Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Page Not Found

Page not found. Your pixels are in another canvas.

Jupyter notebook markdown generator

Posts

Future Blog Post

less than 1 minute read

Published: January 01, 2199

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published: August 14, 2015

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published: August 14, 2014

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published: August 14, 2013

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published: August 14, 2012

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

confWsps

Toward Smart Manufacturing Using Decision Analytics

Published: October 30, 2014

This paper is focused on decision analytics for smart manufacturing. We consider temporal manufacturing processes with stochastic throughput and inventories. We demonstrate the use of the recently proposed concept of the decision guidance analytics language to perform monitoring, analysis, planning, and execution tasks. To support these tasks we define the structure of and develop modular reusable process component models, which represent data, decision/control variables, computation of functions, constraints, and uncertainty. The tasks are then implemented by posing declarative queries of the decision guidance analytics language for data manipulation, what-if prediction analysis, decision optimization, and machine learning.

Recommended citation: A. Brodsky, M. Krishnamoorthy, D. Menasce, G. Shao, and S.Rachuri, Toward Smart Manufacturing Using Decision Analytics. In Proceedings of the 2014 IEEE International Conference on Big Data, Washington DC. October 2014." https://doi.org/10.1109/BigData.2014.7004330

Temporal manufacturing query language (tMQL) for domain specific composition, what-if analysis, and optimization of manufacturing processes with inventories

Published: January 15, 2015

Smart manufacturing requires streamlining operations and optimizing processes at a global and local level. This paper considers manufacturing processes that involve physical or virtual inventories of products, parts and materials, that move from machine to machine. The inventory levels vary with time and are a function of the configuration settings of the machines involved in the process. These environments require analysis, e.g., answering what-if questions, and optimization to deter- mine optimal operating settings for the entire process. The modeling complexities in performing these tasks are not always within the grasp of production engineers. To address this problem, the paper proposes the tempo- ral Manufacturing Query Language (tMQL) that allows the composition of modular process models for what-if analysis and decision optimization queries. tQML sup- ports an extensible and reusable model knowledge base against which declarative queries can be posed. Addi- tionally, the paper describes the steps to translate the components of a tMQL model to input data files used by a commercial optimization solver.

Recommended citation: M. Krishnamoorthy, A. Brodsky, and D. A. Menasce, Temporal manufacturing query language (tMQL) for domain specific composition, what-if analysis, and optimization of manufacturing processes with inventories. Technical Report Department of Computer Science, George Mason University, 2014. Also presented at the 2015 INFORMS Computing Soc. Conf. workshop, Richmond, VA. January 2015. https://cs.gmu.edu/media/techreports/GMU-CS-TR-2014-3.pdf

Optimizing Stochastic Temporal Manufacturing Processes with Inventories: An Efficient Heuristic Algorithm Based on Deterministic Approximations

Published: January 16, 2015

This paper deals with stochastic temporal manufacturing processes with work-in-process inventories in which multiple products are produced from raw materials and parts. The processes may be composed of subprocesses, which, in turn may be either composite or atomic, i.e., a machine on a manufacturing floor. We assume that machines' throughput is stochastic and so are work-in- process inventories and costs. We consider the problem of optimizing the process, that is, finding throughput expectation setting for each machine at each time point over the time horizon as to minimize the total cost of production subject to satisfying the production demand with a requested probability. To address this problem, we propose an efficient iterative heuristic algorithms that is based on (1) producing high quality candidate machine settings based on a deterministic approxima- tion of the stochastic problem, and (2) running stochastic simulations to find the best machine setting out of the produced candidates using optimal simulation budget allocation methods. We conduct an experimental study that shows that our algorithm significantly outperforms four popular simulation-based optimization algorithms."

