Developing Computational Intelligence for Smart Qualification Testing of Electronic Products
In electronics manufacturing, the necessary quality of electronic components and parts is ensured through qualification testing using standards and user requirements. The challenge is that product qualification testing is time-consuming and comes at a substantial cost. The work contributes to develo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8963648/ |
| _version_ | 1818330536822702080 |
|---|---|
| author | Mominul Ahsan Stoyan Stoyanov Chris Bailey Alhussein Albarbar |
| author_facet | Mominul Ahsan Stoyan Stoyanov Chris Bailey Alhussein Albarbar |
| author_sort | Mominul Ahsan |
| collection | DOAJ |
| description | In electronics manufacturing, the necessary quality of electronic components and parts is ensured through qualification testing using standards and user requirements. The challenge is that product qualification testing is time-consuming and comes at a substantial cost. The work contributes to develop a novel prognostics framework for predicting qualification test outcomes of electronic components enabling the reduction of qualification test time and cost. The research focuses on the development of a new, prognostics-based approach to qualification of electronics parts that can enable “smart testing” using data-driven modelling techniques in order to ensure product robustness and reliability in operation. This work is both novel and original because at present such approach to qualification testing and the associated capability for test time reduction (respectively cost reduction) it offers are non-existent in the electronics industry. An effective way of using three different methods for development of prognostics models are identified and applied. Predictive models are constructed from historical qualification test data in the form of electrical parameter measurements using Machine Learning (ML) techniques. ML models can be imbedded within the sequential electrical tests qualification procedure and enable the forecasting of the pass/fail qualification outcome using only partial information from already completed electrical tests. Data-driven prognostics models are developed using the following machine learning techniques: (1) Support Vector Machine (SVM), (2) Neural Network (NN) and (3) K-Nearest Neighbor (KNN). The results show that with just over half of the individual tests completed, the models are capable of forecasting the final qualification outcome, pass or fail, with accuracy as high as 92.5%. The predictive power and overall performance of the researched models in predicting qualification test binary outcomes with varying ratios of Pass and Fail data in the processed datasets are analysed. |
| first_indexed | 2024-12-13T13:05:31Z |
| format | Article |
| id | doaj.art-63fafe3b0e5a40819ea8585abd91f592 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T13:05:31Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-63fafe3b0e5a40819ea8585abd91f5922022-12-21T23:44:51ZengIEEEIEEE Access2169-35362020-01-018169221693310.1109/ACCESS.2020.29678588963648Developing Computational Intelligence for Smart Qualification Testing of Electronic ProductsMominul Ahsan0https://orcid.org/0000-0002-7300-506XStoyan Stoyanov1https://orcid.org/0000-0001-6091-1226Chris Bailey2https://orcid.org/0000-0002-9438-3879Alhussein Albarbar3https://orcid.org/0000-0003-1484-8224Department of Engineering, Smart Infrastructure and Industry Research Group, John Dalton Building, Manchester Metropolitan University, Manchester, U.K.School of Computing and Mathematical Sciences, Queen Mary Building, Old Royal Naval College, University of Greenwich, London, U.K.School of Computing and Mathematical Sciences, Queen Mary Building, Old Royal Naval College, University of Greenwich, London, U.K.Department of Engineering, Smart Infrastructure and Industry Research Group, John Dalton Building, Manchester Metropolitan University, Manchester, U.K.In electronics manufacturing, the necessary quality of electronic components and parts is ensured through qualification testing using standards and user requirements. The challenge is that product qualification testing is time-consuming and comes at a substantial cost. The work contributes to develop a novel prognostics framework for predicting qualification test outcomes of electronic components enabling the reduction of qualification test time and cost. The research focuses on the development of a new, prognostics-based approach to qualification of electronics parts that can enable “smart testing” using data-driven modelling techniques in order to ensure product robustness and reliability in operation. This work is both novel and original because at present such approach to qualification testing and the associated capability for test time reduction (respectively cost reduction) it offers are non-existent in the electronics industry. An effective way of using three different methods for development of prognostics models are identified and applied. Predictive models are constructed from historical qualification test data in the form of electrical parameter measurements using Machine Learning (ML) techniques. ML models can be imbedded within the sequential electrical tests qualification procedure and enable the forecasting of the pass/fail qualification outcome using only partial information from already completed electrical tests. Data-driven prognostics models are developed using the following machine learning techniques: (1) Support Vector Machine (SVM), (2) Neural Network (NN) and (3) K-Nearest Neighbor (KNN). The results show that with just over half of the individual tests completed, the models are capable of forecasting the final qualification outcome, pass or fail, with accuracy as high as 92.5%. The predictive power and overall performance of the researched models in predicting qualification test binary outcomes with varying ratios of Pass and Fail data in the processed datasets are analysed.https://ieeexplore.ieee.org/document/8963648/Data-driven prognosticsdata analysismachine learningmodelingelectronics manufacturingquality |
| spellingShingle | Mominul Ahsan Stoyan Stoyanov Chris Bailey Alhussein Albarbar Developing Computational Intelligence for Smart Qualification Testing of Electronic Products IEEE Access Data-driven prognostics data analysis machine learning modeling electronics manufacturing quality |
| title | Developing Computational Intelligence for Smart Qualification Testing of Electronic Products |
| title_full | Developing Computational Intelligence for Smart Qualification Testing of Electronic Products |
| title_fullStr | Developing Computational Intelligence for Smart Qualification Testing of Electronic Products |
| title_full_unstemmed | Developing Computational Intelligence for Smart Qualification Testing of Electronic Products |
| title_short | Developing Computational Intelligence for Smart Qualification Testing of Electronic Products |
| title_sort | developing computational intelligence for smart qualification testing of electronic products |
| topic | Data-driven prognostics data analysis machine learning modeling electronics manufacturing quality |
| url | https://ieeexplore.ieee.org/document/8963648/ |
| work_keys_str_mv | AT mominulahsan developingcomputationalintelligenceforsmartqualificationtestingofelectronicproducts AT stoyanstoyanov developingcomputationalintelligenceforsmartqualificationtestingofelectronicproducts AT chrisbailey developingcomputationalintelligenceforsmartqualificationtestingofelectronicproducts AT alhusseinalbarbar developingcomputationalintelligenceforsmartqualificationtestingofelectronicproducts |