QUALITY ENGINEERING
Academic Year 2024/2025 - Teacher: GIOVANNI CELANOExpected Learning Outcomes
At the end of the course the students should be able:
- to implement statistical inference tools in quality control and improvement problems;
- to choose and implement statistical process on-line monitoring tools to carry out quality control in a specific industrial or service environemnt;
- to perform process a system capability analysis;
- to decide if a measurement system is fit for use in quality control;
- to design an efficient experimental plan to get quality improvement;
- to know the basics of Minitab® and JMP® software quality tools and to know the R software basics.
Learning is based on theory classes and practice sessions. Practice sessions consist of solving numerical problems/class works and attending digital labs on real industrial cases.
Course Structure
Required Prerequisites
Passing the course: Programmazione e Controllo della Produzione
Attendance of Lessons
Class attendance is mandatory. A roll call is done at the beginning of each class.
Students should attend at least 70% of scheduled classes, Point. 3.3, Regolamento Didattico CLM Ingegneria Gestionale. Reduced attendance is considered for students enrolled into categories described by Art. 27 of “Regolamento Didattico di AteneoDetailed Course Content
This course introduces students to evidence-based quality engineering tools commonly used either in industry or service organizations. Emphasis is given to statistical tools for on-line monitoring and data analysis to implement quality control and to experimental design techniques to achieve continuous improvement. Process capability analysis and measurement system assessment are considered, as well.
During the QE course students are introduced to the Minitab® and JMP® software for smart quality data analysis and to the basics of R software environment.Textbook Information
1. D.C. Montgomery, “Statistical Quality Control”, 6th edn or successive, Wiley. MAIN TEXT. The most widely used textbook about SQC in Universities teaching courses on Quality Engineering and in Companies implementing SQC tools.
2. AIAG Measurement System Assessment - Reference Manual 4th Edition
Course Planning
| Subjects | Text References | |
|---|---|---|
| 1 | 1.SIX SIGMA AND STATISTICAL MODELS FOR QC (Prerequisites)The Six Sigma Philosophy: The Six Sigma Roles and hierarchy, Meaning of Six Sigma. Statistical tools for quality control: Sampling from a population. Exploratory Data Analysis. Data summarization. The summary statistics: mean sample standard deviation, quantiles. Describing variation with histograms, box and whiskers plots and individual value plots. Data Visualization with Excel and Minitab. Feature relationships and correlation. Distribution Analysis. The normal distribution. Probability Plots. The Anderson Darling test. Fraction nonconforming calculation. Quality control and process monitoring. Short term and long term variability. The DMAIC Process Steps for improvement projects. Lean principles and Six Sigma. Case Studies*. Discrete distributions: Hypergeometric, Binomial, Poisson Distributions. An application to acceptance sampling of lots: Design of a single-sampling plan. AQL and RQL. Continuous distributions: Lognormal, Exponential Distributions. | Text 1(Six Sigma):Ch.1, 1.4.1 p.28-32Ch.2 (only reading)Text 3(Six Sigma):Ch.8 (DMAIC Description)Ch.9 (only reading)Text 1:Ch.3, Sections 3.1.2 to 3.3.3, 3.4, 3.5.3Ch.15. Sections 15.1-15.2.3. |
| 2 | . STATISTICAL INFERENCE IN QUALITY CONTROL AND IMPROVEMENT. Statistics and Sampling Distributions. Sampling from a Normal, Binomial and Poisson Distribution. Point Estimation of Process Parameters. Statistical Inference for a Single Sample. Inference on the Mean of a Normal Distribution, (t-test and z-test), Confidence Intervals. The p-value approach (exact calculation for the Z test and approximate calculation for the t test). The OC curve for the z-test: Choice of the Sample Size. Inference on the Variance of a Normal Distribution, (chi-squared-test). Statistical Inference for Two Samples comparison in Quality Control. Inference on the ratio of Variances of a Normal Distribution, (F-test), Confidence Interval. Inference for a Difference in Means, (z-test and t-test), Confidence Intervals. The paired t-test. Comparing two populations. Inference on More Than Two Populations: Analysis of Variance (ANOVA). Multiple comparisons: the Fisher LSD test. Multiple Linear Regression: model fitting and diagnostics, prediction. Statistical inference with Minitab. | Text 1:Ch.4, Sections 4.1 to 4.5 |
| 3 | 3. HOW STATISTICAL PROCESS CONTROL WORKS (Weeks #4-#5)Introduction. Chance and Assignable Causes. Statistical Basis of the Control Chart. Choice of Control Limits. Sample Size and Sampling Frequency. The Run Length of a control chart. Rational Subgroups. Analysis of Patterns. Adding Sensitizing Rules to Control Charts. Phase I and II Implementation of Control Charts. The Rest of Magnificent Seven: Pareto Chart, Cause and Effect Diagram. Applications of SPC (reading). | Text 1:Ch.5 |
| 4 | 4. VARIABLES AND ATTRIBUTES CONTROL CHARTS. Introduction. Control Charts for Xbar and R. The operating characteristic curve. Computation of the performance for the Xbar control chart. Control Charts for Xbar and S; the Xbar and S Control Charts with Variable Sample Size. The S^2 control chart. Shewhart Control Charts for Attributes. Control Charts for Fraction Nonconforming (p Charts). Selection of the sample size for a p control chart. Control Charts for Nonconformities (only c Charts). Control charts with Minitab. | Text 1:Ch.6, Sections 6.1 to 6.3.2,6.4 (to p.262), Ch.7, Sections 7.1, 7.2, 7.3.1 (to p.314) |
| 5 | 5. CAPABILITY ANALYSIS OF PROCESS AND MEASUREMENT SYSTEMS. Introduction. Process Capability Ratios: Cp, Cpk. Process Capability Analysis with Control Charts. Confidence intervals (only Cp) and tests on process capability ratios*. Measurement system analysis: reference value and resolution; location variation: bias, linearity, stability, testing for location variation; width variation: precision error, repeatability, reproducibility, testing for width variation, Gauge R&R study: and method with Excel*. Part variation, Total variation. Gauge R&R Analysis with Minitab. | Text 1:Ch.8, Sections 8.1, 8.3 to 8.3.2.Text 4:p.56-69, p.77-92. |
| 6 | 6. BASIC EXPERIMENTAL DESIGN FOR PROCESS IMPROVEMENT AND OPTIMIZATION. Introduction. Guidelines for designing experiments. Factorial experiments. Main effects and interactions. Experiments with more than two levels per factor. The 2k factorial designs with k 2 factors. Single replication of 2k designs. The fractional replication of 2k designs. Process optimization. Introduction to response surface methods. Experimental design with Minitab. | Text 1.Ch 13. Sections 13.1 to 13.5.4. Section 13.6. Ch. 14. Section 14.1 |