Printed Circuit Board Manufacturing Research Articles

Multimodal Human–Robot Interaction Using Gestures and Speech: A Case Study for Printed Circuit Board Manufacturing

In recent years, technologies for human–robot interaction (HRI) have undergone substantial advancements, facilitating more intuitive, secure, and efficient collaborations between humans and machines. This paper presents a decentralized HRI platform, specifically designed for printed circuit board manufacturing. The proposal incorporates many input devices, including gesture recognition via Leap Motion and Tap Strap, and speech recognition. The gesture recognition system achieved an average accuracy of 95.42% and 97.58% for each device, respectively. The speech control system, called Cellya, exhibited a markedly reduced Word Error Rate of 22.22% and a Character Error Rate of 11.90%. Furthermore, a scalable user management framework, the decentralized multimodal control server, employs biometric security to facilitate the efficient handling of multiple users, regulating permissions and control privileges. The platform’s flexibility and real-time responsiveness are achieved through advanced sensor integration and signal processing techniques, which facilitate intelligent decision-making and enable accurate manipulation of manufacturing cells. The results demonstrate the system’s potential to improve operational efficiency and adaptability in smart manufacturing environments.

Wasserstein distributionally robust learning for predicting the cycle time of printed circuit board production

This paper proposes a Wasserstein distributionally robust learning (WDRL) model to predict the production cycle time of highly mixed printed circuit board (PCB) orders on multiple production lines. The PCB production cycle time is essential for optimizing production plans. However, the design of the PCB, production line configuration, order combinations, and personnel factors make the prediction of the PCB production cycle time difficult. In addition, practical production situations with significant disturbances in feature data make traditional prediction models inaccurate, especially when there is new data. Therefore, we establishe a WDRL model, derive a tight upper bound for the expected loss function, and reformulate a tractable equivalent model based on the bound. To demonstrate the effectiveness of this method, we collected data related to surface mounted technology (SMT) production lines from a leading global display manufacturer for our computational experiments. In addition, we also designed experiments with perturbations in the training and testing datasets to verify the WDRL model’s ability to handle perturbations. This proposed method has also been compared with other machine learning methods, such as the support vector regression combined with symbiotic organism search, decision tree, and kernel extreme learning machine, among others. Experimental results indicate that the WDRL model can make robust predictions of PCB cycle time, which helps to effectively plan production capacity in uncertain situations and avoid overproduction or underproduction. Finally, we implement the WDRL model for the actual SMT production to predict the production cycle time and set it as the target for production. We observed a 98–103 % achievement rate in the last 20 months since the implementation in September 2022.

Advanced AI Technologies for Defect Prevention and Yield Optimization in PCB Manufacturing

The integration of Advanced Artificial Intelligence (AI) technologies in Printed Circuit Board (PCB) manufacturing has revolutionized the industry, offering significant improvements in defect prevention and yield optimization. As PCB manufacturing processes become increasingly complex and intricate, traditional methods of defect detection and quality assurance are often insufficient to meet the high demand for precision and efficiency. This paper explores the application of cutting-edge AI methodologies, including machine learning, computer vision, and neural networks, to address critical challenges in PCB production. The primary focus of this research is on the role of AI in enhancing automated defect detection systems and optimizing production yield. AI-based systems such as predictive maintenance, real-time process monitoring, and intelligent decision-making have been shown to drastically reduce defects while improving overall production throughput. Machine learning algorithms can identify subtle defects in real time, often undetectable by conventional methods, while neural networks can analyze historical data to predict potential failures before they occur. Additionally, AI-driven optimization techniques help manufacturers adjust production parameters dynamically, ensuring higher yields and minimizing waste. Through a combination of theoretical analysis and case studies, this paper highlights the effectiveness of AI-driven solutions in PCB manufacturing. Results from industry applications indicate significant improvements in both quality control and yield rates, providing a competitive edge to manufacturers adopting these technologies. Furthermore, this paper discusses future trends, including the integration of AI with the Internet of Things (IoT), edge computing, and sustainable manufacturing practices, which will further enhance the capabilities of AI systems in this field. The findings suggest that advanced AI technologies are not only capable of overcoming existing challenges in defect prevention but also hold the potential to reshape the future of PCB manufacturing by offering highly adaptive, precise, and efficient solutions. This research underscores the transformative impact of AI in modernizing manufacturing processes, making it an indispensable tool for the future of the PCB industry.

