Chandrachur Bhattacharya

AI agents have proliferated in scientific applications as a means of accelerating discovery. Research infrastructure presents unique challenges in terms of building and deploying these applications; for instance diverse computing resources, federated authentication and access, restrictive networking policies, and variable up-times. These challenges are shaping how agentic applications for science are being constructed and deployed in practice. Specifically, in this work, we examine applications built using the Academyframework, a middleware for deploying agents on federated research infrastructure. We survey the architecture and methods employed in agentic applications across eleven different scientific applications, and include insights from interviewing the scientists who designed and built them. From these experiences we distill patterns for constructing future agentic science applications, and implications for the systems research community.

This technical brief makes use of the concept of symbolic time-series analysis (STSA) for identifying discrete states from the nonlinear time response of a chaotic dynamical system for model-free reinforcement learning (RL) control. Along this line, a projection-based method is adopted to construct probabilistic finite state automata (PFSA) for identification of the current state (i.e., operational regime) of the Lorenz system; and a simple Q-map-based (and model-free) RL control strategy is formulated to reach the target state from the (identified) current state. A synergistic combination of PFSA-based state identification and RL control is demonstrated by the simulation of a numeric model of the Lorenz system, which yields very satisfactory performance to reach the target states from the current states in real-time.

Fatigue damage detection and its classification in metallic materials are persistently challenging the structural health monitoring community. The mechanics of fatigue damage is difficult to analyze and is further complicated because of the presence of notches of different geometries. These notches act as possible crack-nucleation sites resulting in failure mechanisms that are drastically different from one another. Often, sensor-based tools are used to monitor and detect fatigue damage in critical metallic materials such as aluminum alloys. Through deep neural networks (DNNs), such a sensor-based approach can be ubiquitously extended for a variety of geometries as appropriate for different applications. To that end, this paper presents a DNN-based transfer learning framework that can be used to classify and detect fatigue damage across candidate notch geometries. The DNNs are built upon ultrasonic time-series data obtained during fatigue testing of Al7075-T6 specimens with two types of notch geometries, namely, a U-notch and a V-notch. The baseline U-notch DNN is shown to achieve an accuracy of 96.1% while the baseline V-notch DNN has an accuracy of 95.8%. Both baseline DNNs are, thereafter, subjected to a transfer learning process by keeping a certain number of layers frozen and retraining only the remaining layers with a small volume of data obtained from the other notch geometry. When a layer of the baseline U-notch DNN is retrained with just 10% of the total V-notch data, an accuracy above 90% is observed for fatigue damage detection of V-notch specimens. Similar results are also obtained when the baseline V-notch DNN is retrained and interrogated to detect damage for U-notch specimens. These results, in summary, demonstrate the data-thrifty quality of combining the concepts of transfer learning and DNN for fatigue damage detection in different geometries of specimens made of high-performance aluminum alloys.

The paper presents a coupled machine learning and pattern recognition algorithm to enable early-stage fatigue damage detection in aerospace-grade aluminum alloys. U- and V-notched Al7075-T6 specimens are instrumented with a pair of ultrasonic sensors and, thereafter, tested on an MTS apparatus integrated with a confocal microscope and a digital microscope. The confocal microscope is focused on the notch root of the specimens, whereas the digital microscope is focused on the side of the notch. Two features, viz., the crack opening displacement (COD) and the crack length, are extracted during the tests in addition to the ultrasonic signal data. These signal data are analyzed using a machine learning framework that is built upon a symbolic time-series algorithm. This framework is interrogated for crack detection in the crack coalescence (CC) regime defined by COD of ~3 μm and detected through the confocal microscope. Additionally, the framework is probed in the crack propagation (CP) regime characterized by a crack length of ~0.2 mm and detected via the digital microscope. For the CC regime, training accuracies of 79.82% and 81.94% are achieved, whereas testing accuracies of 68.18% and 74.12% are observed for the U- and V-notched specimens, respectively. For the CP regime, overall training accuracies of 88.3% and 91.85% are observed, and accordingly, testing accuracies of 81.94% and 85.62% are obtained for the U- and V-notched specimens, respectively. The results show that a combined machine learning and pattern recognition algorithm enables robust and reliable fatigue damage detection in aerospace structural components.

Transfer learning (TL) is a machine learning (ML) tool where the knowledge, acquired from a source domain, is “transferred” to perform a task in a target domain that has (to some extent) a similar setting. The underlying concept does not require the ML method to analyze a new problem from the beginning, and thereby both the learning time and the amount of required target-domain data are reduced for training. An example is the occurrence of thermoacoustic instability (TAI) in combustors, which may cause pressure oscillations, possibly leading to flame extinction as well as undesirable vibrations in the mechanical structures. In this situation, it is difficult to collect useful data from industrial combustion systems, due to the transient nature of TAI phenomena. A feasible solution is the usage of prototypes or emulators, like a Rijke tube, to produce largely similar phenomena. This paper proposes symbolic time-series analysis (STSA)-based TL, where the key idea is to develop a capability of discrimination between stable and unstable operations of a combustor, based on the time-series of pressure oscillations from a data source that contains sufficient information, even if it is not the target regime, and then transfer the learnt models to the target regime. The proposed STSA-based pattern classifier is trained on a previously validated numerical model of a Rijke-tube apparatus. The knowledge of this trained classifier is transferred to classify similar operational regimes in: (i) an experimental Rijke-tube apparatus and (ii) an experimental combustion system apparatus. Results of the proposed TL have been validated by comparison with those of two shallow neural networks (NNs)-based TL and another NN having an additional long short-term memory (LSTM) layer, which serve as benchmarks, in terms of classification accuracy and computational complexity.

