Quality in the Era of Industry 4.0

5Predictive Quality

5.1 Introduction

Predictive Quality is a relatively new paradigm that has emerged with the advent and convergence of data analytics, machine learning, and quality assurance methodologies. Its roots trace back to the early applications of statistics in quality control during the early 20th century. However, it was not until the late 20th century, with the rise of computing power and the digitization of manufacturing processes, that the concept began to take shape in a more concrete form.

The initial applications of Predictive Quality were rudimentary, relying primarily on simple statistical models to predict future outcomes based on historical data. However, with the advent of more advanced data analytics techniques and the exponential growth of available data in the 21st century, these models have become increasingly sophisticated.

Over the past few decades, predictive analytics [1, 2] has become a key component of quality management in a variety of sectors, from manufacturing to healthcare. With the advent of Industry 4.0, the increased digitization and connectivity of industrial processes have enabled real‐time data collection and analysis on an unprecedented scale. This, in turn, has facilitated the rise of Predictive Quality [3, 4], making it possible to predict and prevent quality issues before they arise.

Research on Predictive Quality has focused on developing more advanced and accurate prediction models, exploring the use of machine learning and ...