AI-Driven Quality Control in PCB Manufacturing: Enhancing Production Efficiency and Precision

This paper investigates the application of Artificial Intelligence (AI) in enhancing quality control within Printed Circuit Board (PCB) manufacturing processes, focusing on how AI-driven technologies improve production efficiency and precision. The research addresses traditional quality control methods, such as manual inspection and Automated Optical Inspection (AOI), highlighting their limitations in keeping up with the complexities and demand for high-precision PCBs in modern electronics. The study delves into how AI technologies, particularly machine learning, computer vision, and predictive analytics, are being leveraged to overcome these limitations. By automating defect detection, improving accuracy, and enabling real-time analysis, AI systems not only streamline the quality control process but also significantly reduce human error and production costs. AI-driven quality control systems are shown to increase defect detection rates, reduce inspection times, and enhance overall production throughput. The paper includes a comparative analysis between traditional and AI-based quality control methods, revealing a notable improvement in both detection accuracy and production speed when AI systems are employed. Additionally, cost efficiency is explored, demonstrating how AI systems reduce waste, minimize rework, and lower operational costs. The potential challenges of AI implementation, such as the high initial costs, data requirements, and integration with legacy systems, are also discussed. The paper concludes that despite these challenges, AI offers a transformative solution to the growing demands of the PCB manufacturing industry, with the ability to scale effectively and adapt to future technological advancements. Ultimately, this research underscores the significant role of AI in revolutionizing PCB quality control by providing a more efficient, precise, and cost-effective approach, paving the way for further innovation in the electronics manufacturing sector.

Hybrid inspection of printed board defects

Objectives. A hybrid approach to the problem of searching and classifying defects in printed circuit boards (PCB) is proposed. Key factors and trends in the design and production of PCBs are considered. The relevance of the study is determined by the use of new materials and production technologies.Methods. A hybrid approach based on the algorithm of comparison with reference and the use of the YOLO family of neural network models for detecting objects is used to solve the problem.Results. Models were trained on public sets of PCB images with six classes of defects, and their accuracy was assessed using generally accepted metrics.Conclusion. Experiments have shown that the YOLOv8 neural network architecture has high accuracy of defect detection, low sensitivity to image quality, presence of text and graphic objects on the PCB, but the low quality of training datasets imposes restrictions on the use of only neural networks for defect detection. It is proposed to use a hybrid approach to improve the quality of defect inspection by applying different methods depending on the quality assessment of the analyzed images.

Wideband 2×2 antenna-in-package based on magneto-electric dipole array antenna for 5G mmWave applications

This paper presents an antenna-in-package (AiP) design realised with the conventional multi-layer printed circuit board manufacturing method. The design consists of a wideband 2×2 magneto-electric dipole array antenna operating from 24.25−29.5 GHz and a wideband transition from the analogue beamformer integrated into the proposed MED array antenna (IMED). The IMED array antenna has been fabricated with two distinct NXP analogue beamformer chips, i.e., MMW 9004 KC and MMW 9002 KC covering the N257 and the N258 band, respectively. The measured effective isotropic radiated power at P1dB was 35.3 dBm and 35.1 dBm for the IMED with the MMW 9004 KC and the MMW 9002 KC analogue beamformer chip, respectively. Our proposed antenna demonstrates the feasibility of designing a single wideband AiP that can be integrated with different analogue beamformers operating within the frequency band of the proposed antenna. This is true, provided the RFIC used for integration has the same footprint for RF ports, serial peripheral interface control ports, and DC power supply ports. The primary benefit of the proposed technique is the design antenna can adapt the operating frequency to different frequency standards by incorporating additional analogue chips without increasing the design complexity. This feature enables the antenna manufacturer to tailor the antenna products to different frequency standardisations depending on where the antenna will be employed. The AiP operates at 5G millimeter-wave (mmWave) frequencies, with the potential for Internet of Things applications. Furthermore, from our simulation results, the proposed IMED can potentially be extended as a phased array antenna with 2D scanning.

