The evolution of computers and communication technology has brought with it a surge of powerful devices and gadgets capable of capturing data unlike ever before. These raw, unorganized facts alone are useless. With the right system though, data can be effectively manipulate and manage to produces valuable information used by industry leaders to make accurate and timely decisions. Oftentimes this data is so massive that it's difficult to process using traditional techniques. Inevitably, a new system will be required to keep pace with the digital age that promises explosive growth.
Shing Chang, a quality engineer, uses algorithms to turn raw data into relevant information. With more than 20 years' experience, his research has benefited various manufacturing, service and health care organizations by designing production systems that inspire more confident decision making.
Four phases of statistical process control: a big data framework
Chang is currently researching an alternative method for statistical process control (SPC). The current approach uses a two-phase method -- Phase 1 and 2. Chang is testing a four-phase process aimed to improve quality control in modern production environments. His discoveries have the potential to expand SPC capabilities beyond current industry standards to improve operational effectiveness.
Research objectives - Develop a four-phase SPC process to better monitor quality control in modern production environments.
1. Phase 0: Identify parameters for monitoring
2. Phase 1 & 2: Monitor real-time large quantities of fast flowing data
3. Phase 3: Assess long-term process for quality assurance
Additional research interests
- Multivariate statistical process control
- Nonlinear profile monitoring
- Neural networks and fuzzy set applications in quality engineering
- Multivariate experimental design