Recommended citation: M. Krishnamoorthy, A. Brodsky, and D. Menasce, Optimizing Stochastic Temporal Manufacturing Processes with Inventories: An Efficient Heuristic Algorithm Based on Deterministic Approximations. In Proceedings of 2015 INFORMS Computing Soc. Conf., Richmond, VA. January 2015 https://doi.org/10.1287/ICS.2015.0003

Analysis and optimization in smart manufacturing based on a reusable knowledge base for process performance models

Published: November 01, 2015

In this paper, we propose an architectural design and software framework for fast development of descriptive, diagnostic, predictive, and prescriptive analytics solutions for dynamic production processes. The proposed architecture and framework will support the storage of modular, extensible, and reusable Knowledge Base (KB) of process performance models. The approach requires the development of automatic methods that can translate the high-level models in the reusable KB into low-level specialized models required by a variety of underlying analysis tools, including data manipulation, optimization, statistical learning, estimation, and simulation. We also propose an organization and key structure for the reusable KB, composed of atomic and composite process performance models and domain-specific dashboards. Furthermore, we illustrate the use of the proposed architecture and framework by performing diagnostic tasks on a composite performance model.

Recommended citation: A. Brodsky, G. Shao, M. Krishnamoorthy, A. Narayanan, D Menasce, and R. Ak, Analysis and optimization in smart manufacturing based on a reusable knowledge base for process performance models. In Proceedings of the 2015 IEEE International Conference on Big Data, Santa Clara, CA. November 2015. https://doi.org/10.1109/BigData.2015.7363902

Modular Modeling and Optimization of Temporal Manufacturing Processes with Inventories

Published: January 08, 2016

Smart manufacturing requires streamlining operations and optimizing processes at a global and local level. This paper considers temporal manufacturing processes that involve physical or virtual inventories of products, parts and materials that move through a network of subprocesses. The inventory levels vary with time and are a function of the configuration settings of the machines involved in the process. These environments require analysis, e.g., answering what-if questions, and optimization to determine optimal operating settings for the entire process. To address this problem, the paper proposes modular process components that can represent these manufacturing environments at various levels of granularity for performing what-if analysis and decision optimization queries. These components are extensible and reusable against which optimization and what-if questions can be posed. Additionally, the paper describes the steps to translate these complex components and optimization queries into a formal mathematical programming model, which is then solved by a commercial optimization solver.

Recommended citation: M. Krishnamoorthy, A. Brodsky, and D. Menasce, Modular Modeling and Optimization of Temporal Manufacturing Processes with Inventories. In Proceedings of the 2016 Hawaii International Conference on System Sciences, Kauai, HI. January 2016. https://doi.org/10.1109/HICSS.2016.177

A System and Architecture for Reusable Abstractions of Manufacturing Processes

Published: December 08, 2016

In this paper we report on the development of a system for managing a repository and conducting analysis and optimization on manufacturing performance models. The repository is designed to contain (1) unit manufacturing process performance models, (2) composite performance models representing production cells, lines, and facilities, (3) domain specific analytical views, and (4) ontologies and taxonomies. Initial implementation includes performance models for milling and drilling as well as a composite performance model for machining. These performance models formally capture (1) the metrics of energy consumption, CO 2 emissions, tool wear, and cost as a function of process controls and parameters, and (2) the process feasibility constraints. The initial scope of the system includes (1) an Integrated Development Environment and its interface, and (2) simulation and deterministic optimization of performance models through the use of Unity Decision Guidance Management System.

Recommended citation: A. Brodsky, M. Krishnamoorthy, W. Z. Bernstein, and M. O. Nachawati, A System and Architecture for Reusable Abstractions of Manufacturing Processes. In Proceedings of the 2016 IEEE International Conference on Big Data, Washington DC. December 2016. https://doi.org/10.1109/BigData.2016.7840823

Manufacturing and Contract Service Networks: Composition, Optimization and Tradeoff Analysis based on a Reusable Repository of Performance Models