Implementation of microcontroller board on a sustainable and degradable PLA/flax composite substrate: a case study

In this paper, we present a novel polylactic-acid/flax-composite substrate and the implementation of a demonstrator: a microcontroller board based on commercial design. The substrate is developed for printed circuit board (PCB) applications. The pre-preg is biodegradable, reinforced, and flame-retarded. The novel material was developed to counter the increasing amount of e-waste and to improve the sustainability of the microelectronics sector. The motivation was to present a working circuit in commercial complexity that can be implemented on a rigid substrate made of natural, bio-based materials with a structure very similar to the widely used Flame Retardant Class 4 (FR4) substrate at an early technological readiness level (2–3). The circuit design is based on the Arduino Nano open-source microcontroller board design so that the demonstration could be programmable and easy to fit into education, IoT applications, and embedded designs. During the work, the design was optimized at the level of layout. The copper-clad pre-preg was then prepared and processed with subtractive printed wiring technology and through hole plating. The traditional surface mounting methodology was applied for assembly. The resulting yield of PCB production was around 50%. Signal analysis was successful with analogue data acquisition (voltage) and low-frequency (4 kHz) tests, indistinguishable from sample FR4 boards. Eventually, the samples were subjected to highly accelerated stress test (HAST). HAST tests revealed limitations compared to traditional FR4 printed circuit materials. After six cycles, the weight loss was around 30% in the case of PLA/Flax, and as three-point bending tests showed, the possible ultimate strength (25 MPa at a flexural state) was reduced by 80%. Finally, the sustainability aspect was assessed, where we found that ∼95 vol% and ∼90 wt% of the traditional substrate can be substituted, significantly easing the load of waste on the environment.

Local and Global Context-Enhanced Lightweight CenterNet for PCB Surface Defect Detection.

Printed circuit board (PCB) surface defect detection is an essential part of the PCB manufacturing process. Currently, advanced CCD or CMOS sensors can capture high-resolution PCB images. However, the existing computer vision approaches for PCB surface defect detection require high computing effort, leading to insufficient efficiency. To this end, this article proposes a local and global context-enhanced lightweight CenterNet (LGCL-CenterNet) to detect PCB surface defects in real time. Specifically, we propose a two-branch lightweight vision transformer module with local and global attention, named LGT, as a complement to extract high-dimension features and leverage context-aware local enhancement after the backbone network. In the local branch, we utilize coordinate attention to aggregate more powerful features of PCB defects with different shapes. In the global branch, Bi-Level Routing Attention with pooling is used to capture long-distance pixel interactions with limited computational cost. Furthermore, a Path Aggregation Network (PANet) feature fusion structure is incorporated to mitigate the loss of shallow features caused by the increase in model depth. Then, we design a lightweight prediction head by using depthwise separable convolutions, which further compresses the computational complexity and parameters while maintaining the detection capability of the model. In the experiment, the LGCL-CenterNet increased the mAP@0.5 by 2% and 1.4%, respectively, in comparison to CenterNet-ResNet18 and YOLOv8s. Meanwhile, our approach requires fewer model parameters (0.542M) than existing techniques. The results show that the proposed method improves both detection accuracy and inference speed and indicate that the LGCL-CenterNet has better real-time performance and robustness.

Effective oxidation decomplexation of Cu-EDTA and Cu2+ electrodeposition from PCB manufacturing wastewater by persulfate-based electrochemical oxidation: Performance and mechanisms.

Complex wastewater matrices such as printed circuit board (PCB) manufacturing wastewater present a major environmental concern. In this work, simultaneous decomplexation of metal complex Cu-EDTA and reduction/electrodeposition of Cu2+ was conducted in a persulfate-based electrochemical oxidation system. Oxidizing/reductive species were simultaneously produced in this system, which realized 99.8% of Cu-EDTA decomplexation, 94.5% of Cu2+ reduction/electrodeposition under the conditions of original solution pH = 3.2, electrode distance = 3cm, [Na2S2O8]0 = 5mM, current density = 12mA/cm2, and reaction time = 180min. The total treatment cost is as low as 0.80 USD/mol Cu-EDTA. Effective mineralization (74.1% total organic carbon removal) of the solution was obtained after 3h of treatment. •OH and SO4•- drove the Cu-EDTA decomplexation, destroying the chelating sites and finally it was effectively mineralized to CO2, H2O and Cu2+. The mechanisms of copper electrodeposition on the stainless steel cathode and persulfate activation by the BDD anode were proposed based on the electrochemical measurements. The electrodes exhibited excellent reusability and low metal (total iron and Ni2+) leaching during 20 cycles of application. This study provide an effective and sustainable method for the application of the electro-persulfate process in treating complex wastewater matrices.

