Teaching plan for the course unit

(Short version)

 Català English Close

 General information

Course unit name: Industrial Statistics

Course unit code: 361250

Coordinator: XAVIER TORT-MARTORELL LLABRES

Department: Faculty of Economics and Business

Credits: 6

Single program: S

 Estimated learning time Total number of hours 150

 Face-to-face and/or online activities 60
 -  Lecture with practical component Face-to-face and online 15 -  Problem-solving class Face-to-face and online 15 -  IT-based class Face-to-face 30
 Supervised project 30
 Independent learning 60

 Learning objectives
 Referring to knowledge The objective is for students to learn to design and implement an experiment plan in order to discover how a series of variables (controllable or otherwise) of a process affect a quality of interest. Students should also appreciate the importance of combating variability to improve quality, know how to characterize the variability of a process and be familiar with techniques to reduce variability and minimize it. Specifically, at the end of the course students should be able to:   — Select designs that allow them to analyse the behaviour of a product or process both in terms of the mean and the variance transmitted by uncontrollable factors.   — Analyse the effect of control and noise factors in the response of interest and select the most robust conditions.   — Select designs that allow them to explore the response surface with second-order polynomials (central composite design, Box-Behnken design, etc.).   — Explore the region of interest of the experimental variables that maximize (minimize) the response and study the nature of the surface.   — Design real experiments and implement them following a sequential strategy, from the experimental approach to be adopted to the drawing of conclusions.   — Understand how sophisticated control graphics work and use them.   — Implement a statistical process control in a real process, taking into account the nature of the process and the associated costs.   — Carry out repeatability and reproducibility studies to guarantee that the measurement system used in a process is adequate.  Referring to abilities, skills — Obtain information of interest and learn from books and articles.   — Work in groups to agree on decisions and solve problems together.   — Work as a team to agree on decisions and solve problems together.   — Communicate ideas and results effectively, both in writing and orally.

 Teaching blocks

1. Six Sigma improvement methodology

*   Need for improvement. Organizational aspects, roles and responsibilities. Improvement methodology: stages. Objectives and tasks of each of the five stages: define, measure, analyse, improve and control. Repeatability and reproducibility (R&R) studies. Cases and exercises

2. Design of industry experiments and response surface methodology

*   Importance of experimentation in an industrial environment. Review of factorial designs at two levels. Blocking in factorial designs. Central points. Response surface using first degree polynomials. Use of the "steepest ascent" to approach the region of interest. Response surface using second degree polynomials. Central composite and Box-Behnken designs. Fitting the model

3. Statistical process control: monitoring and best fit

*   Selection of appropriate control charts depending on the variable to be monitored. Concept of rational subgroups and ARL. Limitations of Shewart control charts. Autocorrelated data and non-stationary processes. Predictions using an EWMA model. Continuous and periodic fit of non-stationary processes

4. Case studies of the application of statistics in industry and the services sector

*   The case of silicone tubes. Case of the professional cooperative savings bank

Book

BOX, George E. P. et al. Statistics for experimenters design, innovation, and discovery. 2nd ed. Hoboken: Wiley Interscience, 2005

MONTGOMERY, Douglas C. Diseño y análisis de experimentos. México: Limusa Wiley, 2002

MYERS, Raymond H. et al. Response surface methodology: process and product optimization. Hoboken: Wiley Interscience, 2009

HAHN, Gerald J. et al. The role of statistics in business and industry. Hoboken, New Jersey: Wiley, 2008