Technical Library | 2021-11-22 20:39:44.0
Quality control is a key activity performed by manufacturing companies to verify product conformance to the requirements and specifications. Standardized quality control ensures that all the products are evaluated under the same criteria. The decreased cost of sensors and connectivity enabled an increasing digitalization of manufacturing and provided greater data availability. Such data availability has spurred the development of artificial intelligence models, which allow higher degrees of automation and reduced bias when inspecting the products. Furthermore, the increased speed of inspection reduces overall costs and time required for defect inspection. In this research, we compare five streaming machine learning algorithms applied to visual defect inspection with real world data provided by Philips Consumer Lifestyle BV. Furthermore, we compare them in a streaming active learning context, which reduces the data labeling effort in a real-world context. Our results show that active learning reduces the data labeling effort by almost 15% on average for the worst case, while keeping an acceptable classification performance. The use of machine learning models for automated visual inspection are expected to speed up the quality inspection up to 40%.
Technical Library | 2017-08-31 13:43:48.0
Wire bonded packages using conventional copper leadframe have been used in industry for quite some time. The growth of portable and wireless products is driving the miniaturization of packages resulting in the development of many types of thin form factor packages and cost effective assembly processes. Proper optimization of wire bond parameters and machine settings are essential for good yields. Wire bond process can generate a variety of defects such as lifted bond, cracked metallization, poor intermetallic etc. NSOP – non-stick on pad is a defect in wire bonding which can affect front end assembly yields. In this condition, the imprint of the bond is left on the bond pad without the wire being attached. NSOP failures are costly as the entire device is rejected if there is one such failure on any bond pad. The paper presents some of the failure modes observed and the efforts to address NSOP reduction
Technical Library | 2024-04-29 21:19:42.0
Over the years, computer vision and machine learning disciplines have considerably advanced the field of automated visual inspection for Printed Circuit Board (PCB-AVI) assurance. However, in practice, the capabilities and limitations of these advancements remain unknown because there are few publicly accessible datasets for PCB visual inspection and even fewer that contain images that simulate realistic application scenarios. To address this need, we propose a publicly available dataset, "FICS-PCB"1, to facilitate the development of robust methods for PCB-AVI. The proposed dataset includes challenging cases from three variable aspects: illumination, image scale, and image sensor. This dataset consists of 9,912 images of 31 PCB samples and contains 77,347 annotated components. This paper reviews the existing datasets and methodologies used for PCBAVI, discusses challenges, describes the proposed dataset, and presents baseline performances using feature engineering and deep learning methods for PCB component classification.
Technical Library | 2015-06-30 16:07:12.0
Robotics for automated fluid dispensing have the ability to apply a variety of materials including epoxy, silicone, and acrylic coatings. These materials are extensively used in today’s high-speed fluid dispensers for the electronics industry. Whether a dispenser is applying epoxy or another material, the central concept for applying any form of material remains the same. Specific points of an item being dispensed onto are programmed into the dispensing system. The automated fluid dispensers software interprets the programmed information and keeps the travel path in memory. A robotic arm moves fluid dispensing nozzles along this travel path and applies epoxy onto the surface of the item with precise accuracy. Machine speed can be adjusted to emit varying amounts of epoxy. The overall application process is auto-regulating and will not be disrupted.
Technical Library | 2017-05-17 22:33:43.0
The selective soldering application requires a combination of performance attributes that traditional liquid fluxes designed for wave soldering applications cannot fulfill. First, the flux deposition on the board needs to be carefully controlled. Proper fine tuning of the flux physicochemical characteristics combined with a process optimization are mandatory to strike the right balance between solderability and reliability. However, localization of the flux residue through the drop jet process is not enough to guarantee the expected performance level. The flux needs to be designed to minimize the impact of unavoidable spreading and splashing events.From this perspective a fundamental understanding of the relationships between formulation and reliability is critical. In this application, thermal history of the flux residues (from room temperature to solder liquidus) is a key performance driver. Finally, it is necessary to conduct statistically designed experiments on industrial selective soldering machines in order to map the relationships between flux characteristics and selective process friendliness.
Technical Library | 2020-08-27 01:15:10.0
Automobile surface defects like scratches or dents occur during the process of manufacturing and cross-border transportation. This will affect consumers' first impression and the service life of the car itself. In most worldwide automobile industries, the inspection process is mainly performed by human vision, which is unstable and insufficient. The combination of artificial intelligence and the automobile industry shows promise nowadays. However, it is a challenge to inspect such defects in a computer system because of imbalanced illumination, specular highlight reflection, various reflection modes and limited defect features. This paper presents the design and implementation of a novel automatic inspection system (AIS) for automobile surface defects which are the located in or close to style lines, edges and handles. The system consists of image acquisition and image processing devices, operating in a closed environment and noncontact way with four LED light sources. Specifically, we use five plane-array Charge Coupled Device (CCD) cameras to collect images of the five sides of the automobile synchronously. Then the AIS extracts candidate defect regions from the vehicle body image by a multi-scale Hessian matrix fusion method. Finally, candidate defect regions are classified into pseudo-defects, dents and scratches by feature extraction (shape, size, statistics and divergence features) and a support vector machine algorithm. Experimental results demonstrate that automatic inspection system can effectively reduce false detection of pseudo-defects produced by image noise and achieve accuracies of 95.6% in dent defects and 97.1% in scratch defects, which is suitable for customs inspection of imported vehicles.
