Resumen de An automated process for designing test sites for electronic products based on figure of merit and machine learning
Consumer electronic manufacturing (CEM) companies maintain a range of electronic products that are designed and tested according to the type and end-user requirements. These electronic products go through a validation and verification test for proof of design and a manufacturing test for checking reliability, quality, and manufacturing defects. Testing is carried out using test sites, designed based on the electronic product type. Currently, there is no standard approach for setting up a test site for electronic products. Electronic companies launch new products frequently and spend a lot of time to verify their designs. These designs are verified through rigorous validation carried out using several pre-manufacturing tests. The products are ready for manufacturing after passing these tests. At this stage, the companies setup test-sites for testing these products, which are different from validation tests. At the moment there is no standard way of deciding how to setup a test-site. Normally the parameters used for taking this decision include the type of testing required, test partial or complete batch, type of equipment to be used etc. The existing techniques rely on few parameters and the selection of these parameters also vary due to lack of standard method. This paper is a step towards defining a common approach to setup test sites. Consumer electronic manufacturing (CEM) companies face a constant challenge to maintain quality standards during frequent product launches. A manufacturing test verifies product functionality and identifies manufacturing defects. Failure to complete testing can even result in product recalls. In this research, a universal automated testing system has been proposed for CEM companies to streamline their test process in reduced test cost and time. Manufacturing industry plays an important role in the development of a country by providing employment to its skilled and semi-skilled workforce. Companies focus on maintaining a good standard of their products which can be achieved through manufacturing test. In order to compete with similar companies, the manufacturing companies need to have an optimized electronic product testing system. Products are tested for manufacturing faults and functionality to maintain quality control which is a continuous process. It can be achieved through a process where manufacturing test data is collected and analyzed.
In the first part of the research, two processes are presented, for setting up new test sites and optimization of existing test sites for consumer and other electronic products. The proposed processes include a voice of customer (VoC) interface, that is based on a unique dataset and through machine-learning technique automatically translate customer information into customer requirements, and a figure of merit (FoM) presented as an outcome of this research using several key test-related parameters. These proposed processes are an important step towards defining a standard approach for setting test sites for consumer and other electronic products. The processes are implemented using a software application developed in LabVIEW, which is linked to a database containing test data for around 400 products collected as part of this research and form a knowledge base for the proposed processes. In this research a software application is developed using LabVIEW to implement a standard way of setting up a test-site. The software prompts test site design authority to enter parameters required to setup a test site using voice of customer (VoC), figure of merit (FoM), database (DB) and test readiness review (TRR) interfaces. This application is linked to a database containing test equipment details and previous test sites data like test jigs, interface adapters, estimated and actual test times, first time yield etc. Based on the user input data the software performs analysis and generate reports to setup a test site and also evaluate test readiness of the test site. This approach incorporates most of the techniques required to setup for most of the electronic products. Finally, the processes are validated by setting up a new experimental test site for an RF receiver and optimization of an existing test site of an antenna system.
In the second part of this research, a universal hardware interface is designed for connecting commercial off-the-shelf (COTS) test equipment and unit under test (UUT). A software application, based on machine learning, is developed in LabVIEW. The test site data for around 100 test sites have been collected. The application automatically selects COTS test equipment drivers and interfaces on UUT and test measurements for test sites through a universal hardware interface. Further, it collects real-time test measurement data, performs analysis, generates reports and key performance indicators (KPIs), and provides recommendations using machine learning. It also maintains a database for historical data to improve manufacturing processes. The proposed system can be deployed standalone as well as a replacement for the test department module of enterprise resource planning (ERP) systems providing direct access to test site hardware. The LabVIEW based application is presented for collection and analysis of manufacturing test site data. The data collected is for low and mid volume batch-size for a month, where a weekly analysis is normally done. The application provides a standard approach based on graphical analysis to review data trends and provide recommendations to the manufacturing organizations for cost reduction, increased first time yield, training requirements for the operators etc. Initial results obtained using the application show that the proposed approach is efficient and reliable for test site data collection and analysis of variety of products. Finally, the system is validated through an experimental setup in a CEM company.
