Given the foundational role of system requirements in design projects, designers can benefit from classifying, comparing, and observing connections between requirements. Manually undertaking these processes, however, can be laborious and time-consuming. Previous studies have employed Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art natural language processing (NLP) deep neural network model, to automatically analyze written requirements. Yet, it remains unclear whether BERT can sufficiently capture the nuances that differentiate requirements between and within design documents. This work evaluates BERT’s performance on two requirement classification tasks (one inter- document and one intra-document) executed on a corpus of 1,303 requirements sourced from five system design projects. First, in the “parent document classification” task, a BERT model is fine-tuned to classify requirements according to their originating project. A separate BERT model is then fine-tuned on a “functional classification” task where each requirement is classified as either functional or nonfunctional. Our results also include a comparison with a baseline model, Word2Vec, and demonstrate that our model achieves higher classification accuracy. When evaluated on test sets, the former model receives a Matthews correlation coefficient (MCC) of 0.95, while the latter receives an MCC of 0.82, indicating BERT’s ability to reliably distinguish requirements. This work then explores the application of BERT’s representations, known as embeddings, to identify similar requirements and predict requirement change.

This paper compares the economic viability and performance outcomes of two different thermoelectric device architectures to determine the advantages and appropriate use of each configuration. Hybrid thermoelectric coolers (TECs) employ thin-film thermoelectric materials sandwiched between a plastic substrate and form a corrugated structure. Roll-to-roll (R2R) manufacturing and low-cost polymer materials offer a cost advantage to the hybrid architecture at the sacrifice of performance capabilities while conventional bulk devices offer increased performance at a higher cost. Performance characteristics and cost information are developed for both hybrid and conventional bulk single-stage thermoelectric modules. The design variables include device geometry, electrical current input, and thermoelectric material type. The tradeoffs between cooling performance and cost will be explored, and the thermoelectric system configuration is analyzed for both hybrid and conventional bulk TECs.

A system must continue to meet stakeholder needs throughout its service life to maintain value. Excess that is embedded into components during the design phase can enable in-service system evolution when new or changed requirements are introduced. However, while the concept of excess has been established in the literature, it is not clear how to identify and quantify the set of excesses in a particular design. This paper uses component properties and functional flow information to map and quantify the excess that exists within a system. Understanding the functional flow relationships between components allows for the bottlenecks at component interfaces to be identified. Those flows that do not limit the potential evolvability of a system can be removed from consideration, allowing for critical interface parameters to be highlighted and their capabilities quantified. The method is demonstrated on a consumer heat gun, where quantifying the excess within components allows for a reduced map to be created with irrelevant flows removed. Finally, changes to the system are explored to demonstrate how knowledge of component excess can be used to initially validate a proposed evolution.

Invasive aquatic plant species can expand rapidly throughout water bodies and cause severely adverse economic and ecological impacts. While mechanical, chemical, and biological methods exist for the identification and treatment of these invasive species, they are manually intensive, inefficient, costly, and can cause collateral ecological damage. To address current deficiencies in aquatic weed management, this paper details the development of a small fleet of fully autonomous boats capable of subsurface hydroacoustic imaging (to scan aquatic vegetation), machine learning (for automated weed identification), and herbicide deployment (for vegetation control). These capabilities aim to minimize manual labor and provide more efficient, safe (reduced chemical exposure to personnel), and timely weed management. Geotagged hydroacoustic imagery of three aquatic plant varieties (Hydrilla, Cabomba, and Coontail) was collected and used to create a software pipeline for subsurface aquatic weed classification and distribution mapping. Employing deep learning, the novel software achieved a classification accuracy of 99.06% after training.