Using RBF algorithm for Scanning Acoustic Microscopy inspection of flip chip

Abstract This chapter presents several materials and processes related to soldering technology. It first provides information on lead-free solders. This is followed by sections devoted to flip-chip processes, diffusion soldering, and modeling. Scanning acoustic microscopy and fine-focus x-ray techniques are also included. The chapter then describes several evaluation procedures and tests developed to measure solderability. Reference is also made to the production of calibration standards of solderability. The chapter also describes the characteristics of reinforced solders and amalgams as solders and the strategies to boost the strength of solders. Further, the chapter considers methods for quantifying the mechanical integrity of joints and predicting their dimensional stability under specified environmental conditions. It discusses the effects of rare earth elements on the properties of solders. The chapter concludes with information on advanced joint characterization techniques.

Download Full-text

Machine Learning Assisted Signal Analysis in Acoustic Microscopy for Non-Destructive Defect Identification

ISTFA 2019: Conference Proceedings from the 45th International Symposium for Testing and Failure Analysis ◽

10.31399/asm.cp.istfa2019p0035 ◽

2019 ◽

Author(s):

Michael Kögel ◽

Sebastian Brand ◽

Frank Altmann

Keyword(s):

Machine Learning ◽

Failure Analysis ◽

Human Error ◽

Flip Chip ◽

Acoustic Microscopy ◽

Classification Model ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Scanning Acoustic Microscopy ◽

Chip Technology

Abstract Signal processing and data interpretation in scanning acoustic microscopy is often challenging and based on the subjective decisions of the operator, making the defect classification results prone to human error. The aim of this work was to combine unsupervised and supervised machine learning techniques for feature extraction and image segmentation that allows automated classification and predictive failure analysis on scanning acoustic microscopy (SAM) data. In the first part, conspicuous signal components of the time-domain echo signals and their weighting matrices are extracted using independent component analysis. The applicability was shown by the assisted separation of signal patterns to intact and defective bumps from a dataset of a CPU-device manufactured in flip-chip technology. The high success-rate was verified by physical cross-sectioning and high-resolution imaging. In the second part, the before mentioned signal separation was employed to generate a labeled dataset for training and finetuning of a classification model based on a one-dimensional convolutional neural network. The learning model was sensitive to critical features of the given task without human intervention for classification between intact bumps, defective bumps and background. This approach was evaluated on two individual test samples that contained multiple defects in the solder bumps and has been verified by physical inspection. The verification of the classification model reached an accuracy of more than 97% and was successfully applied to an unknown sample which demonstrates the high potential of machine learning concepts for further developments in assisted failure analysis.

Download Full-text

Edge Enhancement for Acoustic Microscopy of Flip Chip Devices

ISTFA 2005: Conference Proceedings from the 31st International Symposium for Testing and Failure Analysis ◽

10.31399/asm.cp.istfa2005p0199 ◽

2005 ◽

Author(s):

Daniel J. D. Sullivan ◽

Andrew J. Komrowski ◽

Luis A. Curiel ◽

Kevan V. Tan

Keyword(s):

Flip Chip ◽

Acoustic Microscopy ◽

Scanning Acoustic Microscopy ◽

Edge Enhancement ◽

New Materials ◽

Ir Imaging ◽

The Hours ◽

Edge Cracks ◽

Standard Practices ◽

Non Destructive

Abstract Scanning acoustic microscopy (SAM) is a non-destructive tool for analysis of packaged devices. New materials, package configurations, and technologies have required adaptation of standard practices in SAM. The detection of cracked die, voids, or delamination in the underfill or package are standard issues for SAM. SAM can routinely detect large cracks through the central 80% of the die; however, the occurrence of smaller cracks at the edge of the flip chip die is problematic. This article proposes a model in which alteration in the standard SAM parameters, the gain and Time-of-Flight, enable detection of die edge cracks in assembled Flip Chip devices. IR imaging after thinning and polishing of the die confirms the die edge cracks. The SAM analysis can replace the IR imaging for detection of small die edge cracks taking minutes to complete instead of the hours involved in the sample preparation for IR imaging.

Download Full-text