technology initially focused on transformers that was developed and demonstrated at a major electric utility, Con Edison. A version of it that can be retrofitted onto existing transformers in the field was also developed. Two new 500 kVA distribution network transformers were built with embedded fiber-optic (FO) sensors and qualified per industry standards. Vibration, temperature, and corrosion were key parameters monitored. The first transformer with embedded FO sensors was installed at a Con Edison facility and monitored at our team's office. The second one was installed in an urban street-side underground location with online data processing/feature extraction algorithms and monitored through a wireless router. Additionally, an older transformer was also retrofitted. Data analysis was done on these transformers showing promising correlations with their corresponding loading cycles. Additionally, key events such as the transformer primary-side energizing, and other events were detected. Overall, the technology was demonstrated over 6 months across the 3 transformers instrumented with promising results. Thus, it has the potential to enable predictive grid maintenance for transformers and other grid assets.

Utilities across the world are wrestling with evolving market dynamics, population growth and climate change. Distributed Energy Resources (DERs) such as solar photovoltaics, distributed generators and energy storage systems are becoming important parts of the U.S. energy mix. These factors are driving an increasing need for low-cost grid asset monitoring. Aside from being costly, traditional utility monitoring systems are not sufficiently robust and do not provide real-time visibility into the condition of grid assets such as transformers. Lack of accurate real-time measurements on performance has resulted in the use of lagging indicators, such as oil sample analysis. To address this need, an innovative embedded optical sensing technology, Transformer Real-time Assessment Intelligent System (TRANSENSOR) was developed, validated and demonstrated in this project. To date, TRANSENSOR has focused on transformers but is extendable to other grid assets. In addition to the technology being embedded into new transformers during manufacturing, a retrofit configuration that can be installed on existing transformers in the field was also developed. It is anticipated that the ability to retrofit existing transformers will help accelerate adoption of the underlying TRANSENSOR technology. Phase 1 of the project focused on laboratory development and qualification of the technology. Following iterations and exploration of relevant optical sensing modalities and multiplexed configurations of interest for the transformer environment, an effective candidate configuration was agreed upon, down-selected and custom-designed for embedding into General Electric (GE) network transformers. Two new GE 500 kilovolt ampere (kVA), 27 kilovolt (kV) distribution network transformers were built with embedded fiber-optic (FO) sensors and successfully qualified per industry standards at GE’s Shreveport, Louisiana facility during Phase 1 of the project. Following the successful completion of Phase 1, the team proceeded to Phase 2, which focused on a field demonstration of the technology. Over Phase 2, the first new GE transformer built with embedded fiber-optic sensors was installed in an above-ground cage and connected to the grid at Con Edison’s Astoria facility. A second transformer equipped with TRANSENSOR was installed in an underground vault. Additionally, an older (1982 year model) GE transformer in an above-ground cage was retrofitted with fiber- optic sensors and reconnected to the grid at ConEd’s facility. Analysis of data acquired from the sensors showed interesting correlations with transformer loading. Additionally, key events such as transformer low-voltage network connection, primary-side energizing, and a pressure loss event from an oil sampling were detected by the TRANSENSOR system. Online data processing/feature extraction algorithms for the second transformer in the underground vault detected key features and event alerts that were transmitted through a wireless 4G connection. The remote deployment concept showed promising results with data collection running for a total of 8 months across the three (3) GE transformers instrumented for the Phase 2 field demonstration. This sets the stage well for further development and commercialization.

Being able to quickly detect anomalies and reason about their root causes in critical manufacturing systems can significantly reduce the analysis time to bring operations back online, thus reducing expensive unplanned downtime. Machine learning-based anomaly detection approaches often need significant amounts of labeled data for training and are challenging to scale for manufacturing deployments. A robust blended system dynamics and discrete event simulation physics-based modeling methodology is proposed for the task of automated anomaly detection. The blended model consists of discrete event simulation (DES) components for the discrete manufacturing process modeling, and system dynamics (SD) components for continuous variables. The methodology strikes a balance between the computational overhead for online monitoring and the level of details required to perform anomaly detection tasks. The implementation of models takes an object-oriented approach, allowing multiple components of a smart factory to be robustly described in a modular, extendable and reconfigurable manner. The proposed methodology is applied to and validated by data collected from a real commercial manufacturing plant. A production line is modeled with DES components and heat transfer is modeled with SD. The blended model is then utilized for anomaly detection. It is demonstrated that the model-based approach is effective not only for detecting but also explaining particular types of anomalies in a commercial discrete manufacturing system.

