Midterm1_333

.pdf

School

Hobart & William Smith Colleges *

*We aren’t endorsed by this school

Course

MISC

Subject

Aerospace Engineering

Date

Oct 30, 2023

Type

pdf

Pages

Uploaded by troysteiner02

Your Name: ____________________ Prof. Liu MAE 333 Data Analytics for Engineers 1 MAE 333 Midterm Exam Rules Please read the full exam rule that is posted on class blackboard under “Midterm” session before you start this exam. Here are some important items that you should know. Individual Work: • This exam is an individual assignment. Collaboration with others is prohibited. • You may not seek assistance from anyone except me (Dr. Liu) or TA (Romesh) on the exam. For example, you may not talk to other students about the exam problems, and you may not look at other students' exams. Resources Allowed: • You can use your course materials, lecture notes, and any resources provided by Dr. Liu. • You may use software and tools that have been discussed or recommended in the course. • You may use website resources to help you understand the dataset. • ChatGPT and other AI chatbots are prohibited from using for this exam. Questions and Clarifications: • If you have any questions or need clarification on the exam questions, contact the instructor (xliu127@syr.edu) or teaching assistant (rsprasad@syr.edu) via email or office hours. • Office hours: o Dr. Liu, 10/19 11:00 – 12:20, 359 Link o Romesh, 10/19 15:00 - 17:00, 275 Link o Dr. Liu, 10/20 15:30 - 17:00, Zoom: https://syracuseuniversity.zoom.us/j/97344704571 Submission Guidelines: • Your completed exam must be submitted electronically by 10/20, 11:59 PM. • Late submissions will not be accepted unless prior arrangements are made with the instructor. • You are expected to complete the exam on this Word document directly. After the completion, converted this Word document to PDF and submit it to o Gradescope, please match pages for the questions. o Turnitin, folder is located under “Midterm” . o Submit .R code file to blackboard code submission folder , under “Midterm” . Honor Pledge I affirm that I will not give or receive any unauthorized help on this exam, and that all work will be my own. Signature: Stephen M Fisher

Your Name: ____________________ Prof. Liu MAE 333 Data Analytics for Engineers 2 Please answer all the questions below, and make sure to include all your work to receive a full grade. If a question involves creating a graph or table, it is mandatory to take a screenshot and attach it to your response as part of your answer. For calculation questions, show your steps (or code in R). In this exam, we will be working on a data set from a 3D printer. The data was collected based on the Ultimaker S5 3-D printer settings and filaments. Material and strength tests were carried out on a Sincotec GMBH tester capable of pulling 20 kN. The setting parameters for the 3-D printer include: • Layer Height (mm) • Wall Thickness (mm) • Infill Density (%) • Infill Pattern • Nozzle Temperature (C°) • Bed Temperature (C°) • Print Speed (mm/s) • Material • Fan Speed (%) Output Parameters: (Measured) • Roughness (μm) • Tensile (ultimate) Strength: three levels, Low (less than or equal to 15 MPa), Medium (greater than 15 MPa, less than or equal to 26 MPa), and High (great than 26 MPa) • Elongation (%) The study aims to determine how much of the adjustment parameters in 3d printers affect print quality, accuracy, and strength. 1. List all the variables that are categorical. The variables that are categorical are Infill Pattern, Material, and Tensile strength. 2. List all the variables that are numerical. The variables that are numerical are layer height, wall thickness, infill density, nozzle temperature, bed temperature, print speed, fan speed, roughness, and elongation. 3. Briefly overview your dataset and understand the attributes. Are there any NAs in the dataset? If yes, please remove them before you proceed for the next step. Use str() to show how many variables and observations you have after cleanup. Yes, there are NAs in the dataset.

Your Name: ____________________ Prof. Liu MAE 333 Data Analytics for Engineers 3 4. Find the appropriate summary statistics and graphical display of the data to assess the following research question, “ What is the proportion of tensile strength that qualifies as high? ” 1) Use R to get the counts for each level of the variable. 2) Calculate the value of summary statistics to answer the research question. Write your answer below or screenshot the result from R. 3) If we create a random variable X using the following mapping rules: High -> 3, Medium -> 2, Low -> 1. Is this a discrete or continuous random variable? This is a discrete random variable. 4) In R, create a new attribute named “tensile _strength _RV” to your dataframe following the rules mentioned in 3). Use summary () to overview this variable. Screen shot your R output. 5) Create a Probability Mass Function (PMF) table for the variable “tensile_strength_RV”. 6) What is the expected value for the variable X? Interpret your result. The expected value is 1.96. The expected value is the mean of tensile_strength_RV.

Your Name: ____________________ Prof. Liu MAE 333 Data Analytics for Engineers 4 5. Determine the suitable summary statistics and graphical representation of the data to evaluate the research question , “ Does the proportion of tensile strength vary across different materials? ” 1) What is the explanatory variable to be assessed in this research question? Material is the explanatory variable. 2) Use the variabl e “tensile_strength” to explore this question. What would be the best way to summarize the relationship between these two variables? Demonstrate your summarization below. 3) Construct a row or column proportion table below whichever answers the question better.

Your Name: ____________________ Prof. Liu MAE 333 Data Analytics for Engineers 5 4) Answer the research question using summary statistics generated from above. Yes, the proportion of tensile strength varies across the different materials, because we can see that their proportions are in fact different for the two materials. They are opposites for high and low, but the same for medium. 5) Considering that each observation in this dataset represents a final 3D printed part, excluding the ones with missing values, what is the probability of randomly selecting a PLA part with high tensile strength? From the previous table, 0.625, or 62.5%. 6. Determine the suitable summary statistics and graphical representation of the data to evaluate the research question, “ Does the use of a honeycomb infill pattern result in greater elongation compared to a grid infill pattern? ” 1) Create a five-number summary of the response variable for each level of the explanatory variable. 2) Use honeycomb – crib to answer the research question. Interpret the value of the summary statistics in context of the problem. The summary statistics of the response variable for each level of the explanatory variable provides useful context. For example, the third number is the median, and this is useful as the median for honeycomb is greater than grid. This means that on average honeycomb infill results in greater elongation than grid, so yes, the use of honeycomb results in greater elongation. The distance between the 1st and 3 rd quartiles is pretty much the same, so this shows that there is a similar spread for both. Also, the min and max values are roughly the same as well.

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version