Estimation of Wire Bonding State by the Ensemble Based MT Method and Thin AE Sensor

Abstract

With non-destructive, simple, and low-priced testing methods (which can be applied to manufacturing processes), we can assure high quality production by applying inspection across all products. Quality assurance in wire bonding is possible by using state diagnosis which utilizes detection of elastic waves close to the bonded joint. We succeeded in detecting elastic waves under difficult conditions and in harsh environments by using a thin AE (Acoustic Emission) sensor developed using AlN piezoelectric thin film technology. We attempted to conduct a wire bonding state estimation using the MT (Mahalanobis-Taguchi) method which is a simple and powerful pattern recognition technique. Two issues are raised when applying this method to the manufacturing process: 1) a large probability bias caused by an insufficient number of data samples, and 2) securing homogeneity of the Unit Space. In this paper, we present a state diagnosis method utilizing a real-world application which uses piezoelectric thin film sensing and an improved MT method to which ensemble learning is applied. Performance of this proposed method is also examined through a common benchmark dataset to assure efficient operation in any manufacturing process.

Non-destructive Anomaly Detection Method for Wire Bonding Using a Thin Film AE Sensor

“…12, 2019 crimination method based on wire bonding pull test results, using machine learning based on AE waveform input obtained by a thin film AE sensor. [6] In that study, it was difficult to collect many samples because wire bonding was manually performed using a manual wire bonder.…”

“…In a previous study, [6] we proposed an anomaly detection method using MT method based on quality engineering method. In the proposed method, feature vectors determined through AE waveform analysis are input, and pass/fail is determined based on the fracture load in wire pull testing.…”