Published: December 11, 2017

In this paper we report on the development of a software framework and system for composition, optimization and trade-off analysis of manufacturing and contract service networks based on a reusable repository of performance models. Performance models formally describe process feasibility constraints and metrics of interest, such as cost, throughput and CO 2 emissions, as a function of fixed and control parameters, such as equipment and contract properties and settings. The repository contains performance models for (1) unit manufacturing processes, (2) base contract services, and (3) a composite steady-state service network. The proposed framework allows process engineers to (1) hierarchically compose model instances of service networks, which can represent production cells, lines, factory facilities and supply chains, and (2) perform deterministic optimization based on mathematical programming and Pareto-optimal trade-off analysis. We case study the framework on a service network for a heat sink product which involves contract vendors and manufacturers, unit manufacturing process services including cutting/shearing and Computer Numerical Control (CNC) machining with milling and drilling steps, quality inspection, finishing and assembly.

Recommended citation: A. Brodsky, M. Krishnamoorthy, M. O. Nachawati, and W.Z. Bernstein, and D Menasce, Manufacturing and Contract Service Networks: Composition, Optimization and Tradeoff Analysis based on a Reusable Repository of Performance Models. In Proceedings of the 2017 IEEE International Conference on Big Data, Boston, MA. December 2017. https://doi.org/10.1109/BigData.2017.8258114

Stochastic Decision Optimization based on Deterministic Approximations of Processes described as Closed-form Arithmetic Simulation

Published: April 11, 2018

We propose an efficient one-stage stochastic optimisation algorithm for the problem of finding process controls that minimise the expectation of cost while satisfying multiple deterministic and stochastic feasibility constraints with a given high probability. The proposed algorithm is based on a series of deterministic approximations to produce a candidate solution set and on a refinement step using stochastic simulations with optimal simulation budget allocation. We conduct an experimental study for a real-world manufacturing service network, which shows that the proposed algorithm significantly outperforms four popular simulation-based stochastic optimisation algorithms.

Recommended citation: M. Krishnamoorthy, A. Brodsky, and D. Menasce, Stochastic Decision Optimization based on Deterministic Approximations of Processes described as Closed-form Arithmetic Simulation. In Proceedings of the IFIP WG 8.3 on Decision Support Systems, June 2018. Best Paper Award. https://doi.org/10.1080/12460125.2018.1468174

Stochastic Optimization for Steady State Production Processes based on Deterministic Approximations

Published: February 01, 2021

We consider steady-state production processes that have feasibility constraints and metrics of cost and throughput that are stochastic functions of process controls. We propose an efficient stochastic optimization algorithm for the problem of finding process controls that minimize the expectation of cost while satisfying deterministic feasibility constraints and stochastic steady state demand for the output product with a given high probability. The proposed algorithm is based on (1) a series of deterministic approximations to produce a candidate set of near-optimal control settings for the production process, and (2) stochastic simulations on the candidate set using optimal simulation budget allocation methods. We demonstrate the proposed algorithm on a use case of a real-world heat-sink production process that involves contract suppliers and manufacturers as well as unit manufacturing processes of shearing, milling, drilling, and machining, and conduct an experimental study that sh ows that the proposed algorithm significantly outperforms four popular simulation-based stochastic optimization algorithms.

Recommended citation: M. Krishnamoorthy, A. Brodsky, and D. Menasce, Stochastic Optimization for Steady State Production Processes based on Deterministic Approximations. In the International Conference on Operations Research and Enterprise Systems 2021, February 2021. https://doi.org/10.5220/0010343802870294

Apprentice for Event Generator Tuning

Published: August 23, 2021

APPRENTICE is a tool developed for event generator tuning. It contains a range of conceptual improvements and extensions over the tuning tool Professor. Its core functionality remains the construction of a multivariate analytic surrogate model to computationally expensive Monte-Carlo event generator predictions. The surrogate model is used for numerical optimization in chi-square minimization and likelihood evaluation. Apprentice also introduces algorithms to automate the selection of observable weights to minimize the effect of mis-modeling in the event generators. We illustrate our improvements for the task of MC-generator tuning and limit setting.