Dual-band flexible metamaterial absorber working in 5G band

This article presents a thin and flexible artificial electromagnetic absorber with two absorption peaks at frequencies of 28 and 39 GHz for 5G communication. Copper and a flexible FR4 substrate are used in a pyramid-shaped layered configuration, achieving absorption rates exceeding 99% at 28 and 39 GHz. The thickness of the proposed structure is only 0.34 mm, which is ∼1/32 and 1/23 of the corresponding free-space wavelengths at the absorption frequencies. Due to its symmetric structure, the absorber is polarization-insensitive. Furthermore, the proposed structure exhibits over 90% absorption within the incident angle range of −45° to 45°. To investigate its absorption mechanism, the electric field and magnetic field distributions at the absorption frequencies were analyzed. Then a 150 × 150 mm2 sample was fabricated using printed circuit board manufacturing techniques. This sample was placed on flat or curved surfaces and tested under normal or oblique incidences. The experimental results were consistent with the simulated results, confirming the feasibility of the design. This absorber can be applied in 5G communication and millimeter-wave imaging.

Sustainable printed circuit board substrates based on flame-retarded PLA/flax composites to reduce environmental load of electronics: Quality, reliability, degradation and application tests

The present paper introduces a novel, sustainable approach to produce an eco-friendly Printed Circuit Board (PCB) substrate; a substitute for traditional substrates, to significantly reduce e-waste. We present the prepreg technology, the road to actual circuit assembly with application studies, life cycle analysis (LCA), and sustainability analysis. The flame-retarded prepregs and resulting PCB assemblies were based on polylactic acid (PLA), the structure is reinforced with flax textiles. After copper lamination, subtractive PCB production was performed, and thermal and mechanical reliability was investigated in the case of both laminated and bare substrates. Steps of surface roughness, peel and thermal analysis followed. After a new set of assemblies, the post-assembly analysis was extended with further shear strength analysis on the soldered components and mass analysis regarding thermal processes. The evaluation showed that PLA/Flax substrates provide reliable structural performance up to 200 °C in the reflow soldering process; this allows limited but stabilized application possibilities with specific eco-friendly lead-free solders. A basic blinker circuit and a field programmable gate array (FPGA)--based design was produced and tested; the latter has the general complexity of a commercial circuit. A vol% and wt% analysis extended our discussion with a reduction of harmful components in waste in the range of 90%, which is a disruptive and significant result. Life cycle analysis (LCA) quantified the ecological impact of the assembly, highlighting a significant ease on environmental load (∼10%) for the total assembly. Finally, a qualitative degradation study was introduced to the prepared samples to investigate short-term stability with mechanical-, colour-, mass- and scanning electron microscopy (structure) analysis. Early results show that the boards can withstand the harsh environment of a composting bin for a few days, but in the time of a few weeks, degradation starts, pointing to eventual decomposition. The work directly connects with multiple sustainability development goals.

Telemetric angle and position sensing using millimeter-wave metamaterial and a frequency-modulated continuous-wave (FMCW) chip

Abstract. We present a fully telemetric sensor concept for angle and position measurement. It is based on single-layer millimeter-wave metamaterials that exhibit an anisotropic resonant behavior in interaction with incident electromagnetic waves. The angle of rotation is determined from the reflected millimeter waves of the metamaterial target using a millimeter wave chip transceiver. We use a metamaterial geometry exhibiting anisotropic Fano-type resonant behavior. The Fano-type resonance shows a distinct minimum in the reflection spectrum, even with a single layer of metamaterial. The metamaterial target is manufactured on a printed circuit board (PCB) laminate with low-cost standard manufacturing methods. We present an analytical model estimating the resonance frequency of the metamaterial used. The model allows us to assess whether with the Fano-type metamaterial unit cell structure resonance frequencies in the millimeter wave regime are achievable and compliant with standard PCB manufacturing design rules. We performed proof-of-principle experiments with the metamaterial targets and a vector network analyzer, assisted by a detailed analysis of the sensor effect by means of finite-element method calculations. Finally, we implemented a demonstrator setup containing a state-of-the-art frequency-modulated continuous-wave (FMCW) radar chip and a metamaterial target manufactured with standard PCB manufacturing processes.

Comparison of Different NDT Techniques for Evaluation of the Quality of PCBs Produced Using Traditional vs. Additive Manufacturing Technologies.

