index.json

[{"authors":["admin"],"categories":null,"content":"I’m an Applied Scientist and AI Engineer with over 15 years of R\u0026amp;D experience in software for consumer and industrial applications. I’ve developed and deployed AI solutions, empowering data science teams to build and visualize multiple analytics models and techniques at scale, deployed to diverse cloud services. With a BSc in Computer Science and Ph.D. in Mechanical Engineering, I’ve created novel methods combining physics-based knowledge with Deep Learning frameworks creating hybrid AI solutions. In my research in collaboration with the Diagnostics and Prognostics lab at NASA Ames, we enabled fast and accurate monitoring of Lithium-ion batteries with probabilistic hybrid machine learning.\n","date":-62135596800,"expirydate":-62135596800,"kind":"taxonomy","lang":"en","lastmod":-62135596800,"objectID":"2525497d367e79493fd32b198b28f040","permalink":"/authors/admin/","publishdate":"0001-01-01T00:00:00Z","relpermalink":"/authors/admin/","section":"authors","summary":"I’m an Applied Scientist and AI Engineer with over 15 years of R\u0026amp;D experience in software for consumer and industrial applications. I’ve developed and deployed AI solutions, empowering data science teams to build and visualize multiple analytics models and techniques at scale, deployed to diverse cloud services. With a BSc in Computer Science and Ph.D. in Mechanical Engineering, I’ve created novel methods combining physics-based knowledge with Deep Learning frameworks creating hybrid AI solutions.","tags":null,"title":"Renato G. Nascimento","type":"authors"},{"authors":["Renato G. Nascimento","Felipe A. C. Viana","Matteo Corbetta","Chetan S. Kulkarni"],"categories":null,"content":"","date":1632268800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1632268800,"objectID":"e84de9484407157a5fd6202854b19b19","permalink":"/publication/2021-jps-nascimento-et-al/","publishdate":"2021-09-22T18:31:57.200253Z","relpermalink":"/publication/2021-jps-nascimento-et-al/","section":"publication","summary":"Lithium-ion batteries are commonly used to power unmanned aircraft vehicles (UAVs). The ability to model and forecast remaining useful life of these batteries enables UAV reliability assurance. Building principled accurate models is challenging due to the complex electrochemistry that governs battery operation. Alternatively, reduced order models have the advantage of capturing the overall behavior of battery discharge, although they suffer from simplifications and residual discrepancy. This paper presents a hybrid modeling approach that directly implements physics within deep neural networks. While most of the input–output relationship is captured by reduced-order models, data-driven kernels reduce the gap between predictions and observations. A reduced-order model based on Nernst and Butler–Volmer equations represents the overall battery discharge, and a multilayer perceptron models the battery non-ideal voltage. Battery aging is characterized by time-dependent internal resistance and the amount of available Li-ions, which are modeled through an ensemble of variational Bayesian multilayer perceptrons. The approach is validated using data publicly available through the NASA Prognostics Center of Excellence website. Results showed that our hybrid battery prognosis model can be successfully calibrated, even with a limited number of observations. Moreover, the model can help optimizing battery operation by offering long-term forecast of battery capacity.","tags":null,"title":"Hybrid physics-informed neural networks for lithium-ion battery modeling and prognosis","type":"publication"},{"authors":["Renato G. Nascimento","Felipe A. C. Viana","Matteo Corbetta","Chetan S. Kulkarni"],"categories":null,"content":"","date":1627430400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1627430400,"objectID":"e20a89518378ad3d3ba9be653bcfa700","permalink":"/publication/2021-aviation-nascimento-et-al/","publishdate":"2021-07-28T18:31:57.199658Z","relpermalink":"/publication/2021-aviation-nascimento-et-al/","section":"publication","summary":"","tags":null,"title":"Usage-based Lifing of Lithium-Ion Battery with Hybrid Physics-Informed Neural Networks","type":"publication"},{"authors":["Kajetan Fricke","Renato G. Nascimento","Felipe A. C. Viana"],"categories":null,"content":"","date":1610323200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1610323200,"objectID":"791f416e0ca21326309921c7d81a680d","permalink":"/publication/2021-scitech-fricke-et-al/","publishdate":"2020-12-15T18:31:57.199658Z","relpermalink":"/publication/2021-scitech-fricke-et-al/","section":"publication","summary":"","tags":null,"title":"Quadcopter Soft Vertical Landing Control with Hybrid Physics-informed Machine Learning","type":"publication"},{"authors":["Felipe A. C. Viana","Renato G. Nascimento","Arinan Dourado","Yigit Yucesan"],"categories":null,"content":"","date":1607990400,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1607990400,"objectID":"c2a1d2312afa3a017c286e6894c67558","permalink":"/publication/2020-cs-viana-et-al/","publishdate":"2020-12-15T18:31:57.200253Z","relpermalink":"/publication/2020-cs-viana-et-al/","section":"publication","summary":"A number of physical systems can be described by ordinary differential equations. When physics is well understood, the time dependent responses are easily obtained numerically. The