Recommended citation: M. Krishnamoorthy, H. Schulz, X. Ju, W. Wang, S. Leyffer, Z. Marshall, S. Mrenna, J. Muller, and J. B.Kowalkowski, Apprentice for Event Generator Tuning. In 25th International Conference on Computing in High-Energy and Nuclear Physics. August 2021. https://doi.org/10.1051/epjconf/202125103060

journals

Tree pruner: An efficient tool for selecting data from a biased genetic database

Published: February 09, 2011

Background: Large databases of genetic data are often biased in their representation. Thus, selection of genetic data with desired properties, such as evolutionary representation or shared genotypes, is problematic. Selection on the basis of epidemiological variables may not achieve the desired properties. Available automated approaches to the selection of influenza genetic data make a tradeoff between speed and simplicity on the one hand and control over quality and contents of the dataset on the other hand. A poorly chosen dataset may be detrimental to subsequent analyses. Results: We developed a tool, Tree Pruner, for obtaining a dataset with desired evolutionary properties from a large, biased genetic database. Tree Pruner provides the user with an interactive phylogenetic tree as a means of editing the initial dataset from which the tree was inferred. The tree visualization changes dynamically, using colors and shading, reflecting Tree Pruner actions. At the end of a Tree Pruner session, the editing actions are implemented in the dataset.Currently, Tree Pruner is implemented on the Influenza Research Database (IRD). The data management capabilities of the IRD allow the user to store a pruned dataset for additional pruning or for subsequent analysis. Tree Pruner can be easily adapted for use with other organisms. Conclusions: Tree Pruner is an efficient, manual tool for selecting a high-quality dataset with desired evolutionary properties from a biased database of genetic sequences. It offers an important alternative to automated approaches to the same goal, by providing the user with a dynamic, visual guide to the ongoing selection process and ultimate control over the contents (and therefore quality) of the dataset.

Recommended citation: M. Krishnamoorthy, P. Patel, M. Dimitrijevic, J. Dietrich, M. Green, and C. Macken, Tree pruner: An efficient tool for selecting data from a biased genetic database. In BMC bioinformatics Journal, January 2011. http://doi.org/10.1186/1471-2105-12-51

A multiple-alignment based primer design algorithm for genetically highly variable DNA targets

Published: August 21, 2013

Background: Primer design for highly variable DNA sequences is difficult, and experimental success requires attention to many interacting constraints. The advent of next-generation sequencing methods allows the investigation of rare variants otherwise hidden deep in large populations, but requires attention to population diversity and primer localization in relatively conserved regions, in addition to recognized constraints typically considered in primer design. Results: Design constraints include degenerate sites to maximize population coverage, matching of melting temperatures, optimizing de novo sequence length, finding optimal bio-barcodes to allow efficient downstream analyses, and minimizing risk of dimerization. To facilitate primer design addressing these and other constraints, we created a novel computer program (PrimerDesign) that automates this complex procedure. We show its powers and limitations and give examples of successful designs for the analysis of HIV-1 populations. Conclusions: PrimerDesign is useful for researchers who want to design DNA primers and probes for analyzing highly variable DNA populations. It can be used to design primers for PCR, RT-PCR, Sanger sequencing, next-generation sequencing, and other experimental protocols targeting highly variable DNA samples.

