Issue link: https://iconnect007.uberflip.com/i/1500520
JUNE 2023 I SMT007 MAGAZINE 63 ity and control, with output data reporting that drives better accuracy of your ERP. With all the buzz surrounding ChatGPT and other online AI-based technologies, how has AI made its way into data analysis and how does that improve the customer experience? Applications such as ChatGPT don't have direct application to manufacturing. ese types of tools are just high-powered chatbots at the end of the day, creating responses to ques- tions based on massive amounts of text content from the web, statistically aggregated to be the most probable response to provide. Obviously, they will not be able to solve a sol- der printing process issue or help with that 0.5% yield improvement that is a function of all process settings going back to the semiconductor chips on the PCBA. However, the underlying technology (a subcategory of AI called machine learn- ing), is a game changer for the electronics indus- try. Today, anyone with a strong engineering background, coupled with good scripting/programming skills using Python, can implement a machine learning algorithm to hunt for patterns in data. ese algorithms can be used for outlier detection, which is incredibly useful for catching quality and process issues in the line, as well as predic- tive machine maintenance. Machine learning algorithms can also be lev- eraged to do virtual product testing based on process data measurements from earlier in the line, thus removing the need to do 100% testing of products going out to customers. e qual- ity, throughput, and overall margin improve- ments are incredible. But you need well-cat- aloged contextual data to do this. Otherwise, your engineers will spend most of their time aggregating and cleaning data, and you'll get nowhere. Based on your experience, what are the biggest mistakes made when collecting or analyzing data? e biggest mistake I see is not embedding basic traceability attributes in the data at the point it's generated—for example, part num- ber, test program or machine recipe, lot num- ber or board serial number, and date+time of execution should be there as a minimum. e idiocy is that many common data stan- dards don't specify these fields as required. Just look at the SEMI E142 specification, for exam- ple. Machine vendors and third-party data so- ware providers are notori- ous for violating standards because these standards are inherently overly com- plicated. Oen, engineers try to get around this by embed- ding information in the file name. But file names get overwritten, and even worse, have you tried to generate analytics by reading in file names? With today's access to scripting languages, such as Python, which is open source and free, coupled with simple modern web/network APIs (application programming interfaces) approaches, this information can be injected into the data as it's being generated. All you need is an API accessible source of routing information, such as an MES, and you've got it solved. Where do you see the future of your industry in general, and data analysis specifically? It's an exciting time for the electronics manu- facturing industry, with engineering becoming more and more data centric. With improving The biggest mistake I see is not embedding basic traceability attributes in the data at the point it's generated...