Technical Library | 2024-04-29 21:39:52.0
In this paper, we develop and put into practice an Automatic Optical Inspection (AOI) system based on machine vision to check the holes on a printed circuit board (PCB). We incorporate the hardware and software. For the hardware part, we combine a PC, the three-axis positioning system, a lighting device and CCD cameras. For the software part, we utilize image registration, image segmentation, drill numbering, drill contrast, and defect displays to achieve this system. Results indicated that an accuracy of 5µm could be achieved in errors of the PCB holes allowing comparisons to be made. This is significant in inspecting the missing, the multi-hole and the incorrect location of the holes. However, previous work only focusses on one or other feature of the holes. Our research is able to assess multiple features: missing holes, incorrectly located holes and excessive holes. Equally, our results could be displayed as a bar chart and target plot. This has not been achieved before. These displays help users analyze the causes of errors and immediately correct the problems. Additionally, this AOI system is valuable for checking a large number of holes and finding out the defective ones on a PCB. Meanwhile, we apply a 0.1mm image resolution which is better than others used in industry. We set a detecting standard based on 2mm diameter of circles to diagnose the quality of the holes within 10 seconds.
Technical Library | 2019-03-25 12:45:56.0
Work instructions are time consuming to generate for engineers, often requiring regeneration from scratch to address very minor changes. They need to be produced in varying levels of detail, with varying guidelines, for multiple stations, operators and lines. Minor component, station or process changes – down to the modification of an individual BOM component – can cause headaches when attempting to maintain consistency across multiple work instructions that are touched by the change.The solution presented here improves efficiency and saves engineering time by making use of a database driven approach. Manufacturing details, component information, process guidelines, annotations, machine-specific data, and more can be stored in one central database. Any information stored in this single repository can then be modified quickly in one location and automatically propagate seamlessly throughout multiple work instructions. These can be instantly printed out or displayed on screens at appropriately affected stations with the simple click of a button, as opposed to regenerating from scratch, or going in and reviewing many documents to find and update with the change.
Technical Library | 2020-03-26 14:55:29.0
This paper introduces line confocal technology that was recently developed to characterize 3D features of various surface and material types at sub-micron resolution. It enables automatic microtopographic 3D imaging of challenging objects that are difficult or impossible to scan with traditional methods, such as machine vision or laser triangulation.Examples of well-suited applications for line confocal technology include glossy, mirror-like, transparent and multi-layered surfaces made of metals (connector pins, conductor traces, solder bumps etc.), polymers (adhesives, enclosures, coatings, etc.), ceramics (components, substrates, etc.) and glass (display panels, etc.). Line confocal sensors operate at high speed and can be used to scan fast-moving surfaces in real-time as well as stationary product samples in the laboratory. The operational principle of the line confocal method and its strengths and limitations are discussed.Three metrology applications for the technology in electronics product manufacturing are examined: 1. 3D imaging of etched PCBs for micro-etched copper surface roughness and cross-sectional profile and width of etched traces/pads. 2. Thickness, width and surface roughness measurement of conductive ink features and substrates in printed electronics applications. 3. 3D imaging of adhesive dots and lines for shape, dimensions and volume in PCB and product assembly applications.
Technical Library | 2019-07-02 23:02:05.0
The introduction of lead-free solders resulted in a selection of different chemistries for solder pastes. The higher melting points of lead-free alloys required thermal heat resistant rosin systems and activators that are active at elevated temperatures. As a result, more frequent maintenance of the filtration systems is required and machine downtime is increased.Last year a different method of cleaning reflow ovens was introduced. Instead of cooling down the process gasses to condensate the residues, a catalyst was used to maintain the clean oven. Catalytic thermal oxidation of residues in the nitrogen atmosphere resulted in cleaner heating zones. The residues were transformed into carbon dioxide. This remaining small amount of char was collected in the catalyst. In air ovens the catalyst was not seen as a beneficial option because the air extracted out of the oven was immediately exhausted into the environment. When a catalyst is used in an air environment there is not only the carbon dioxide residues, but also water. When a catalyst is used in an air reflow oven the question is where the water is going to. Will it condensate in the process part of the oven or is the gas temperature high enough to keep it out of the process area? A major benefit of using a catalyst to clean the air before it is exhausted into the environment is that the air pollution is reduced dramatically. This will make environmental engineers happy and result in less pollution of our nature. Apart from this, the exhaust tubes remain clean which reduces the maintenance of air ovens.This paper will give more detailed information of catalyst systems during development and performance in production lines.
