Automatic digitization of printed circuit layouts

A new technique for automatic input of printed circuit layout data to a computer graphics system, providing a powerful alternative to the existing manual digitization method, is described. The technique is based on optical scanning and graphics recognition. Substantial reduction in the digitized data is made possible by using the properties of printed circuit art work. The technique has been extended to encompass some areas of engineering documentation.     

Programs for two-sided printed circuit board design

A set of programs for the computer-aided design of two-sided PCB's uses a routing algorithm based on artificial intelligence techniques. The data input is translated and checked. The programs also supply a component map as well as the routing solution draft distinguishing the pins, via holes and each side of the board.     

高精度线路板夹角测量算法

结合SUSAN算子,OFMM算子与奇异点去除方法,提出了一种高精度线路板(PCB)夹角测量算法。该算法首先利用SUSAN算子检测出所有可能的边缘点;然后选定区域获取被测夹角的边缘目标点,利用最小二乘拟合法去除奇异的边缘点后,进行亚像素定位;最后对被测量夹角的亚像素边缘点进行直线拟合,利用直线方程计算出夹角。通过对真实线路板图像的测量,实验结果证明了该算法的有效性。该方法已应用于自制的光学自动测量仪,取得较好的效果。     

Automatic inspection system for printed circuit boards

The purpose of this correspondence is to present problems and methods in automating visual inspection of printed circuit boards (PCB's). Vertical and diagonal illumination are useful in detecting PCB patterns correctly. An algorithm comparing local features of the patterns to be inspected with those of the pattern to be referenced is proposed. An inspection system using developed technologies is also described.     

Artificial neural network approach in printed circuit board assembly

In this study, automation of the circuit board assembly process is considered using artificial neural networks with knowledge-based systems. Basic issues in achieving intelligent control that can adapt to changing conditions in the assembly process are discussed. The feasibility of using neural networks for pattern recognition and optimum component insertion sequence generation is examined. The study provides a basic foundation for designing a conceptual architecture for adaptive intelligent control of circuit board assembly. Real-time testing of component recognition is conducted using adaptive resonance theory (ART 1) as a neural network paradigm.     

Design of manufacturing cells: Operation assignment in printed circuit board manufacturing

We consider an operation assignment problem that arose from a printed circuit (PC) board assembly process. Components can either be inserted on boards manually or by machine. The objective is to determine an assignment of components (operations) to a set of capacitated machines (with the remainder of the components inserted manually) to minimize the total set-up and processing cost for assembling all boards. The problem can be formulated as a mixed integer linear program, but is too large to be practically solved. For the case of one machine, we present two different solution heuristics. We show that while each can be arbitrarily bad, on average the algorithms perform quite well. For the case of multiple machines, we present four different solution heuristics. We discuss implementation of our results at Hewlett-Packard.     

A comparison of setup strategies for printed circuit board assembly

This paper develops and tests a set of strategies for operating a single printed-circuit-board assembly machine. In particular, the paper addresses decisions associated with feeder changeover, placement sequencing, and board sequencing. Solution procedures are developed and implemented for a variety of setup management strategies, including group and partial setup. These procedures are tested on a range of problems to determine their relative performance under different production environments. The procedure for group setup is shown to be applicable when component commonality is high and changeovers are time consuming. Partial setup strategies, which focus on minimizing the total production time, are shown to adapt to changing production conditions and therefore outperform the other setup strategies.     

Heuristic approaches for batching jobs in printed circuit board assembly

The goal of the printed circuit board job-batching problem is to minimize the total manufacturing time required to process a set of printed circuit board jobs on an insertion machine. We have developed four families of heuristics to solve this problem: the clustering family, the bin-packing family, a family of sequencing genetic algorithms, and a grouping genetic algorithm. Within each family of heuristics, we developed several variations. Some of the variations use techniques from the literature and some of the techniques we developed specifically for this problem. We test the variations and select a good performer from each family.     

