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 | 2023-11-20 18:10:20.0
The electronics production is prone to a multitude of possible failures along the production process. Therefore, the manufacturing process of surface-mounted electronics devices (SMD) includes visual quality inspection processes for defect detection. The detection of certain error patterns like solder voids and head in pillow defects require radioscopic inspection. These high-end inspection machines, like the X-ray inspection, rely on static checking routines, programmed manually by the expert user of the machine, to verify the quality. The utilization of the implicit knowledge of domain expert(s), based on soldering guidelines, allows the evaluation of the quality. The distinctive dependence on the individual qualification significantly influences false call rates of the inbuilt computer vision routines. In this contribution, we present a novel framework for the automatic solder joint classification based on Convolutional Neural Networks (CNN), flexibly reclassifying insufficient X-ray inspection results. We utilize existing deep learning network architectures for a region of interest detection on 2D grayscale images. The comparison with product-related meta-data ensures the presence of relevant areas and results in a subsequent classification based on a CNN. Subsequent data augmentation ensures sufficient input features. The results indicate a significant reduction of the false call rate compared to commercial X-ray machines, combined with reduced product-related optimization iterations.
Technical Library | 2023-11-20 18:49:11.0
Non-destructive testing during the manufacture of printed wiring boards (PWBs) has become ever more important for checking product quality without compromising productivity. Using x-ray inspection, not only provides a non-destructive test but also allows investigation within optically hidden areas, such as the quality of post solder reflow of area array devices (e.g. BGAs, CSPs and flip chips). As the size of components continues to diminish, today's x-ray inspection systems must provide increased magnification, as well as better quality x-ray images to provide the necessary analytical information. This has led to a number of x-ray manufacturers offering digital x-ray inspection systems, either as standard or as an option, to satisfy these needs. This paper will review the capabilities that these digital x-ray systems offer compared to their analogue counterparts. There is also a discussion of the various types of digital x-ray systems that are available and how the use of different digital detectors influences the operational capabilities that such systems provide.
Technical Library | 2020-08-27 01:22:45.0
Initially adopted internal specifications for acceptance of printed circuit boards (PCBs) used for wire bonding was that there were no nodules or scratches allowed on the wirebond pads when inspected under 20X magnification. The nodules and scratches were not defined by measurable dimensions and were considered to be unacceptable if there was any sign of a visual blemish on wire-bondable features. Analysis of the yield at a PCB manufacturer monitored monthly for over two years indicated that the target yield could not be achieved, and the main reasons for yield loss were due to nodules and scratches on the wirebonding pads. The PCB manufacturer attempted to eliminate nodules and scratches. First, a light-scrubbing step was added after electroless copper plating to remove any co-deposited fine particles that acted as a seed for nodules at the time of copper plating. Then, the electrolytic copper plating tank was emptied, fully cleaned, and filtered to eliminate the possibility of co-deposited particles in the electroplating process. Both actions greatly reduced the density of the nodules but did not fully eliminate them. Even though there was only one nodule on any wire-bonding pad, the board was still considered a reject. To reduce scratches on wirebonding pads, the PCB manufacturer utilized foam trays after routing the boards so that they did not make direct contact with other boards. This action significantly reduced the scratches on wire-bonding pads, even though some isolated scratches still appeared from time to time, which caused the boards to be rejected. Even with these significant improvements, the target yield remained unachievable. Another approach was then taken to consider if wire bonding could be successfully performed over nodules and scratches and if there was a dimensional threshold where wire bonding could be successful. A gold ball bonding process called either stand-off-stitch bonding (SSB) or ball-stitch-on-ball bonding (BSOB) was used to determine the effects of nodules and scratches on wire bonds. The dimension of nodules, including height, and the size of scratches, including width, were measured before wire bonding. Wire bonding was then performed directly on various sizes of nodules and scratches on the bonding pad, and the evaluation of wire bonds was conducted using wire pull tests before and after reliability testing. Based on the results of the wire-bonding evaluation, the internal specification for nodules and scratches for wirebondable PCBs was modified to allow nodules and scratches with a certain height and a width limitation compared to initially adopted internal specifications of no nodules and no scratches. Such an approach resulted in improved yield at the PCB manufacturer.
