Issue link: https://iconnect007.uberflip.com/i/1309864
NOVEMBER 2020 I PCB007 MAGAZINE 61 the minor differences in resistance can be fatal in repeatability even though fully conforming. These options are available today to help capture electrical defects in plated barrels, whether they directly affect the electrical pro- file of the circuit board or are hiding in the functional spectrum of the barrel that does not affect board integrity. Consult with your ET de- partment on how this may help you in the fu- ture. If you have questions, you can reach out to me as well. The holidays are upon us. Be safe, keep your distance, and hug your family. PCB007 Todd Kolmodin is VP of quality for Gardien Services USA and an expert in electrical test and reliability issues. To read past columns or contact Kolmodin, click here. masked by parasitic resistance and limitations of the standard metering systems being used. The specific detects are taper plate and micro- fractures. This is where 4-wire Kelvin really shines. The high-resolution measurement is able to capture these minute changes in resistance of the barrel. Many questions arise on how the Kelvin test works. The industry standard is a master comparison test. What we mean here is that a known electrically correct PCB is used to create the Kelvin master. This is done by per- forming several cycles (user-definable) on the PCB, and when complete, the master values are written. The subsequent PCBs are then compared to the master values for evaluation. Differing from the forced barrel test, the theoretical val- ues can be programmed in advance. However, due to the variances in plating from lot to lot, will require maintenance and repair, which can be long and costly. The new NTU approach embeds AI into the network of sensor nodes, connected to multiple small, less-powerful processing units, that act like "mini-brains" distributed on the robotic skin. This means learning happens locally, and the wiring requirements and response time for the robot are reduced five to ten times compared to conventional ro- bots, say the scientists. (Source: NTU Singapore) Using a brain-inspired approach, scientists from Nan- yang Technological University, Singapore (NTU Singapore) developed a way for robots to have AI recognize pain and to self-repair when damaged. The system has AI-enabled sensor nodes to process and respond to "pain" arising from pressure exerted by a physical force. The system also allows the robot to detect and repair its own damage when minorly "injured," with- out the need for human intervention. Currently, robots use a network of sensors to generate information about their immediate environment. For exam- ple, a disaster rescue robot uses camera and microphone sensors to locate a survivor under debris and then pulls the person out with guidance from touch sensors on their arms. A factory robot working on an assembly line uses vi- sion to guide its arm to the right location and touch sen- sors to determine if the object is slipping when picked up. Today's sensors typically do not process information but send it to a single large, powerful, central process- ing unit where learning occurs. As a result, existing ro- bots are usually heavily wired, which results in delayed response times. They are also susceptible to damage that NTU Singapore Scientists Develop 'Mini-Brains' to Help Robots Recognize Pain and to Self-Repair