No abstract

No abstract

No abstract

Each year, over 700 students take the Engineering Graphics course taught within the General Engineering Program at Clemson University. A SCALE-UP (Student-Centered Activities for Large-Enrollment Undergraduate Programs) environment is utilized to provide a highly collaborative, hands-on classroom format with a primary emphasis on learning by guided inquiry and live demonstrations rather than by traditional lecturing. One of the goals of using this format is real-time assistance and rapid feedback. In the spring term, each class day, 400 student submit a solid model file. This presents a challenge to returning feedback before the next class period. The current grading method consists of students submitting solid model files to a course management system and awarding credit for submissions matching the mass of the presented design. However, this method does not allow students to earn partial credit based on the relative accuracy of their model. To date, instructors have been unable to reward partial credit in an automated or timely manner. The objective of this research is to evaluate the use of shape similarity algorithms to provide decision making support while grading solid models for this engineering graphics course. The proposed method of automated grading is to use a solid model similarity algorithm and the mass properties to assess the relative similarity of each submission to a correct solid model. The distribution of grades using the proposed method is compared to the existing method’s distribution. Use of the proposed method ensures that the results from this research can be applied to other engineering graphics courses, regardless of the solid modeling software used.

The objective of this research is to investigate the requirements and performance of parts-of-speech tagging of assembly work instructions. Natural Language Processing of assembly work instructions is required to perform data mining with the objective of knowledge reuse. Assembly work instructions are key process engineering elements that allow for predictable assembly quality of products and predictable assembly lead times. Authoring of assembly work instructions is a subjective process. It has been observed that most assembly work instructions are not grammatically complete sentences. It is hypothesized that this can lead to false parts-of-speech tagging (by Natural Language Processing tools). To test this hypothesis, two parts-of-speech taggers are used to tag 500 assembly work instructions (obtained from the automotive industry). The first parts-of-speech tagger is obtained from Natural Language Processing Toolkit (nltk.org) and the second parts-of-speech tagger is obtained from Stanford Natural Language Processing Group (nlp.stanford.edu). For each of these taggers, two experiments are conducted. In the first experiment, the assembly work instructions are input to the each tagger in raw form. In the second experiment, the assembly work instructions are preprocessed to make them grammatically complete, and then input to the tagger. It is found that the Stanford Natural Language Processing tagger with the preprocessed assembly work instructions produced the least number of false parts-of-speech tags.