Recommended citation: J. Brodin, M. Krishnamoorthy, G. Athreya, W. Fischer, P. Hraber, C. Gleasner, L. Green, B. Korber, and T. Leitner, A multiple-alignment based primer design algorithm for genetically highly variable DNA targets. In BMC bioinformatics Journal, August 2013. http://doi.org/10.1186/1471-2105-14-255

Autonomic smart manufacturing

Published: March 12, 2015

Smart manufacturing (SM) systems have to optimise manufacturing activities at the machine, unit or entire manufacturing facility level as well as adapting the manufacturing process on the fly as required by a variety of conditions (e.g. machine breakdowns and/or slowdowns) and unexpected variations in demands. This paper provides a framework for autonomic smart manufacturing (ASM) that relies on a variety of models for its support: (1) a process model to represent machines, parst inventories and the flow of parts through machines in a discrete manufacturing floor; (2) a predictive queueing network model to support the analysis and planning phases of ASM; and (3) optimisation models to support the planning phase of ASM. In essence, ASM is an integrated decision support system for smart manufacturing that combines models of different nature in a seamless manner. As shown here, these models can be used to predict manufacturing time and the energy consumed by the manufacturing process, as well as for finding the machine settings that minimise the energy consumed or the manufacturing time subject to a variety of constraints using non-linear optimisation models. The diversity of models used affords different levels of integration and granularity in the decision-making process. An example of a car manufacturing process is used throughout the paper to explain the concepts and models introduced here.

Recommended citation: D. Menasce, M. Krishnamoorthy, and A. Brodsky, Autonomic smart manufacturing. In the Journal of Decision Systems, Special Issue on Integrated Decision Support Systems, June 2015. http://doi.org/10.1080/12460125.2015.1046714

Analysis and Optimization in Smart Manufacturing based on a Reusable Knowledge Base for Process Performance Models

Published: April 23, 2016

In this paper, we propose an architectural design and software framework for fast development of descriptive, diagnostic, predictive, and prescriptive analytics solutions for dynamic production processes. The proposed architecture and framework will support the storage of modular, extensible, and reusable knowledge base (KB) of process performance models. The approach requires developing automated methods that can translate the high-level models in the reusable KB into low-level specialized models required by a variety of underlying analysis tools, including data manipulation, optimization, statistical learning, estimation, and simulation. We also propose an organization and key structure for the reusable KB, composed of atomic and composite process performance models and domain-specific dashboards. Furthermore, we illustrate the use of the proposed architecture and framework by prototyping a decision support system for process engineers. The decision support system allows users to hierarchically compose and optimize dynamic production processes via a graphical user interface.

Recommended citation: A. Brodsky, G. Shao, M. Krishnamoorthy, A. Narayanan, D Menasce, and R. Ak, Analysis and Optimization in Smart Manufacturing based on a Reusable Knowledge Base for Process Performance Models. In the International Journal of Advanced Manufacturing Technology. April 2016. http://doi.org/10.1007/s00170-016-8761-7

Stochastic Decision Optimization based on Deterministic Approximations of Processes described as Closed-form Arithmetic Simulation

Published: April 11, 2018

Recommended citation: M. Krishnamoorthy, A. Brodsky, and D. Menase, Stochastic Decision Optimization based on Deterministic Approximations of Processes described as Closed-form Arithmetic Simulation. In the Journal of Decision Systems. May 2018. http://doi.org/10.1080/12460125.2018.1468174

Factory optima: a web-based system for composition and analysis of manufacturing service networks based on a reusable model repository

Published: December 14, 2018

This paper reports on the development of Factory Optima, a web-based system that allows manufacturing process engineers to compose, optimise and perform trade-off analysis of manufacturing and contract service networks based on a reusable repository of performance models. Performance models formally describe process feasibility constraints and metrics of interest, such as cost, throughput and CO2 emissions, as a function of fixed and control parameters, such as equipment and contract properties and settings. The repository contains performance models representing (1) unit manufacturing processes, (2) base contract services and (3) a composite steady-state service network. The proposed framework allows process engineers to hierarchically compose model instances of service networks, which can represent production cells, lines, factory facilities and supply chains, and perform deterministic optimisation based on mathematical programming and Pareto-optimal trade-off analysis. Factory Optima is demonstrated using a case study of a service network for a heat sink product which involves contract vendors and manufacturing activities, including cutting, shearing, Computer Numerical Control (CNC) machining with milling and drilling operations, quality inspection, finishing, and assembly.