Technical Library | 2019-03-15 16:26:50.0
While there have been quite dramatic and evident improvements in almost every facet of manufacturing over the last several decades owing to the advent and mass adoption of computer automation and networking, there is one aspect of production that remains stubbornly unaffected. Massive databases track everything from orders, to inventory, to personnel. CAD systems allow for interactive and dynamic 3D rendering and testing, digital troubleshooting, and simulation and analysis prior to mass production. Yet, with all of this computational power and all of this networking capability, one element of production has remained thoroughly and firmly planted in the past. Nearly all manufacturing or assembly procedures are created, deployed, and stored using methodologies derived from a set of assumptions that ceased to be relevant fifty years ago. This set of assumptions, referred to below as the “Paper Paradigm” has been, and continues as the dominant paradigm for manufacturing procedures to this day. It is time for a new paradigm, one that accounts for the vastly different technological landscape of this era, one that provides a simple, efficient interface, deep traceability, and dynamic response to rapidly changing economic forces.This paper seeks to present an alternative. Instead of enhancing and improving on systems that became irrelevant with the invention of a database, instead of propping up an outdated, outmoded and inefficient system with incremental improvements; rewrite the paradigm. Change the underlying assertions to more accurately reflect our current technological capability. Instead of relying on evolutionary improvements, it is time for a revolution in manufacturing instructions.
Technical Library | 2019-09-11 23:33:04.0
There are numerous techniques to singulate printed circuit boards after assembly including break-out, routing, wheel cutting and now laser cutting. Lasers have several desirable advantages such as very narrow kerf widths as well as virtually no dust, no mechanical stress, visual pattern recognition and fast set-up changes. The very narrow kerf width resulting from laser ablation and the very tight tolerance of the cutting path placement allows for more usable space on the panel. However, the energy used in the laser cutting process can also create unwanted products on the cut walls as a result of the direct laser ablation. The question raised often is: What are these products, and how far can the creation of such products be mitigated through variation of the laser cutting process, laser parameters and material handling? This paper discusses the type and quantity of the products found on sidewalls of laser depaneled circuit boards and it quantifies the results through measurements of breakdown voltage, as well as electrical impedance. Further this paper discusses mitigation strategies to prevent or limit the amount of change in surface quality as a result of the laser cutting process. Depending on the final application of the circuit board it may prompt a need for proper specification of the expected results in terms of cut surface quality. This in turn will impact the placement of runs and components during layout. It will assist designers and engineers in defining these parameters sufficiently in order to have a predictable quality of the circuit boards after depaneling.
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 | 2019-08-07 22:56:45.0
The requirement to reconsider traditional soldering methods is becoming more relevant as the demand for bottom terminated components (QFN/BTC) increases. Thermal pads under said components are designed to enhance the thermal and electrical performance of the component and ultimately allow the component to run more efficiently. Additionally, low voiding is important in decreasing the current path of the circuit to maximize high speed and RF performances. The demand to develop smaller, more reliable, packages has seen voiding requirements decrease below 15 percent and in some instances, below 10 percent.Earlier work has demonstrated the use of micro-fluxed solder preforms as a mechanism to reduce voiding. The current work builds upon these results to focus on developing an engineered approach to void reduction in leadless components (QFN) through increasing understanding of how processing parameters and a use of custom designed micro-fluxed preforms interact. Leveraging the use of a micro-fluxed solder preform in conjunction with low voiding solder paste, stencil design, and application knowhow are critical factors in determining voiding in QFN packages. The study presented seeks to understand the vectors that can contribute to voiding such as PCB pad finish, reflow profile, reflow atmosphere, via configuration, and ultimately solder design.A collaboration between three companies consisting of solder materials supplier, a power semiconductor supplier, and an electronic assembly manufacturer worked together for an in-depth study into the effectiveness of solder preforms at reducing voiding under some of the most prevalent bottom terminated components packages. The effects of factors such as thermal pad size, finish on PCB, preform types, stencil design, reflow profile and atmosphere, have been evaluated using lead-free SAC305 low voiding solder paste and micro-fluxed preforms. Design and manufacturing rules developed from this work will be discussed.
