Search for: All records

Abstract Existing models for evaluating early-stage designs typically assume that solutions follow dominant solving approaches in the problem domain. While effective for comparing alternatives within dominant solving approaches, these models often undervalue or overlook solutions that use atypical or novel approaches, especially when these differ significantly in key design variables. This bias prematurely constrains the design space and becomes a pressing problem as firms increasingly leverage nontraditional sources of innovation and creativity (e.g., through crowdsourcing). To address this, we introduce a modeling approach that enables comparison of design solutions from multiple solving paradigms. It represents engineering design as a problem-solving process, with solutions generated by selecting concepts and embodiments to achieve specific functions. The model simulates how different solvers navigate this process based on their expertise, producing a variety of solutions rather than those limited to dominant strategies. The quality of each solution is represented as a probability distribution over performance and cost. The model’s effectiveness is demonstrated using a robotic arm design problem, leveraging a dataset from a large-scale field experiment. Results show that the model can estimate performance and cost across different solving approaches, capturing valuable solutions that traditional models would miss. This is particularly significant when evaluating designs from nontraditional solvers, as they are more likely to diverge from dominant solving paradigms. As firms increasingly turn to nontraditional sources of expertise for innovation, this modeling approach could enable comprehensive identification and fair assessment of a range of design solutions. 

Abstract Engineering design relies heavily on heuristics, yet there is a lack of systematic methods for identifying and validating design heuristics. This paper introduces a computational approach to representing engineering design problems that involve decomposition and assignment decisions, facilitating systematic extraction of generalizable heuristics. We model design processes using a Markov Decision Process (MDP) framework, characterizing problems through attributes of the problem space, solver capabilities, and trade-offs embedded within preference functions. Reinforcement learning methods are employed to learn optimal policies, from which we extract inclusionary and exclusionary heuristics using Gaussian Mixture Models. The effectiveness of the approach is demonstrated through two case studies: solver-aware system architecting (SASA) for a robotic arm design and sequential information acquisition in parametric design optimization. The results highlight the context-dependent nature of learned heuristics, demonstrating how problem complexity, designer preferences, and solver characteristics influence their selection. 

Abstract This paper introduces an educational multiplayer web-based game to teach solver-aware systems architecting (SASA) heuristics, along with preliminary findings regarding its educational value. SASA is a framework for leveraging the relative strengths of domain experts, crowds, and specialists to design innovative complex systems by pairing technical problem decomposition with solver assignment decisions. This new line of thinking calls for a paradigm shift from the typical approach to system development, as it greatly increases the complexity of the problem space by expanding the set of actions designers could pursue by introducing solver-assignment decisions in addition to the already vast technical decomposition decisions. To that end, heuristics could provide an effective mechanism to navigate this landscape by leading towards satisficing solutions in a cost and time-efficient manner. The game was piloted on 30 participants. It first introduced the basic SASA concepts, and then asked participants increasingly more difficult system architecting problems that ranged from subproblem-level (module) heuristics to system-level problems with two counterbalancing objectives. Findings suggest that the game could be an effective tool for higher-order learning, as by the end of the game, all participants exhibited acceptable command of using SASA heuristics for making system-level tradeoffs. Future work could leverage the game’s rich data collection mechanism to investigate biases and background factors that influence designer learning outcomes. 

Abstract Systems design involves decomposing a system into interconnected subsystems and allocating resources to teams responsible for designing each subsystem. The outcomes of the process depend on how well limited resources are allocated to different teams, and the strategy each team uses to design the subsystems. This article presents an approach based on hierarchical reinforcement learning (RL) to generate heuristics for solving complex design problems under resource constraints. The approach consists of formulating systems design problems as hierarchical multiarmed bandit (MAB) problems, where decisions are made at both the system level (allocating budget across subsystems) and the subsystem level (selecting heuristics for sequential information acquisition). The approach is demonstrated using an illustrative example of a race car optimization in The Open Racing Car Simulator (TORCS) environment. The results indicate that the RL agent can learn to allocate resources strategically, prioritize the subsystems with the greatest influence on overall performance, and identify effective information acquisition heuristics for each subsystem. For example, the RL agent learned to allocate a larger portion of the budget to the gearbox subsystem, which has a higher-dimensional design space compared to other subsystems. The results also indicate that the extracted heuristics lead to convergence to high-performing car configurations with greater efficiency when compared to using Bayesian optimization for design. 

Abstract This article proposes the solver-aware system architecting framework for leveraging the combined strengths of experts, crowds and specialists to design innovative complex systems. Although system architecting theory has extensively explored the relationship between alternative architecture forms and performance under operational uncertainty, limited attention has been paid to differences due to who generates the solutions. The recent rise in alternative solving methods, from gig workers to crowdsourcing to novel contracting structures emphasises the need for deeper consideration of the link between architecting and solver-capability in the context of complex system innovation. We investigate these interactions through an abstract problem-solving simulation, representing alternative decompositions and solver archetypes of varying expertise, engaged through contractual structures that match their solving type. We find that the preferred architecture changes depending on which combinations of solvers are assigned. In addition, the best hybrid decomposition-solver combinations simultaneously improve performance and cost, while reducing expert reliance. To operationalise this new solver-aware framework, we induce two heuristics for decomposition-assignment pairs and demonstrate the scale of their value in the simulation. We also apply these two heuristics to reason about an example of a robotic manipulator design problem to demonstrate their relevance in realistic complex system settings.