Fatigue failure occurs ubiquitously in mechanical structures when they are subjected to cyclic loading well below the material’s yield stress. The tell-tale sign of a fatigue failure is the emergence of cracks at the internal or surface defects. In general, a machinery component has a finite fatigue life based on the number of cycles, it can sustain before a fracture occurs. However, the estimated life is generally conservative and often a large factor of safety is applied to make the component fail-safe. From the perspective of better utilization of a machinery component, it is, however, desirable to have maximum usage of the component without a catastrophic failure. It is, therefore, conducive to have a measure that can capture precursors to failure to facilitate active diagnosis of the machinery health. In this study, a precursor detection method is developed upon modifications of probabilistic finite state automata (PFSA). The efficacy of the proposed method is demonstrated on cold-rolled AL7075-T6 notched specimens in a computer-instrumented and computer-controlled fatigue testing apparatus. The results show that the proposed method is capable of detecting the emergence of cracks (at ∼95% accuracy) and also can capture precursors with good fidelity.

Natural circulation loop (NCL) systems are buoyancy-driven heat exchangers that are used in various industrial applications. The concept of passive heat exchange in NCL systems is attractive, because there is no need for an externally driven equipment (e.g., a pump) to maintain the fluid circulation. However, relying on buoyancy as the sole driving force may lead to several potential difficulties, one of which is generation of (possibly) time-varying nonlinearities in the dynamical system, where a difference in the time scales of heat transfer and fluid flow causes the flow to change from a steady-state regime to either an oscillatory regime or a flow-reversal regime, both of which are undesirable. In this paper, an algorithm is developed using tools of symbolic time-series analysis (e.g., probabilistic finite state automata (PFSA)) for the purpose of identifying selected regimes of operation in NCL systems using only data from the early transient operation, where the underlying principle is built upon the concept of pattern classification from measurements of fluid-flow dynamics. The proposed method is shown to be capable of identifying the current regime of operation from the initial time response under a given set of operational parameters. The efficacy of regime classification is demonstrated by testing on two datasets, generated from numerical simulation of a MATLAB SimuLink model that has previously been validated with experimental data. The results of the proposed PFSA-based classification are compared with those of a hidden Markov model (HMM) that serves as the baseline.

Natural circulation loop (NCL) systems are buoyancy-driven heat exchangers that are used in various industrial applications. The concept of passive heat exchange in NCL systems is attractive, because there is no need for an externally driven equipment (e.g., a pump) to maintain the fluid circulation. However, relying on buoyancy as the sole driving force may lead to several potential difficulties, one of which is generation of (possibly) time-varying nonlinearities in the dynamical system, where a difference in the time scales of heat transfer and fluid flow causes the flow to change from a steady-state regime to either an oscillatory regime or a flow-reversal regime, both of which are undesirable. In this paper, tools of symbolic time series analysis (e.g., probabilistic finite state automata (PFSA)) are proposed to identify selected regimes of operation in NCL systems, where the underlying principle is built upon the concept of pattern classification from measurements of fluid-flow dynamics. The proposed method is shown to be capable of identifying the current regime of operation from the initial time response under a given set of operational parameters. The efficacy of regime classification is demonstrated by testing on two data sets, generated from numerical simulation of a MATLAB SimuLink model that has previously been validated with experimental data. The results of the proposed PFSA-based classification are compared with those of a hidden Markov model (HMM) that serves as the baseline.

Chaotic dynamical systems are essentially nonlinear and are highly sensitive to variations in initial conditions and process parameters. Chaos may appear both in natural (e.g., heartbeat rhythms and weather fluctuations) and human-engineered (e.g., thermo-fluid, urban traffic, and stock market) systems. For prediction and control of such systems, it is often necessary to be able to distinguish between non-chaotic and chaotic behavior; several methods exist to detect the presence (or absence) of chaos, specially in noisy signals. A dynamical system may exhibit multiple chaotic regimes, and apparently, there exist no methods, reported in open literature, to classify these regimes individually. This paper demonstrates an application of standard hidden Markov modeling (HMM), which is a commonly used supervised method, as a technique to classify multiple regimes from a time series of dynamical systems, where classified regimes could be chaotic or non-chaotic. The proposed HMM-based method of regime classification has been tested using numerical data obtained from several well-known chaotic dynamical systems (e.g., Hénon, forced Duffing, Rössler, and Lorenz attractor). It is apparently well-suited to serve as a bench mark for the development of alternative data-driven methods to enhance the performance (e.g., accuracy and computational speed) of regime classification in chaotic dynamical systems.