Design of Crack Detection System Software for IC Package Using Blob Analysis and Neural Network

نویسندگان

  • Rosdiyana Samad
  • Mohd Rizal Arshad
  • Zahurin Samad
چکیده

In this research, three methods for the detection of crack defects on integrated circuit (IC) packages are proposed. These methods use blob analysis technique in image processing stage, and use multi-layered perceptron (MLP) neural network to classify the IC package. This paper presents the various filters and operations employed in blob analysis. The simulation results have shown, that a two-layer back-propagation neural network, which has a log-sigmoid transfer function in the hidden and output layer, could be trained to classify the IC package image. An early stopping technique was used in this study to provide benefits to the network performance in terms of a decrease in over-fitting. It was found that the optimal number of hidden neurons for the network 1,2 and 3 were 12, 12 and 10. The first method produced an accuracy of 74.82% with 87.72 ms processing time, while the second method utilizing the same classifier, achieved 86.17% accuracy with 119.45 ms processing time. The third method achieved 96.1% accuracy with 188.44 ms processing speed. The results obtained in this study indicated that the third method proceed better performance with higher accuracy and processing speed below 200 ms. Key-words: IC package, Crack detection, Blob analysis, MLP neural network, Image processing

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Crack Detection of Timoshenko Beams Using Vibration Behavior and Neural Network

Abstract: In this research, at first, the natural frequencies of a cracked beam are obtained analytically, then, location and depth of a crack in beam is identified by neural network method. The research is applied on a beam with an open crack for three different boundary conditions. For this purpose, at first, the natural frequencies of the cracked beam are obtained analytically, to get the ex...

متن کامل

A New Method for Intrusion Detection Using Genetic Algorithm and Neural Network

    The article attempts to have neural network and genetic algorithm techniques present a model for classification on dataset. The goal is design model can the subject acted a firewall in network and this model with compound optimized algorithms create reliability and accuracy and reduce error rate couse of this is article use feedback neural network and compared to previous methods increase a...

متن کامل

A New Method for Intrusion Detection Using Genetic Algorithm and Neural Network

    The article attempts to have neural network and genetic algorithm techniques present a model for classification on dataset. The goal is design model can the subject acted a firewall in network and this model with compound optimized algorithms create reliability and accuracy and reduce error rate couse of this is article use feedback neural network and compared to previous methods increase a...

متن کامل

Experimental and finite-element free vibration analysis and artificial neural network based on multi-crack diagnosis of non-uniform cross-section beam

Crack identification is a very important issue in mechanical systems, because it is a damage that if develops may cause catastrophic failure. In the first part of this research, modal analysis of a multi-cracked variable cross-section beam is done using finite element method. Then, the obtained results are validated usingthe results of experimental modal analysis tests. In the next part, a nove...

متن کامل

Analysis and Diagnosis of Partial Discharge of Power Capacitors Using Extension Neural Network Algorithm and Synchronous Detection Based Chaos Theory

Power capacitors are important equipment of the power systems that are being operated in high voltage levels at high temperatures for long periods. As time goes on, their insulation fracture rate increases, and partial discharge is the most important cause of their fracture. Therefore, fast and accurate methods have great importance to accurately diagnosis the partial discharge. Conventional me...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005