Multilayer printed circuit boards (PCBs) can be produced not only in the traditional way but also additively. Both traditional and additive manufacturing can lead to invisible defects in the internal structure of the electronic component, eventually leading to the spontaneous failure of the device. No matter what kind of technology is used for the production of PCBs, when they are used in important structures, quality control is important to ensure the reliability of the component. The nondestructive testing (NDT) of the structure of manufactured electronic components can help ensure the quality of devices. Investigations of possible changes in the structure of the product can help identify the causes of defects. Different types of manufacturing technologies can lead to diverse types of possible defects. Therefore, employing several nondestructive inspection techniques could be preferable for the inspection of electronic components. In this article, we present a comparison of various NDT techniques for the evaluation of the quality of PCBs produced using traditional and additive manufacturing technologies. The methodology for investigating the internal structure of PCBs is based on several of the most reliable and widely used technologies, namely, acoustic microscopy, active thermography, and radiography. All of the technologies investigated have their advantages and disadvantages, so if high-reliability products are to be produced, it would be advantageous to carry out tests using multiple technologies in order to detect the various types of defects and determine their parameters.

Evaluation of the Environmental Impact within Semiconductor Packaging Materials

This paper reports the sustainability of materials and components required for PCB manufacturing, namely the substrate material, die-attach method and IC chip design. Electronics manufacturing processes are generally decided by the technical and economic requirements, and not sustainability, resulting in poor practices and unintended outcomes. Alternative methods could be used and this paper reviews some of the drivers and opportunities for sustainable PCB manufacturing. A lifecycle assessment (LCA) was performed on simple Printed Circuit Boards (PCB) and a comparison of the manufacturing approach using FR-4, polyimide and paper-based substrates is made. The impacts of different processing steps were considered, all scored using the ReCiPe Endpoint. The results found solder material has a significant influence, with lower-temperature solders reducing the overall environmental impact. However, it has been found that the component that has the biggest environmental impact overall is the IC. We discuss how die size, technology node and packaging formats effects this rating, and also show how the move towards alternative materials can reduce the environmental impact of electronic products.

Simulation‐based optimisation for order release of printed circuit board workshop with process switching constraints

AbstractWorkload control (WLC) is usually employed to make order release to attain workload balance, satisfactory delivery rate and high production efficiency. However, in the real production environment of printed circuit board (PCB) industries, slight modifications in the product process shifts the bottleneck resources which leads to misjudge the effect of WLC and may ultimately increase the lateness of orders. Therefore, this research focuses on the order release problem of PCB production system considering main process flow and shifting of bottlenecks. At first, certain improvements are proposed on the classic WLC method and two order release control strategies based on process switching are designed to generate order release plan on the basis of Lancaster University Management School Corrected Order Release method. Furthermore, different scheduling rules are investigated along with the upper workload limits on the PCB system simultaneously. Finally, a simulation model is developed to analyse the impact of order release methods on the system performance through simulation experiments. Furthermore, extensive simulation experiments for different scheduling rules on bottleneck resource and different workload upper limit ratios are also carried out in the current research. Simulation results show that the process order release control strategy based on process switching has a strong adaptability in PCB manufacturing system.

Evaluating Performance Incorporating Multi-Criteria Decision Making and ESG Index: The Case of Taiwanese PCB Industry

The Printed Circuit Board (PCB) industry is known as the "mother of electronic system product" in the high-tech electronics industry. When this industry enters a mature stage, cost control becomes the key to its success. Additionally, as the corporate’s awareness of social responsibility like ESG (Environment, Social, & Governance) has risen, the cost control remains a critical indicator for evaluating a company's performance. This study uses the consolidated financial statements of 35 companies in Taiwan's listed PCB industry through collecting data from the Taiwan Stock Exchange from 2022 to 2022. This study chooses 16 key financial indicators through expert opinions and selects 7 input variables and 5 output variables from 5 screening criteria. Then, through the normalization of grey relational data, the degree of influence of each indicator on the performance of PCB manufacturers is analyzed, and which independent variables have better prediction power through the multiple regression model is achieved. The Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) analysis in Multi-Criteria Decision-Making (MCDM) is applied to identify the ranking. The relative distance compared with the best manufacturer and the worst manufacturer is used to evaluate and rank the pros and cons of each ranking. VIKOR is then used to analyze ranking further. The results of data analysis have shown slightly different rankings based on TOPSIS and VIKOR. However, it seems the analysis of VIKOR is more accurate. The comparison of Taiwanese PCB manufacturers before and after the ranking is also revealed. Several practical directions for corporate planning or improvement are suggested. The link between ESG indicators and finance is observed not significant.