particular numerical method used for integration depends on the application. Unfortunately, when physics is not fully understood, the discrepancies between predictions and observed responses can be large and unacceptable. In this paper, we propose an approach that uses observed data to estimate the missing physics in the original model (i.e., model-form uncertainty). In our approach, we first design recurrent neural networks to perform numerical integration of the ordinary differential equations. Then, we implement the recurrent neural network as a directed graph. This way, the nodes in the graph represent the physics-informed kernels found in the ordinary differential equations. We quantify the missing physics by carefully introducing data-driven in the directed graph. This allows us to estimate the missing physics (discrepancy term) even for hidden nodes of the graph. We studied the performance of our proposed approach with the aid of three case studies (fatigue crack growth, corrosion-fatigue crack growth, and bearing fatigue) and state-of-the-art machine learning software packages. Our results demonstrate the ability to perform estimation of discrepancy, reducing gap between predictions and observations, at reasonable computational cost.","tags":null,"title":"Estimating model inadequacy in ordinary differential equations with physics-informed neural networks","type":"publication"},{"authors":["Andre V. Zuben","Renato G. Nascimento","Felipe A. C. Viana"],"categories":null,"content":"","date":1604880000,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1604880000,"objectID":"6e328735fffc579b3337d5a18f7da107","permalink":"/publication/2020-phm-zuben-et-al/","publishdate":"2020-11-09T18:31:57.199658Z","relpermalink":"/publication/2020-phm-zuben-et-al/","section":"publication","summary":"","tags":null,"title":"Visualizing corrosion in automobiles using generative adversarial networks","type":"publication"},{"authors":["Renato G. Nascimento","Kajetan Fricke","Felipe A. C. Viana"],"categories":null,"content":"","date":1602115200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1602115200,"objectID":"44262326cafdc14471ce3bdab175edd5","permalink":"/publication/2020-eaai-nascimento-et-al/","publishdate":"2020-10-02T18:31:57.200253Z","relpermalink":"/publication/2020-eaai-nascimento-et-al/","section":"publication","summary":"We present a tutorial on how to directly implement integration of ordinary differential equations through recurrent neural networks using Python. In order to simplify the implementation, we leveraged modern machine learning frameworks such as TensorFlow and Keras. Besides, offering implementation of basic models (such as multilayer perceptrons and recurrent neural networks) and optimization methods, these frameworks offer powerful automatic differentiation. With all that, the main advantage of our approach is that one can implement hybrid models combining physics-informed and data-driven kernels, where data-driven kernels are used to reduce the gap between predictions and observations. Alternatively, we can also perform model parameter identification. In order to illustrate our approach, we used two case studies. The first one consisted of performing fatigue crack growth integration through Euler’s forward method using a hybrid model combining a data-driven stress intensity range model with a physics-based crack length increment model. The second case study consisted of performing model parameter identification of a dynamic two-degree-of-freedom system through Runge–Kutta integration. The examples presented here as well as source codes are all open-source under the GitHub repository https://github.com/PML-UCF/pinn_code_tutorial.","tags":null,"title":"A tutorial on solving ordinary differential equations using Python and hybrid physics-informed neural network","type":"publication"},{"authors":["Renato G. Nascimento","Felipe A. C. Viana"],"categories":null,"content":"","date":1599004800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1599004800,"objectID":"023d10d16a24d3a103ea4f04f2a715bf","permalink":"/publication/2020-aiaa-nascimento-viana/","publishdate":"2020-09-02T18:31:57.200253Z","relpermalink":"/publication/2020-aiaa-nascimento-viana/","section":"publication","summary":"Maintenance of engineering assets (for example, aircraft, jet engines, and wind turbines) is a profitable business. Unfortunately, building models that estimate remaining useful life for large fleets is daunting due to factors such as duty cycle variation, harsh environments, inadequate maintenance, and mass production problems that cause discrepancies between designed and observed lives. We model cumulative damage through recurrent neural networks. Besides architectures such as long short-term memory and gated recurrent unit, we introduced a novel physics-informed approach. Essentially, we merge physics-informed and data-driven layers. With that, engineers and scientists can use physics-informed layers to model well understood phenomena (for example, fatigue crack growth) and use data-driven layers to model poorly characterized parts (for example, internal loads). A numerical experiment is used to present the main features of the proposed physics-informed recurrent neural network. The problem consists of predicting fatigue crack length for a fleet of aircraft. The models are trained using full input observations (far-field loads) and