Development of an automated solder inspection system with neural network using oblique computed tomography

Atsushi Teramoto, Takayuki Murakoshi, Masatoshi Tsuzaka, Hiroshi Fujita

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The high density LSI packages such as BGA is being utilized in the car electronics and communications infrastructure products. These products require a high-speed and reliable inspection technique for their solder joints. In this paper, an automated X-ray inspection system for BGA mounted substrate based on oblique computed tomography are proposed. Automated inspection consisted of OCT capturing, position adjustment, bump extraction, character extraction and judgment. Five characteristic features related to the bump shape are introduced. And by combining the characteristic features using artificial neural network, the condition of solder bump was judged. In the experiments, these techniques were evaluated using actual BGA mounted substrate. As a result, the correct rate of judgment reached 99.7%, which shows the clear evidence that proposed techniques may be useful in the practice.

Original languageEnglish
Title of host publication2007 Proceedings of the ASME InterPack Conference, IPACK 2007
Pages453-457
Number of pages5
DOIs
Publication statusPublished - 01-12-2007
EventASME Electronic and Photonics Packaging Division - Vancouver, BC, United States
Duration: 08-07-200712-07-2007

Publication series

Name2007 Proceedings of the ASME InterPack Conference, IPACK 2007
Volume1

Other

OtherASME Electronic and Photonics Packaging Division
CountryUnited States
CityVancouver, BC
Period08-07-0712-07-07

Fingerprint

Soldering alloys
Tomography
Inspection
Neural networks
Substrates
Electronic equipment
Railroad cars
X rays
Communication
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems

Cite this

Teramoto, A., Murakoshi, T., Tsuzaka, M., & Fujita, H. (2007). Development of an automated solder inspection system with neural network using oblique computed tomography. In 2007 Proceedings of the ASME InterPack Conference, IPACK 2007 (pp. 453-457). (2007 Proceedings of the ASME InterPack Conference, IPACK 2007; Vol. 1). https://doi.org/10.1115/IPACK2007-33017
Teramoto, Atsushi ; Murakoshi, Takayuki ; Tsuzaka, Masatoshi ; Fujita, Hiroshi. / Development of an automated solder inspection system with neural network using oblique computed tomography. 2007 Proceedings of the ASME InterPack Conference, IPACK 2007. 2007. pp. 453-457 (2007 Proceedings of the ASME InterPack Conference, IPACK 2007).
@inproceedings{0c0bd923a9c5415eaf8d739641c21c4e,
title = "Development of an automated solder inspection system with neural network using oblique computed tomography",
abstract = "The high density LSI packages such as BGA is being utilized in the car electronics and communications infrastructure products. These products require a high-speed and reliable inspection technique for their solder joints. In this paper, an automated X-ray inspection system for BGA mounted substrate based on oblique computed tomography are proposed. Automated inspection consisted of OCT capturing, position adjustment, bump extraction, character extraction and judgment. Five characteristic features related to the bump shape are introduced. And by combining the characteristic features using artificial neural network, the condition of solder bump was judged. In the experiments, these techniques were evaluated using actual BGA mounted substrate. As a result, the correct rate of judgment reached 99.7{\%}, which shows the clear evidence that proposed techniques may be useful in the practice.",
author = "Atsushi Teramoto and Takayuki Murakoshi and Masatoshi Tsuzaka and Hiroshi Fujita",
year = "2007",
month = "12",
day = "1",
doi = "10.1115/IPACK2007-33017",
language = "English",
isbn = "0791842770",
series = "2007 Proceedings of the ASME InterPack Conference, IPACK 2007",
pages = "453--457",
booktitle = "2007 Proceedings of the ASME InterPack Conference, IPACK 2007",

}

Teramoto, A, Murakoshi, T, Tsuzaka, M & Fujita, H 2007, Development of an automated solder inspection system with neural network using oblique computed tomography. in 2007 Proceedings of the ASME InterPack Conference, IPACK 2007. 2007 Proceedings of the ASME InterPack Conference, IPACK 2007, vol. 1, pp. 453-457, ASME Electronic and Photonics Packaging Division, Vancouver, BC, United States, 08-07-07. https://doi.org/10.1115/IPACK2007-33017

Development of an automated solder inspection system with neural network using oblique computed tomography. / Teramoto, Atsushi; Murakoshi, Takayuki; Tsuzaka, Masatoshi; Fujita, Hiroshi.

2007 Proceedings of the ASME InterPack Conference, IPACK 2007. 2007. p. 453-457 (2007 Proceedings of the ASME InterPack Conference, IPACK 2007; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Development of an automated solder inspection system with neural network using oblique computed tomography

AU - Teramoto, Atsushi

AU - Murakoshi, Takayuki

AU - Tsuzaka, Masatoshi

AU - Fujita, Hiroshi

PY - 2007/12/1

Y1 - 2007/12/1

N2 - The high density LSI packages such as BGA is being utilized in the car electronics and communications infrastructure products. These products require a high-speed and reliable inspection technique for their solder joints. In this paper, an automated X-ray inspection system for BGA mounted substrate based on oblique computed tomography are proposed. Automated inspection consisted of OCT capturing, position adjustment, bump extraction, character extraction and judgment. Five characteristic features related to the bump shape are introduced. And by combining the characteristic features using artificial neural network, the condition of solder bump was judged. In the experiments, these techniques were evaluated using actual BGA mounted substrate. As a result, the correct rate of judgment reached 99.7%, which shows the clear evidence that proposed techniques may be useful in the practice.

AB - The high density LSI packages such as BGA is being utilized in the car electronics and communications infrastructure products. These products require a high-speed and reliable inspection technique for their solder joints. In this paper, an automated X-ray inspection system for BGA mounted substrate based on oblique computed tomography are proposed. Automated inspection consisted of OCT capturing, position adjustment, bump extraction, character extraction and judgment. Five characteristic features related to the bump shape are introduced. And by combining the characteristic features using artificial neural network, the condition of solder bump was judged. In the experiments, these techniques were evaluated using actual BGA mounted substrate. As a result, the correct rate of judgment reached 99.7%, which shows the clear evidence that proposed techniques may be useful in the practice.

UR - http://www.scopus.com/inward/record.url?scp=40449118935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40449118935&partnerID=8YFLogxK

U2 - 10.1115/IPACK2007-33017

DO - 10.1115/IPACK2007-33017

M3 - Conference contribution

AN - SCOPUS:40449118935

SN - 0791842770

SN - 9780791842775

T3 - 2007 Proceedings of the ASME InterPack Conference, IPACK 2007

SP - 453

EP - 457

BT - 2007 Proceedings of the ASME InterPack Conference, IPACK 2007

ER -

Teramoto A, Murakoshi T, Tsuzaka M, Fujita H. Development of an automated solder inspection system with neural network using oblique computed tomography. In 2007 Proceedings of the ASME InterPack Conference, IPACK 2007. 2007. p. 453-457. (2007 Proceedings of the ASME InterPack Conference, IPACK 2007). https://doi.org/10.1115/IPACK2007-33017