scholarly journals NEXTorch: A Design and Bayesian Optimization Toolkit for Chemical Sciences and Engineering

2021 ◽  
Author(s):  
Yifan Wang ◽  
Tai-Ying Chen ◽  
Dionisios Vlachos
Keyword(s):  
Active Learning ◽  
Geometry Optimization ◽  
Optimization Theory ◽  
Computational Design ◽  
Bayesian Optimization ◽  
Optimization Approach ◽  
Loop Optimization ◽  
Human In The Loop ◽  
Condition Optimization ◽  
Reactor Geometry

<div> <div> <div> <p>Automation and optimization of chemical systems require well-inform decisions on what experiments to run to reduce time, materials, and/or computations. Data-driven active learning algorithms have emerged as valuable tools to solve such tasks. Bayesian optimization, a sequential global optimization approach, is a popular active-learning framework. Past studies have demonstrated its efficiency in solving chemistry and engineering problems. We introduce NEXTorch, a library in Python/PyTorch, to facilitate laboratory or computational design using Bayesian optimization. NEXTorch offers fast predictive modeling, flexible optimization loops, visualization capabilities, easy interfacing with legacy software, and multiple types of parameters and data type conversions. It provides GPU acceleration, parallelization, and state-of-the-art Bayesian Optimization algorithms and supports both automated and human-in-the-loop optimization. The comprehensive online documentation introduces Bayesian optimization theory and several examples from catalyst synthesis, reaction condition optimization, parameter estimation, and reactor geometry optimization. NEXTorch is open-source and available on GitHub. </p> </div> </div> </div>

scholarly journals NEXTorch: A Design and Bayesian Optimization Toolkit for Chemical Sciences and Engineering

2021 ◽  
Author(s):  
Yifan Wang ◽  
Tai-Ying Chen ◽  
Dionisios Vlachos
Keyword(s):  
Active Learning ◽  
Geometry Optimization ◽  
Optimization Theory ◽  
Computational Design ◽  
Bayesian Optimization ◽  
Optimization Approach ◽  
Loop Optimization ◽  
Human In The Loop ◽  
Condition Optimization ◽  
Reactor Geometry

<div> <div> <div> <p>Automation and optimization of chemical systems require well-inform decisions on what experiments to run to reduce time, materials, and/or computations. Data-driven active learning algorithms have emerged as valuable tools to solve such tasks. Bayesian optimization, a sequential global optimization approach, is a popular active-learning framework. Past studies have demonstrated its efficiency in solving chemistry and engineering problems. We introduce NEXTorch, a library in Python/PyTorch, to facilitate laboratory or computational design using Bayesian optimization. NEXTorch offers fast predictive modeling, flexible optimization loops, visualization capabilities, easy interfacing with legacy software, and multiple types of parameters and data type conversions. It provides GPU acceleration, parallelization, and state-of-the-art Bayesian Optimization algorithms and supports both automated and human-in-the-loop optimization. The comprehensive online documentation introduces Bayesian optimization theory and several examples from catalyst synthesis, reaction condition optimization, parameter estimation, and reactor geometry optimization. NEXTorch is open-source and available on GitHub. </p> </div> </div> </div>

scholarly journals Strategies for Improving Optimal Positioning of Quality Sensors in Urban Drainage Systems for Non-Conservative Contaminants

Water ◽  
2021 ◽  
Vol 13 (7) ◽  
pp. 934
Author(s):  
Mariacrocetta Sambito ◽  
Gabriele Freni
Keyword(s):  
Treatment Plant ◽  
Optimal Solution ◽  
Monitoring Network ◽  
Computational Effort ◽  
Bayesian Optimization ◽  
Urban Drainage ◽  
Optimization Approach ◽  
Sensor Location ◽  
Contamination Source ◽  
Monitoring Point

In the urban drainage sector, the problem of polluting discharges in sewers may act on the proper functioning of the sewer system, on the wastewater treatment plant reliability and on the receiving water body preservation. Therefore, the implementation of a chemical monitoring network is necessary to promptly detect and contain the event of contamination. Sensor location is usually an optimization exercise that is based on probabilistic or black-box methods and their efficiency is usually dependent on the initial assumption made on possible eligibility of nodes to become a monitoring point. It is a common practice to establish an initial non-informative assumption by considering all network nodes to have equal possibilities to allocate a sensor. In the present study, such a common approach is compared with different initial strategies to pre-screen eligible nodes as a function of topological and hydraulic information, and non-formal 'grey' information on the most probable locations of the contamination source. Such strategies were previously compared for conservative xenobiotic contaminations and now they are compared for a more difficult identification exercise: the detection of nonconservative immanent contaminants. The strategies are applied to a Bayesian optimization approach that demonstrated to be efficient in contamination source location. The case study is the literature network of the Storm Water Management Model (SWMM) manual, Example 8. The results show that the pre-screening and ‘grey’ information are able to reduce the computational effort needed to obtain the optimal solution or, with equal computational effort, to improve location efficiency. The nature of the contamination is highly relevant, affecting monitoring efficiency, sensor location and computational efforts to reach optimality.