Recommended citation: A. Brodsky, M. O. Nachawati, M. Krishnamoorthy, W. Z. Bernstein, and D. A. Menasce, Factory optima: a web-based system for composition and analysis of manufacturing service networks based on a reusable model repository. In the International Journal of Computer Integrated Manufacturing, February 2019. http://doi.org/10.1080/0951192X.2019.1570805

Practical algorithms for multivariate rational approximation

Published: April 01, 2020

We present two approaches for computing rational approximations to multivariate functions, motivated by their effectiveness as surrogate models for high-energy physics (HEP) applications. Our first approach builds on the Stieltjes process to efficiently and robustly compute the coefficients of the rational approximation. Our second approach is based on an optimization formulation that allows us to include structural constraints on the rational approximation (in particular, constraints demanding the absence of singularities), resulting in a semi-infinite optimization problem that we solve using an outer approximation approach. We present results for synthetic and real-life HEP data, and we compare the approximation quality of our approaches with that of traditional polynomial approximations.

Recommended citation: A. Austin, M. Krishnamoorthy, S. Leyffer, S. Mrenna, J. Muller, and H. Schulz, Practical algorithms for multivariate rational approximation. In the Computer Physics Communications, October 2020. http://doi.org/10.1016/j.cpc.2020.107663

BROOD: Bilevel and Robust Optimization and Outlier Detection for Efficient Tuning of High-Energy Physics Event Generators.

Published: January 17, 2022

The parameters in Monte Carlo (MC) event generators are tuned on experimental measurements by evaluating the goodness of fit between the data and the MC predictions. The relative importance of each measurement is adjusted manually in an often time-consuming, iterative process to meet different experimental needs. In this work, we introduce several optimization formulations and algorithms with new decision criteria for streamlining and automating this process. These algorithms are designed for two formulations: bilevel optimization and robust optimization. Both formulations are applied to the datasets used in the ATLAS A14 tune and to the dedicated hadronization datasets generated by the Sherpa generator, respectively. The corresponding tuned generator parameters are compared using three metrics. We compare the quality of our automatic tunes to the published ATLAS A14 tune. Moreover, we analyze the impact of a pre-processing step that excludes data that cannot be described by the physics models used in the MC event generators.

Recommended citation: W. Wang, M. Krishnamoorthy, J. Muller, S. Mrenna, H. Schulz, X. Ju, S. Leyffer, and Z. Marshall, BROOD: Bilevel and Robust Optimization and Outlier Detection for Efficient Tuning of High-Energy Physics Event Generators. In the SciPost Physics. January 2022. https://dx.doi.org/10.21468/SciPostPhysCore.5.1.001

research

Research Assistant

Internship, Los Alamos National Laboratory, Theoretical Biology and Biophysics division, 2008

Designed and developed Tree Viewer, Pruner and Decorator tools to perform selection and annotation of Influenza sequences.
Designed and developed a schema for a large Influenza Sequence Database.
Publications to come out of this work include BMCbio’11.

Research Technologist

Full time, Los Alamos National Laboratory, Theoretical Biology and Biophysics division, 2010

Designed and developed scientific algorithms for highly variable and large scale bioinformatics tools.
Developed and debugged multiple backend modules of the HIV project.
Redesigned the HIV website using Model-View-Controller (MVC) framework and web services.
Publications to come out of this work include BMCbio’13.

Graduate Research Assistant

Part time, George Mason University, Department of Computer Science, 2013

Designed and developed reusable mathematical models for non-linear, stochastic, hierarchical, and temporal manufacturing processes from real-world data.
Designed and developed one-stage stochastic optimization algorithms based on deterministic approximation heuristics.
Developed and published the stochastic optimization algorithm based on deterministic approximations (SODA) to efficiently solve the problem of finding controls for stochastic processes in a large manufacturing service network.
Publications to come out of this work include GMU’14, ICS’15, JDS’15, HICSS’16, JDS’18, and IFIPDSS’18.