A hierarchical scheduling policy applied to printed circuit board assembly

This paper discusses the performance of a new hierarchical production scheduling policy for flexible manufacturing systems. A detailed simulation of an automated printed circuit card assembly line is used as an experimental test bed. This simulation is a model of a line that is currently being installed at the International Business Machines Corporation (IBM) plant at Tucson, Arizona. The hierarchical strategy is effective in meeting production requirements (both total volume and balance among part types) while limiting average work-in-progress. This is a consequence of the nature of the policy whose key elements are a discipline that, at each level of a hierarchy, keeps material flow within capacity, even in the presence of uncertainty, by using feedback.     

一种印刷电路板缺陷图像边缘信息提取方法

为了较好地提取印刷电路板缺陷图像边缘信息,提出了基于二阶曲线拟合、模式聚类与阈值比较法相结合的印刷电路板缺陷图像边缘信息提取方法。首先分析了最小二乘法拟合的基本原理;然后在此基础上提出了采用二阶曲线拟合法来设定阈值进行拟合得到大致的图像边缘,并分析了其基本原理;最后在模式聚类基础上利用阈值比较法选择适当阈值截取拟合曲线得到图像边缘点、去除噪声边缘点,连接各个图像边缘点可得到缺陷图像的边缘信息。用由显微镜及CCD获取的4幅印刷电路板缺陷图像进行了实验;从实验主观效果看,用该方法提取出图像边缘信息的效果较好,图像边缘比较连续,噪声点极少;从实验客观效果评价看,用该方法所得到的图像边缘信息熵较大。实验结果表明,该方法结合了二阶曲线拟合、模式聚类与阈值比较法优点,可较好地提取出印刷电路板缺陷图像的边缘信息。     

基于GENI-SD的定制化印制电路板工序重要性评估

精准评估影响定制化印制电路板质量的关键工序,可更好地指导企业精益管理产品品质,但企业常用方法难以利用工序关联实体间的深层语义。为解决上述问题,构建工序关联实体知识图谱并提出GENI-SD模型评估工序重要性。首先,使用知识图谱表征工序关联实体间的关系,并采用图神经网络模型GENI对工序节点进行重要性评估;然后,引入基于改进谓词感知注意力机制的采样模块和考虑邻边方向的分数聚合,改进GENI容易聚合到噪声邻节点且未考虑邻边方向的不足,建立工序重要性评估新模型GENI-SD。最后,以PCB车间真实数据开展实验验证,结果显示GENI-SD优于其他对比模型,且得到的Spearman和NDCG@10指标值较GENI所得结果分别提高6.78%和0.71%。该研究为工序重要性评估提供了新的有效方法。     

印制电路板及抗干扰技术的设计研究

介绍了电子线路在进行印制电路板设计(PCB)的过程中应该遵循的设计方法,以及按照PCB设计的一般原则的同时,如何进行抗干扰及抑制噪声的设计。     

An experimental printed circuit board drilling system automated by pattern recognition

The two-dimensional image processing necessary for closed-loop control of automated printed circuit board drilling and a mechanical prototype capable of drilling simulated printed-circuit boards are described. A single closed-loop correction of position permits correction of errors introduced by vidicon camera positional nonlinearity, noise, irregular lighting, inaccuracy of transformational constants, and mechanical slippage. These errors are corrected to an acceptable degree and in a short enough time that automatic drilling may present a challenge to manual drilling labor costs.     

A case-based evolutionary model for defect classification of printed circuit board images

In this research, a case-based evolutionary identification model is developed for PCB defect classification problems. Image understanding is the first and foremost step in the inspection of printed circuit boards. This paper presents a two-phase method for the segmentation of printed circuit board (PCB) images. In the first phase, a set of defect images of several existing basic patterns are stored to form a concept space. In the second phase, a new pattern is evolutionally grabbed using some primitive operators generated by calculating the relative position of several similar cases in the concept space. The case-based reasoning system relies on the software agents derived from past experience within the domain database to determine what feature is required to deliver new patterns in satisfying user’s requirements. Experimental results show that the proposed approach is very effective in identifying the defect patterns.     

