A zero defect strategy requires reliable information to support any decision. Reliable information requires measured data from the process and the product. However, in a real production scenario, availability of data does not guarantee by itself an effective information build-up. In particular, measurement uncertainty must be known, kept under control and adequately managed so to keep the confidence level on measured data at the required level for decision making.
The GO0D MAN project will implement Smart On-Line Inspection Tools, i.e. hardware-software cyber-physical systems exhibiting smart behaviours, such as self-adaptation of the sensing functions to the variable product/process parameters/characteristics and to the environmental changes, sensor self-calibration and self-diagnosis.
In such a context, self-adaptation refers to the search for an optimal configuration of the system parameters, when it is subjected to real measurement conditions. This is needed because real measurement conditions can even drastically differ from the theoretical ones. A self-adapting quality control system performs a control action on an influencing parameter acting on the measurement process, so to keep measurement uncertainty at the desired level. Practical examples could be an automatic re-positioning of a transducer (of a camera, for example) around the theoretical optimal position in order to center the target object of the image, or the control of the illumination in a vision system for image contrast enhancement.
Self-calibration can be considered a specific case of self-adaptation; implementing self-calibration is feasible whenever a reference input can be periodically acquired so to correct eventual drift of sensor characteristics and compensate parametric variations. Finally, a measurement system could periodically perform a self-diagnosis test, in order to verify its performance and eventually adopt corrective actions.
Self-diagnosis is very effective to avoid acquiring and processing data from defected measurement systems and again contributes to minimize measurement uncertainty, hence to maximize the confidence level on the diagnosis made on measured data.
The quality control station hosting the Smart On-Line Inspection Tools is capable of performing a test on the component/product under inspection; once associated to an agent, which confers to it autonomous behaviors, is by all means a cyber-physical system.
Specific quality control systems will be developed for each use case of the GO0D MAN project. However, despite different, they will have in common the exploitation of non-contact approaches and smart features.