Health monitoring of railway systems is critical for detecting incipient faults or degradation. In order to reliably do so, an effective monitoring system must be deployed to provide railroad operators with the highest level of operational awareness and safety. In this study, we explore the use of Fiber Bragg Gratings (FBGs) and a highresolution, low-cost optical readout developed at PARC to interrogate the acoustic emissions generated by a train-rail system. The proposed sensing configuration can allow for a scalable, low-cost, field-deployable solution that could enable near real-time monitoring of tracks and wheels. A proof-of-concept was demonstrated with a G-scale train-rail system with FBGs embedded within the ballast layer. Using PARC’s wavelength shift detector, the acoustic emission signal was resolved in both the time and frequency domain. The findings of this work show promise that this could be a viable solution to deploy an optically-based health monitoring system for railroads.

Robots and other similar automation machines have been widely used in various industries, such as automotive and semiconductor industries to improve productivity, quality, and safety in manufacturing processes. However, an unforeseen robot shutdown has the potential to cause an interruption in the entire production line, resulting in significant unplanned downtime, economic, production losses, and even work injuries. Thus, it is of high interest to detect incipient faults in industrial robots before they totally shut down or otherwise fail. A challenge for fault detection in industrial robots is the difficulty to obtain sufficient labeled training data under normal and abnormal health conditions. Thus, unsupervised machine learning algorithms are desired. In this work, a Gaussian mixture model-based unsupervised fault detection framework is proposed to effectively detect the faults in industrial robots using current signals. Signal preprocessing is first performed to clean the measured raw current signals. Then, motion-insensitive fault features chosen based on a system physics model that can reflect the deterioration of the industrial robots are extracted and fed into unsupervised learning algorithms for effective fault detection. The effectiveness and high accuracy of the proposed method are validated by experimental data obtained from industrial robot systems.

Within the State of Victoria there are more than 2,600 rail-related bridges and approximately 6,000 arterial road structures. There are various methods for maintaining these assets. Most approaches use in-person inspections conducted at predefined intervals as determined by the risk profile. While this method of inspection and maintenance is reliable, there are variables and potential risks negatively effecting bridge portfolio management, including meeting safety and security requirements while maximizing the lifetime of the asset. Some examples include availability of skilled inspectors, potential for human error in the performance and analysis of inspections, potential for invisible structural defects to go undetected and unexpectedly worsen between inspections, and unreported traffic incidents that impact structural integrity.

Under a collaboration led and funded by VicTrack, VicRoads, and other Victorian State agencies with funding from the Victoria Public Sector Innovation Fund (PSIF) in Australia, the Palo Alto Research Center (PARC) and University of Melbourne (UoM) are developing Fibridge (overseen by a Project Governance Board chaired by VicTrack), a fiber-optic (FO) smart monitoring system for bridges to enable predictive maintenance using the industrial internet of things (IIoT). The system uses FO sensors attached to bridge structures to accurately measure and estimate parameters indicative of bridge state online, such as structural strain, thermal response, bending moments, shear/impact loads, and corrosion. Fibridge leverages PARC’s low-cost, highresolution, compact wavelength-shift detection technology and intelligent algorithms in combination with UoM and the stakeholder team’s structural engineering know-how to enable effective real-time monitoring, performance management, better reliability, improved safety, and optimized bridge design. While Fibridge is initially targeting road and rail bridges, it will be extendable to other structures with similar maintenance/monitoring pain points. Here we present an overview of the project, enabling technologies, and summarize key results on vehicle load and structural response features detectable, bridge state estimation algorithm development, low-cost optical readout development, and validation test results. An initial proof-of-concept demonstration on a VicRoads highway bridge in Melbourne being monitored with FO sensors has shown promise thus far. At this stage, the technology is being scaled up towards an extended pilot trial on multiple rail, road, and transit bridges in Victoria. A business case for Fibridge to enable cost-effective maintenance is also summarized.

A key challenge hindering the mass adoption of Lithium-ion and other next-gen chemistries in advanced battery applications such as hybrid/electric vehicles (xEVs) has been management of their functional performance for more effective battery utilization and control over their life. Contemporary battery management systems (BMS) reliant on monitoring external parameters such as voltage and current to ensure safe battery operation with the required performance usually result in overdesign and inefficient use of capacity. More informative embedded sensors are desirable for internal cell state monitoring, which could provide accurate state-of-charge (SOC) and state-of-health (SOH) estimates and early failure indicators. Here we present a promising new embedded sensing option developed by our team for cell monitoring, fiber-optic sensors. High-performance large-format pouch cells with embedded fiber-optic sensors were fabricated. The first of this two-part paper focuses on the embedding method details and performance of these cells. The seal integrity, capacity retention, cycle life, compatibility with existing module designs, and mass-volume cost estimates indicate their suitability for xEV and other advanced battery applications. The second part of the paper focuses on the internal strain and temperature signals obtained from these sensors under various conditions and their utility for high-accuracy cell state estimation algorithms.