scholarly journals THE ROLE OF MACHINE LEARNING FOR FLEXIBILITY AND REAL OPTIONS ANALYSIS IN ENGINEERING SYSTEMS DESIGN

2021 ◽  
Vol 1 ◽  
pp. 3121-3130
Author(s):  
Cesare Caputo ◽  
Michel-Alexandre Cardin
Keyword(s):  
Machine Learning ◽  
Real Options ◽  
Systems Design ◽  
Engineering Systems ◽  
Real Options Analysis ◽  
Domain Experts ◽  
Design Variables ◽  
Parameters Uncertainty ◽  
Infrastructure System ◽  
Computational Intractability

AbstractFlexibility analysis helps improve the expected value of engineering systems under uncertainty (economic and/or social). Designing for flexibility, however, can be challenging as a large number of design variables, parameters, uncertainty drivers, decision making possibilities and metrics must be considered. Many available techniques either rely on assumptions that are not suitable for an engineering setting, or may be limited due to computational intractability. This paper makes the case for an increased integration of Machine Learning into flexibility and real options analysis in engineering systems design to complement existing design methods. Several synergies are found and discussed critically between the fields in order to explore better solutions that may exist by analyzing the data, which may not be intuitive to domain experts. Reinforcement Learning is particularly promising as a result of the theoretical common grounds with latest methodological developments e.g. decision-rule based real options analysis. Relevance to the field of computational creativity is examined, and potential avenues for further research are identified. The proposed concepts are illustrated through the design of an example infrastructure system.

Digital Coaching System for Real Options Analysis with Multi-expert and Machine Learning Support

2021 ◽  
pp. 455-473
Author(s):  
Jani Kinnunen ◽  
Mikael Collan ◽  
Irina Georgescu ◽  
Zahra Hosseini
Keyword(s):  
Machine Learning ◽  
Real Options ◽  
Learning Support ◽  
Real Options Analysis

Prospect Theory-based Real Options Analysis for Noncommercial Assets

2015 ◽  
Vol 1 (1) ◽  
Author(s):  
Joshua T. Knight ◽  
David J. Singer
Keyword(s):  
Real Options ◽  
Prospect Theory ◽  
High Speed ◽  
Cash Flows ◽  
Engineering System ◽  
Engineering Systems ◽  
Dynamic Nature ◽  
Real Options Analysis ◽  
Rigorous Approach ◽  
Technological Opportunities

When an engineering system has the ability to change or adapt based on a future choice, then flexibility can become an important component of that system’s total value. However, evaluating noncommercial flexible systems, like those in the defense sector, presents many challenges because of their dynamic nature. Designers intuitively understand the importance of flexibility to hedge against uncertainties. In the naval domain, however, they often do not have the tools needed for analysis. Thus, decisions often rely on engineering experience. As the dynamic nature of missions and new technological opportunities push the limits of current experience, a more rigorous approach is needed. This paper describes a novel framework for evaluating flexibility in noncommercial engineering systems called prospect theory-based real options analysis (PB-ROA). While this research is motivated by the unique needs of the U.S. Navy ship design community, the framework abstracts the principles of real options analysis to suit noncommercial assets that do not generate cash flows. One contribution of PB-ROA is a systematic method for adjusting agent decisions according to their risk tolerances. The paper demonstrates how the potential for loss can dramatically affect decision making through a simplified case study of a multimission variant of a theoretical high-speed connector vessel.