Liquid Metal‐Based High‐Density Interconnect Technology for Stretchable Printed Circuits

AbstractHigh‐density interconnect (HDI) technology for liquid metal (LM)‐based stretchable printed circuit boards is crucial for expanding their applicability. HDI technology provides high‐resolution multilayer circuits with a high density of components, as required for next generation of neuroprobes and ultrasonic and sensor arrays. This study presents a HDI technique utilizing laser engraved micro grooves in silicone with a protective lift‐off mask of polyvinyl alcohol (PVA) and subsequent microscale LM particle spray deposition. This approach achieves high‐resolution LM patterns and enables multilayer connectivity and high‐density integration of components simultaneously, that is, realizing HDI technology. It is demonstrated using a stretchable 0201 LED display with a density of six leads per mm2 and a cochlear implant (CI) electrode array. The demonstrated manufacturing of the CI has the potential to enable fully automated printed circuit board manufacturing of such implants with increased precision and throughput. Implants in guinea pigs show that the CI is capable of activating the auditory neuron with electrical auditory brainstem response (eABR) and electrical compound action potential (eCAP) of high quality. Moreover, the U‐shaped cross section of the LM interconnects provides a higher mechanical shock resistance of the circuit than that of normal rectangular cross sections.

Electrochemical detection of myeloperoxidase (MPO) in blood plasma with surface-modified electroless nickel immersion gold (ENIG) printed circuit board (PCB) electrodes

Printed circuit board (PCB) based biosensors have often utilized hard gold electroplating, that nullifies the cost advantages of this technology as compared to screen printed electrodes. Electroless nickel immersion gold (ENIG) is a popular gold deposition process widely used in PCB manufacturing, but vulnerable to pinhole defects and large surface roughness, which compromises biosensor performance. In this work, we present a method to address these challenges through electrodeposition of methylene blue (MB) to cover surface defects and improve electroactivity of ENIG PCB electrodes. We also demonstrate a process to realize in situ synthesis of gold nanoparticles (AuNPs) using acid-functionalized multi-walled carbon nanotubes (MWCNTs) as scaffold, that are used to immobilize antibody for the target molecule (myeloperoxidase: MPO, early warning biomarker for cardiovascular diseases) through a modified cysteamine/gluteraldehyde based process. The processing steps on the electrode surface are developed in a manner that do not compromise the integrity of the electrode, resulting in repeatable and reliable performance of the sensors. Further, we demonstrate a cost-effective microfluidic packaging process to integrate a capillary pump driven microfluidic channel on the PCB electrode for seamless introduction of samples for testing. We demonstrate the ability of the sensor to distinguish clinically abnormal concentrations of MPO from normal concentrations through extensive characterization using spiked serum and blood plasma samples, with a limit of detection of 15.79 ng/mL.

Image Segmentation of Fiducial Marks with Complex Backgrounds Based on the mARU-Net

Circuits on different layers in a printed circuit board (PCB) must be aligned according to high-precision fiducial mark images during exposure processing. However, processing quality depends on the detection accuracy of fiducial marks. Precise segmentation of fiducial marks from images can significantly improve detection accuracy. Due to the complex background of PCB images, there are significant challenges in the segmentation and detection of fiducial mark images. In this paper, the mARU-Net is proposed for the image segmentation of fiducial marks with complex backgrounds to improve detection accuracy. Compared with some typical segmentation methods in customized datasets of fiducial marks, the mARU-Net demonstrates good segmentation accuracy. Experimental research shows that, compared with the original U-Net, the segmentation accuracy of the mARU-Net is improved by 3.015%, while the number of parameters and training times are not increased significantly. Furthermore, the centroid method is used to detect circles in segmentation results, and the deviation is kept within 30 microns, with higher detection efficiency. The detection accuracy of fiducial mark images meets the accuracy requirements of PCB production.

Reliability evaluation for time-based stochastic manufacturing networks with time-dependent reliability

ABSTRACT This study aims to evaluate the system reliability for a time-based stochastic manufacturing network (TSMN). The architecture of a TSMN includes arcs and nodes where each node is an inspection station and each arc is a workstation of identical machines. Due to the possibility of partial or complete maintenance and machine failures, the reliability should be time-dependent and the arcs could be considered as stochastic capacities. To consider time factor, the Weibull reliability function is utilized to characterize the time-dependent reliability of each machine. Then, based on the reliability of each machine, the workstation reliability can be derived, where the workstation reliability is the probability that a workstation can provide sufficient number of machines to complete a demand until a given time. Focusing on a given TSMN with the specified demand and constrained operating time, the performance for a TSMN, which is referred to as TSMN reliability, can be calculated in terms of workstation reliability. In addition, the situation for machines having different times under operation is analyzed for TSMN reliability. A step-by-step procedure for evaluating the TSMN reliability is developed, and a printed circuit board manufacturing system is discussed for the proposed TSMN reliability procedure.