A Perspective on Future Directions in Intelligent Health Control of Gasturbines and Auxiliaries

1999 ◽  
Author(s):  
K. Eftekhari Shahroudi
Keyword(s):  
Real Time ◽  
Neural Nets ◽  
Fault Models ◽  
Time Data ◽  
Bottom Line ◽  
Loop Optimization ◽  
Human In The Loop ◽  
Health Control ◽  
Usable Information ◽  
Performance Trends

Despite their seemingly impressive claims, current products for Condition Monitoring, Diagnostic and Decision Support Systems (CMD&D) do not provide the reliable bottom line information that end users and operators need. Instead they confuse the issue with gigabytes of logged trends, complex cause-effect matrices, fault signatures etc. The term “Intelligent Health Control” here refers to the next generation of such systems which provide usable information on: • the existence and severity of faults; • how their severity will progress with utilization; • how this progress can be influenced or controlled. In this paper the fundamental shortcomings of current approaches are discussed prior to introducing the basics of Intelligent Health Control in terms of fault models and how they can be used to close the diagnostic, prognostic and intelligent control triangle. The industry will unavoidably shift towards an “information centric” view from the currently predominant “data centric” view. Gigabytes of performance trends will no longer be relevant. Instead, reliable bottom line information will be required on how to minimize or control the costs associated with machinery health degradation or faults. In order to keep the discussion real, the current state of the art of enabling technologies are discussed, including: • Open Information Buses; • Adding real time data server functionality to the control system; • Computational Steering, Human-in-the-Loop Optimization (or semi-automatic problem solving); • Fault Models; • Faster than real time simulation; • Neural Nets.

scholarly journals Gait-symmetry-based human-in-the-loop optimization for unilateral transtibial amputees with robotic prostheses

2020 ◽  
Author(s):  
Yanggan Feng ◽  
Chengqiang Mao ◽  
Qining Wang
Keyword(s):  
Metabolic Cost ◽  
Optimization Method ◽  
Metabolic Energy ◽  
Joint Degeneration ◽  
Joint Injury ◽  
Loop Optimization ◽  
Gait Symmetry ◽  
Human In The Loop ◽  
Risk Of Injury ◽  
Transtibial Amputees

AbstractGait asymmetry due to the loss of unilateral limb increases the risk of injury or progressive joint degeneration. The development of wearable robotic devices paves a way to improve gait symmetry of unilateral amputees. Moreover, the state-of-the-art studies on human-in-the-loop optimization strategies through decreasing the metabolic cost as the optimization task, have met several challenges, e.g. too long period of optimization and the optimization feasibility for unilateral amputees who have the deficit of gait symmetry. Here, in this paper, we proposed gait-symmetry-based human-in-the-loop optimization method to decrease the risk of injury or progressive joint degeneration for unilateral transtibial amputees. The experimental results (N = 3 unilateral transtibial subjects) demonstrate that only average 9.0±4.1min of convergence was taken. Compared to gait symmetry while wearing prosthetics, after optimization, the gait symmetry indicator value of the subjects wearing the robotic prostheses was improved by 21.0% and meanwhile the net metabolic energy consumption value was reduced by 9.2%. Also, this paper explores the rationality of gait indicators and what kind of gait indicators are the optimization target. These results suggest that gait-symmetry-based human-in-the-loop strategy could pave a practical way to improve gait symmetry by accompanying the reduction of metabolic cost, and thus to decrease the risk of joint injury for the unilateral amputees.

Monitoring Water Resources through a Bayesian Optimization-based Approach using Multiple Surface Vehicles: The Ypacarai Lake Case Study

2021 ◽  
Author(s):  
Federico Peralta Samaniego ◽  
Sergio Toral Marín ◽  
Daniel Gutierrez Reina
Keyword(s):  
Water Quality ◽  
Mean Squared Error ◽  
Bayesian Optimization ◽  
Water Quality Parameter ◽  
Optimization Approach ◽  
Decision Strategy ◽  
Sequential Decision ◽  
Partition System ◽  
Autonomous Surface Vehicle ◽  
Voronoi Partition

<div>Bayesian optimization is a popular sequential decision strategy that can be used for environmental monitoring. In this work, we propose an efficient multi-Autonomous Surface Vehicle system capable of monitoring the Ypacarai Lake (San Bernardino, Paraguay) (60 km<sup>2</sup>) using the Bayesian optimization approach with a Voronoi Partition system. The system manages to quickly approximate the real unknown distribution map of a water quality parameter using Gaussian Processes as surrogate models. Furthermore, to select new water quality measurement locations, an acquisition function adapted to vehicle energy constraints is used. Moreover, a Voronoi Partition system helps to distributing the workload with all the available vehicles, so that robustness and scalability is assured. For evaluation purposes, we use both the mean squared error and computational efficiency. The results showed that our method manages to efficiently monitor the Ypacarai Lake, and also provides confident approximate models of water quality parameters. It has been observed that, for every vehicle, the resulting surrogate model improves by 38%.</div>

Sign in / Sign up

Export Citation Format

Share Document