very limited output observations (crack length data for only a portion of the fleet). The results demonstrate that our proposed physics-informed recurrent neural network can model fatigue crack growth even when the observed distribution of crack length does not match the fleet distribution.","tags":null,"title":"Cumulative Damage Modeling with Recurrent Neural Networks","type":"publication"},{"authors":["Renato G. Nascimento","Kajetan Fricke","Felipe A. C. Viana"],"categories":null,"content":"","date":1577836800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1577836800,"objectID":"ca877b416cab50d25cc9b8a2028c03c8","permalink":"/publication/2020-scitech-nascimento-et-al/","publishdate":"2019-10-02T18:31:57.199658Z","relpermalink":"/publication/2020-scitech-nascimento-et-al/","section":"publication","summary":"","tags":null,"title":"Quadcopter Control Optimization through Machine Learning","type":"publication"},{"authors":["Renato G. Nascimento","Felipe A. C. Viana"],"categories":null,"content":"","date":1577836800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1577836800,"objectID":"ef3fd944945c8fb8a89357a735a60476","permalink":"/publication/2020-scitech-sat-nascimento/","publishdate":"2019-10-02T18:31:57.200765Z","relpermalink":"/publication/2020-scitech-sat-nascimento/","section":"publication","summary":"","tags":null,"title":"Satellite Image Classification and Segmentation with Transfer Learning","type":"publication"},{"authors":[],"categories":[],"content":"","date":1570045302,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1570045302,"objectID":"49164d8aaaf4aecdf12072b6d3c56c54","permalink":"/project/pinn/","publishdate":"2019-10-02T15:41:42-04:00","relpermalink":"/project/pinn/","section":"project","summary":"","tags":[],"title":"PINN - Physics-informed neural networks","type":"project"},{"authors":["A. K. Subramaniyan","A. N. Iankoulski","S. Sivaramakrishnan","R. G. Nascimento","F. N. de Paula"],"categories":null,"content":"US Patent App. 16 / 258,489\n","date":1564617600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1564617600,"objectID":"223be253080932d0cf40703170580bab","permalink":"/patent/autonomous_hybrid_analytics/","publishdate":"2019-08-01T00:00:00Z","relpermalink":"/patent/autonomous_hybrid_analytics/","section":"patent","summary":"US Patent App. 16 / 258,489","tags":null,"title":"Autonomous Hybrid Analytics Modeling Platform","type":"patent"},{"authors":["A. K. Subramaniyan","A. N. Iankoulski","R. G. Nascimento"],"categories":null,"content":"US Patent 10,296,296, 2019\n","date":1558396800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1558396800,"objectID":"7ea4a2b036911f2c80d22d2a79184001","permalink":"/patent/integrated_development_analytic_authoring/","publishdate":"2019-05-21T00:00:00Z","relpermalink":"/patent/integrated_development_analytic_authoring/","section":"patent","summary":"US Patent 10,296,296, 2019","tags":null,"title":"Integrated development environment for analytic authoring","type":"patent"},{"authors":["Renato G. Nascimento","Felipe A. C. Viana"],"categories":null,"content":"","date":1546300800,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1546300800,"objectID":"3505ea29fe4bd983790c506bb40f1799","permalink":"/publication/2019-iwdhm-nascimento-viana/","publishdate":"2019-10-02T18:31:57.198848Z","relpermalink":"/publication/2019-iwdhm-nascimento-viana/","section":"publication","summary":"","tags":null,"title":"Fleet prognosis with physics-informed recurrent neural networks","type":"publication"},{"authors":["A. K. Subramaniyan","A. N. Iankoulski","R. G. Nascimento"],"categories":null,"content":"US Patent 9,978,114, 2018\n","date":1526947200,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1526947200,"objectID":"0587c6c1c5680a686ed5d40bc565a383","permalink":"/patent/systems_optimizing_graphics_large_data/","publishdate":"2018-05-22T00:00:00Z","relpermalink":"/patent/systems_optimizing_graphics_large_data/","section":"patent","summary":"US Patent 9,978,114, 2018","tags":null,"title":"Systems and methods for optimizing graphics processing for rapid large data visualization","type":"patent"},{"authors":["A. K. Subramaniyan","A. N. Iankoulski","R. G. Nascimento"],"categories":null,"content":"US Patent App. 15 / 338,886, 2018\n","date":1525305600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1525305600,"objectID":"e4508e2146bedad021fdc9a94ed2ab0b","permalink":"/patent/self-aware_software_analytics/","publishdate":"2018-05-03T00:00:00Z","relpermalink":"/patent/self-aware_software_analytics/","section":"patent","summary":"US Patent App. 15 / 338,886, 2018","tags":null,"title":"Self-aware and self-registering software \u0026 analytics platform components","type":"patent"},{"authors":["A. K. Subramaniyan","J. Lazos","N. C. Kumar","A. N. Iankoulski","R. G. Nascimento"],"categories":null,"content":"US Patent App. 15 / 338,839, 2018\n","date":1525305600,"expirydate":-62135596800,"kind":"page","lang":"en","lastmod":1525305600,"objectID":"b913a5a426682ed587955c0b2a4efa69","permalink":"/patent/system_architecture_rapid_development_analytics/","publishdate":"2018-05-03T00:00:00Z","relpermalink":"/patent/system_architecture_rapid_development_analytics/","section":"patent","summary":"US Patent App. 15 / 338,839, 2018","tags":null,"title":"System architecture for secure and rapid development, deployment and management of analytics and software systems","type":"patent"}]