Bluetooth Low Energy (BLE) is one of the RF-based technologies that has been utilizing Received Signal Strength Indicators (RSSI) in indoor position location systems (IPS) for decades. Its recent signal stability and propagation distance improvement inspired us to conduct this project. Beacons and scanners used two Bluetooth specifications, BLE 5.0 and 4.2, for experimentations. The measurement paradigm consisted of three segments, RSSI–distance conversion, multi-beacon in-plane, and diverse directional measurement. The analysis methods applied to process the data for precise positioning included the Signal propagation model, Trilateration, Modification coefficient, and Kalman filter. As the experiment results showed, the positioning accuracy could reach 10 cm when the beacons and scanners were at the same horizontal plane in a less-noisy environment. Nevertheless, the positioning accuracy dropped to a meter-scale accuracy when the measurements were executed in a three-dimensional configuration and complex environment. According to the analysis results, the BLE wireless signal strength is susceptible to interference in the manufacturing environment but still workable on certain occasions. In addition, the Bluetooth 5.0 specifications seem more promising in bringing brightness to RTLS applications in the future, due to its higher signal stability and better performance in lower interference environments.

The manufacturing industry faces the challenge of small and diversified customer orders. To meet this challenge, strong internal production capabilities are required. A lean manufacturing process that uses fewer resources and offers greater process improvement will help SMEs to continue to contribute to the global economy. Though SMEs provide most employment opportunities, previous studies have focused on large companies in auto-manufacturing-related industries. With the commitment and support of the management, and the application of a value stream map (VSM) and related improvement tools, we produced a practical process improvement model for a lean manufacturing system in an SME. With the commitment and support of the management and the joint efforts of the project improvement staff, the 10 improvement projects over a six-month period all achieved their goals: reduction in lead time from 26 days to 19.5 days, improvement of welding per people per hour (PPH) efficiency by 28.3%, improvement of packaging PPH efficiency by 64.1%, improvement of working in process (WIP) efficiency at the production site by 83.84%, and improvement of raw material storage by 83.84%. The efficiency of the raw material warehouse inventory was improved by 58.63%, and the efficiency of the shipment completion rate was improved by 14.5%.

Under the emerging topic of machine vision technology replacing manual examination, automatic optical inspection (AOI) technology has been adopted for the detection of defects in semi-finished/finished products and is widely used for the defect detection of printed circuit boards (PCB) in electronic industries where surface mount technology (SMT) is applied. In order to convert images from gray-scale to binary in the PCB process, a strict threshold value was set for AOI to prevent ‘escapes’, but this can lead to serious false alarm because of unwanted noises. Therefore, they tend to set up a Noise-Removal procedure after AOI, which increases the computational cost. By applying deep learning to circuit images of the ceramic substrates in AOI, this paper aimed to construct an automatic defect detection system that could also identify the categories as well as the locations of defects. This study proposed and evaluated three models with integrated structures: ResNeXt+YOLO v3, Inception v3+YOLO v3, and YOLO v3. The outcomes indicate that the defect detection system built on ResNeXt+YOLO v3 could most effectively detect standard images that had been misidentified as defects by AOI, categorize genuine defects, and find their location. The proposed method could not only increase the inspection accuracy to 99.2%, but also help decrease the cost of human resources generated by manual re-examination.

The objective of this paper is to implement a two-dimensional wavelet transform (2-D WT) approach for detecting visual defects such as particles, contamination, and scratches on semiconductor wafer dies. The gray image of 1/20 of a wafer die is initially processed by smooth and high-pass filters. Then, it is decomposed directly by 2-D WT at multiple scales and different wavelet bases. The interscale ratio from the wavelet transform modulus sum (WTMS) across adjacent decomposition levels (scales) for suspicious pixels on a wafer die is calculated. Since irregular edges in a small domain preserve much more wavelet energy, an edge pixel potentially belongs to a visual defect if its interscale ratio is less than a predefined threshold. The proposed approach is template-free and is easy to implement, so it is suitable for more product varieties and small-batch production. Real wafer dies with synthetic defects are used as testing samples to evaluate the performance of proposed approach. Experimental results from a small amount of testing samples show that the proposed method is able to identify particle, contamination, and scratch defects without missed detection and false alarm by appropriate choice of wavelet bases, scale, and image resolution. The proposed inspection approach could be considered as a potentially precise and low detection error method for further large amounts of inspections in a real environment.