Measurement's noise, filtered by a type-1 neuro-fuzzy technique in quality assurance

作者：Montes Dorantes Pascual Noradino; Jimenez Gomez Marco Aurelio; Mexicano Santoyo Adriana; Maximiliano Mendez Gerardo

来源：International Journal of Advanced Manufacturing Technology, 2017, 92(1-4): 755-763.

DOI：10.1007/s00170-017-0151-2

• Neuro-fuzzy system
• Knowledge-based system
• ANFIS
• Image processing
• Noise filtering

Measurements are the core of quality systems. The calibration of the measurement devices is a form of evaluating it. The variability of these measurement devices is verified to know the variation inherited in the measurement tool. Additionally, the dynamics of the actual production systems cannot be satisfied by the classic approaches of the human visual inspection. This happens because they exceed the human capacities, and this phenomenon causes the loss of reliability at the outputs of the system. This paper presents a hybrid model of adaptive neuro-fuzzy inference system (ANFIS) to evaluate quality features. Also, for this purpose, it offers knowledge-based expert system able to do the quality assurance tasks by learning and adaptation. The obtained results provide an acceptable error rate for this class of systems to run at the speed of the actual manufacturing system.

• 出版日期2017-9