Industry-Oriented Detection Method of PCBA Defects Using Semantic Segmentation Models

Automated optical inspection(AOI)is a significant process in printed circuit board assembly(PCBA)production lines which aims to detect tiny defects in PCBAs.Existing AOI equipment has several deficiencies including low throughput,large computation cost,high latency,and poor flexibility,which limits the efficiency of online PCBA inspection.In this paper,a novel PCBA defect detection method based on a lightweight deep convolution neural network is proposed.In this method,the semantic segmentation model is combined with a rule-based defect recognition algorithm to build up a defect detection frame-work.To improve the performance of the model,extensive real PCBA images are collected from production lines as datasets.Some optimization methods have been applied in the model according to production demand and enable integration in lightweight computing devices.Experiment results show that the production line using our method realizes a throughput more than three times higher than traditional methods.Our method can be integrated into a lightweight inference system and pro-mote the flexibility of AOI.The proposed method builds up a general paradigm and excellent example for model design and optimization oriented towards industrial requirements.

Magnetogenetics: remote non-invasive magnetic activation of neuronal activity with a magnetoreceptor

Current neuromodulation techniques such as optogenetics and deep-brain stimulation are transforming basic and translational neuroscience. These two neuro- modulation approaches are, however, invasive since surgical implantation of an optical fiber or wire electrode is required. Here, we have invented a non-invasive magnetogenetics that combines the genetic targeting of a mag- netoreceptor with remote magnetic stimulation. The noninvasive activation of neurons was achieved by neuronal expression of an exogenous magnetoreceptor, an iron-sulfur cluster assembly protein 1 （Iscal）. In HEK-293 cells and cultured hippocampal neurons expressing this magnetoreceptor, application of an external magnetic field resulted in membrane depolarization and calcium influx in a reproducible and reversible manner, as indicated by the ultrasensitive fluorescent calcium indicator GCaMP6s.Moreover, the magnetogenetic control of neuronal activity might be dependent on the direction of the magnetic field and exhibits on-response and off-response patterns for the external magnetic field applied. The activation of this magnetoreceptor can depolarize neurons and elicit trains of action potentials, which can be triggered repetitively with a remote magnetic field in whole-cell patch-clamp recording. In transgenic Caenorhabditis elegans expressing this magnetoreceptor in myo-3-specific muscle cells or mec-4- specific neurons, application of the external magnetic field triggered muscle contraction and withdrawal behavior of the worms, indicative of magnet-dependent activation of muscle cells and touch receptor neurons, respectively. The advantages of magnetogenetics over optogenetics are its exclusive non-invasive, deep penetration, long-term continuous dosing, unlimited accessibility, spatial uniformity and relative safety. Like optogenetics that has gone through decade-long improvements, magnetogenetics, with continuous modification and maturation, will reshape the current landscape of neuromodulation toolboxes and will have a broad range of applications to basic and translational neuroscience as well as other biological sciences. We envision a new age of magnetogenetics is coming.