A Comprehensive Robust Design Approach for Decision Trade-Offs in Complex Systems Design

1999 ◽  
Vol 123 (1) ◽  
pp. 1-10 ◽  
Author(s):  
Monu Kalsi ◽  
Kurt Hacker ◽  
Kemper Lewis
Keyword(s):  
Robust Design ◽  
Systems Design ◽  
Decision Makers ◽  
Engineering Systems ◽  
Trade Offs ◽  
Design Variables ◽  
Complex Engineering ◽  
The Cost ◽  
Passenger Aircraft

In this paper we introduce a technique to reduce the effects of uncertainty and incorporate flexibility in the design of complex engineering systems involving multiple decision-makers. We focus on the uncertainty that is created when a disciplinary designer or design team must try to predict or model the behavior of other disciplinary subsystems. The design of a complex system is performed by many different designers and design teams, each of which may only have control over a portion of the total set of system design variables. Modeling the interaction among these decision-makers and reducing the effect caused by lack of global control by any one designer is the focus of this paper. We use concepts from robust design to reduce the effects of decisions made during the design of one subsystem on the performance of the rest of the system. Thus, in a situation where the cost of uncertainty is high, these tools can be used to increase the robustness, or independence, of the subsystems, enabling designers to make more effective decisions. To demonstrate the usefulness of this approach, we consider a case study involving the design of a passenger aircraft.

A Distributed Pool Architecture for Highly Constrained Optimization Problems in Complex Systems Design

2013 ◽  
Vol 13 (3) ◽  
Author(s):  
Vijitashwa Pandey ◽  
Zissimos P. Mourelatos
Keyword(s):  
Design Optimization ◽  
Optimization Problems ◽  
Mechanical Design ◽  
Solution Process ◽  
Systems Design ◽  
Mixed Integer ◽  
Engineering Systems ◽  
Design Problems ◽  
Design Variables ◽  
Complex Engineering

Optimal design of complex engineering systems is challenging because numerous design variables and constraints are present. Dynamic changes in design requirements and lack of complete knowledge of subsystem requirements add to the complexity. We propose an enhanced distributed pool architecture to aid distributed solving of design optimization problems. The approach not only saves solution time but is also resilient against failures of some processors. It is best suited to handle highly constrained design problems, with dynamically changing constraints, where finding even a feasible solution (FS) is challenging. In our work, this task is distributed among many processors. Constraints can be easily added or removed without having to restart the solution process. We demonstrate the efficacy of our method in terms of computational savings and resistance to partial failures of some processors, using two mixed integer nonlinear programming (MINLP)-class mechanical design optimization problems.

scholarly journals Analyzing Real Options and Flexibility in Engineering Systems Design using Decision Rules and Deep Reinforcement Learning

2021 ◽  
pp. 1-31
Author(s):  
Cesare Caputo ◽  
Michel-Alexandre Cardin
Keyword(s):  
Reinforcement Learning ◽  
Real Options ◽  
Decision Rules ◽  
Systems Design ◽  
Computational Design ◽  
Risk Tolerance ◽  
Action Space ◽  
Waste To Energy ◽  
Engineering Systems ◽  
Standard Design

Abstract Engineering systems provide essential services to society e.g., power generation, transportation. Their performance, however, is directly affected by their ability to cope with uncertainty, especially given the realities of climate change and pandemics. Standard design methods often fail to recognize uncertainty in early conceptual activities, leading to rigid systems that are vulnerable to change. Real Options and Flexibility in Design are important paradigms to improve a system's ability to adapt and respond to unforeseen conditions. Existing approaches to analyze flexibility, however, do not leverage sufficiently recent developments in machine learning enabling deeper exploration of the computational design space. There is untapped potential for new solutions that are not readily accessible using existing methods. Here, a novel approach to analyze flexibility is proposed based on Deep Reinforcement Learning (DRL). It explores available datasets systematically and considers a wider range of adaptability strategies. The methodology is evaluated on an example waste-to-energy system. Low and high flexibility DRL models are compared against stochastically optimal inflexible and flexible solutions using decision rules. The results show highly dynamic solutions, with action space parametrized via artificial neural network. They show improved expected economic value up to 69% compared to previous solutions. Combining information from action space probability distributions along expert insights and risk tolerance helps make better decisions in real-world design and system operations. Out of sample testing shows that the policies are generalizable, but subject to tradeoffs between flexibility and inherent limitations of the learning process.

Sign in / Sign up

Export Citation Format

Share Document