Technical Library | 2019-12-12 02:43:44.0
Today we discuss the reason that causes temperature humidity chamber to alarm,In most cases, the equipment alarm is caused by the improper operation in the process of use, which mainly includes following reasons:that are refrigeration system, temperature system and circulating system. First, Refrigeration system 1, refrigeration compressor overpressure alarm. If the refrigerant pressure exceeds the set value, it will stop and alarm at the same time. At this time, the fault must be eliminated and then manually reset. 2, short phase power supply, phase sequence alarm. When the external power supply of the equipment is out of phase or the phase sequence is changed, it will stop and alarm at the same time. 3. The circulating cooling water is short of water to alarm. When the water pressure of the cooling circulating water system is insufficient, it will stop and alarm at the same time, and it must wait for the fault to be eliminated and reset at the same time before it could run normally. 4, refrigeration compressor overheating alarm. When the coil of the compressor is overheated and the power supply of the line is not normal, it will stop and alarm at the same time. Second, Temperature system 1, the overtemperature alarm in the chamber. The sensors in the channel and the sample area are equipped with overtemperature protection devices, and there are also overtemperature protecter on the control panel. When the temperature in the working chamber exceeds the setting value on the controller, it will stop and alarm. 2. sample overtemperature protection. When the temperature in the sample area exceeds the protection temperature set by the controller, it will stop and alarm at the same time. The overtemperature protection of the sample is divided into upper limit protection and lower limit protection, which can be set according to the demand, Third,Circulating system 1. The alarm is caused by the overheating of the circulating fan. When the coil of the fan is over-heated, the alarm will be stopped at the same time. 2. The fan over-current alarm. When the current of the fan exceeds the allowable value, the alarm is stopped at the same time, and the normal operation can only be carried out after the fault maintenance of the overcurrent is completed. This is what we talk about today,if you have more questions,let us know.
Technical Library | 2020-07-29 19:58:48.0
The majority of flexible circuits are made by patterning copper metal that is laminated to a flexible substrate, which is usually polyimide film of varying thickness. An increasingly popular method to meet the need for lower cost circuitry is the use of aluminum on Polyester (Al-PET) substrates. This material is gaining popularity and has found wide use in RFID tags, low cost LED lighting and other single-layer circuits. However, both aluminum and PET have their own constraints and require special processing to make finished circuits. Aluminum is not easy to solder components to at low temperatures and PET cannot withstand high temperatures. Soldering to these materials requires either an additional surface treatment or the use of conductive epoxy to attach components. Surface treatment of aluminum includes the likes of Electroless Nickel Immersion Gold plating (ENIG), which is extensive wet-chemistry and cost-prohibitive for mass adoption. Conductive adhesives, including Anisotropic Conductive Paste (ACP), are another alternate to soldering components. These result in component substrate interfaces that are inferior to conventional solders in terms of performance and reliability. An advanced surface treatment technology will be presented that addresses all these constraints. Once applied on Aluminum surfaces using conventional printing techniques such as screen, stencil, etc., it is cured thermally in a convection oven at low temperatures. This surface treatment is non-conductive. To attach a component, a solder bump on the component or solder printed on the treated pad is needed before placing the component. The Aluminum circuit will pass through a reflow oven, as is commonly done in PCB manufacturing. This allows for the formation of a true metal to metal bond between the solder and the aluminum on the pads. This process paves the way for large scale, low cost manufacturing of Al-PET circuits. We will also discuss details of the process used to make functional aluminum circuits, study the resultant solder-aluminum bond, shear results and SEM/ EDS analysis.