Guest Researcher

Part time, National Institute of Standards and Technology, Life Cycle Engineering, 2015

Designed and populated a repository of reusable mathematical models that were sourced from real-world data, publications, and crowdsourced data.
Developed a software framework and prototype (FactoryOptima) to perform composition, analysis, and optimization on reusable models.
Publications to come out of this work include IEEEBD’14, IEEEBD’15, IEEEBD’16, IJAMT’16, IEEEBD’17, and IJCIM’19.

Postdoctoral Appointee

Full time, Argonne National Laboratory, Mathematics and Computer Science division, 2018

Developed and implemented mathematical and algorithmic techniques for approximating expensive functions in High Energy Physics (HEP).
Developed robust optimization and design of experiment formulations to decide weights of importance with the goal of tuning a HEP Monte Carlo simulator.
Developed, maintained, and published HEP analysis packages called apprentice and outer optimization for efficiently constructing polynomial/rational approximations and for performing least squares minimizations.
Publications to come out of this work include CPC’20, CHEP’21, and SCIPOST’22.

Research Consultant

Full time (Contract), Argonne National Laboratory, Mathematics and Computer Science division, 2022

Currently developing mathematical and algorithmic techniques for directly fitting Monte Carlo simulations to experimental data or data observed in nature using a stochastic trust-region optimization algorithm.
Currently developing a workflow package to efficiently solve derivate-free stochastic optimization problems in a high performance computing environment.

software

Factory Optima

Published: February 06, 2019

Factory Optima (PAPER) is a web-based prototype system that allows manufacturing process engineers to compose, optimize and perform trade-off analysis of manufacturing service networks based on a reusable repository of performance models.

Stochastic optimization based on deterministic approximations (SODA)

Published: February 28, 2021

Stochastic optimization based on deterministic approximations (SODA)(CODE) is an open source package containing the algorithm to perform stochastic optimization based on deterministic approximations to efficiently solve the problem of finding control settings for stochastic processes in a large manufacturing service network subject to the satisfaction of stochastic feasibility constraints.

Outer optimization

Published: April 15, 2021

Outer optimization (CODE) is an open source package to assign weights and solve the tuning problem of finding optimal parameters that minimizes the a least-squares function between approximations of noisy simulations and experimental data or data observed in nature. Instead of setting weights manually based on experience and intuition, the weights are automatically adjusted using a bilevel optimization or a single level robust optimization formulation, thus yielding results efficiently that are less subjective.

Apprentice

Published: July 01, 2022

Apprentice (code and documentation) is an open source package for construction of multivariate analytic surrogate model for computationally expensive Monte-Carlo predictions. The surrogate model is used for numerical optimization of a prediction function since it can be prohibitively expensive to perform optimization over functions with the Monte-Carlo predictions. To summarize, Apprentice can be used for performing three tasks:

Construct surrogate models to computationally expensive Monte-Carlo predictions
Formulate a prediction function with surrogate models
Perform numerical optimization over the prediction function

MÆSTRO

Published: July 20, 2022

Mæstro (code and documentation) stands for Multi-fidelity Adaptive Ensemble Stochastic Trust Region Optimization and it is an open source plug n play derivate fee stochastic optimization solver. The problem being considered in MÆSTRO involves fitting Monte Carlo simulations that describe complex phenomena to experiments by finding parameters of the resource intensive and noisy simulation that yield the least squares objective function value to a noisy experimental data. This problem is solved using an active machine learning algorithm where in each iteration, a local approximation of the simulation signal and of the simulation noise is constructed over data, which is obtained by running the simulation at strategically placed design points within a trust-region around the current iterate. Then the simulation components of the objective are replaced by their approximations and this analytical and closed-form optimization problem is solved to find the next iterate within the trust-region. Then the trust region is moved and the iterations continue until a satisfactory convergence criteria is met.