Circuit model and signal integrity analysis for multilayer printed circuit board interconnection

A circuit modeling method and signal integrity analysis approach for multilayer printed circuit board interconnection based on the partial equivalent element circuit (PEEC) method is proposed. The multilayer interconnection structure is divided into a via hole and microstrip lines. A three‐dimensional (3D) model of a via hole structure is constructed using the PEEC method with Rao–Wilton–Glisson (RWG) basis functions. The microstrip lines on the top and bottom layers are modeled by PEEC method with RWG basis functions and discrete complex image. The model order reduction method is used to analyze effectively the via hole structure. The equivalent circuit of the via hole structure is simplified, and its physical meaning is defined. The scattering (S) parameter obtained from the proposed method is consistent with simulation results, which are computed using the commercial 3D electromagnetic field analysis software FEKO. The correctness of the proposed method is validated. The S parameters of different dimensions are simulated, and the effects of these dimensions on the electromagnetic characteristics of the via hole structure are analyzed. The model of the entire structure is used to conduct eye diagram simulation. © 2013 Wiley Periodicals, Inc. Int J RF and Microwave CAE 24:478–489, 2014.     

基于计算机图像处理的印刷电路板孔检测

提出了基于计算机视觉的图像处理技术的印刷电路板孔检测的四种算法:直径法、最大直径法、跳跃法以及重心法,并讨论了各算法的复杂度和优劣。     

Optimization of printed circuit board component placement using an efficient hybrid genetic algorithm

The hardware restrictions of surface mount placement machines, such as height, pick and place restrictions, and simultaneous pickup are often in printed circuit board (PCB)-related studies. This study proposes an efficient hybrid genetic algorithm (HGA) for solving the nozzle assignment problem and the component pick and place sequence problem. First, the proposed method obtains the sequence of the automatic nozzle changer (ANC) with the maximum number of simultaneous pickups and the minimum number of picks as the solution of the nozzle setup problem. Then, the proposed method uses the nearest neighbor search (NNS), 2-optimization, and a genetic algorithm (GA) with the known ANC sequences to obtain the PCB assembly time with the optimal component pick and place sequence. Experiments are conducted on the PCB of the EVEST EM-780 surface mount placement machine. Results show that the proposed HGA gives the lowest total number of picks, the shortest total head movement distance, and the minimum total PCB assembly time compared to those of other methods.     

An overview of computer aided printed circuit board design in an electronic industry

The present article covers the gradual introduction of computer aids into the laying out of PCBs in an electronic industry, the internal development and introduction of PCB layout stations in that industry, and the subsequent orientation on PCB design aids supplied by specialist companies. For the particular industry in question, that orientation resulted in the acquisition of commercially available systems. The latter was based on an internal study in which five PCB layout systems were compared - the results of which are included in the article. The article also touches upon the economic aspects involved to some extent. In concluding, the choice of approach to design aids for PCBs, i.e., buy or make, is reviewed.     

A memetic algorithm-based heuristic for a scheduling problem in printed circuit board assembly

This research develops a memetic algorithm to solve Printed Circuit Board (PCB) scheduling with sequence-dependent setup times on a single machine with constrained feeder capacity. The objective of the scheduling problem is to minimize the total weighted tardiness. A memetic algorithm-based heuristics is developed by integrating a genetic algorithm, Minimum Slack Time (MST) scheduling rule, “Keep Tool Needed Soonest” (KTNS) policy, and a local search procedure. Application of the MA results in two outcome plans: a scheduling plan and a feeder setup plan.Numerical experiments show that compared to a number of commonly used dispatching rules, the memetic algorithm provides better solutions in term of minimum total weighted tardiness. Even the computation is the highest, it still practical. Calibration of MA parameter values is also explored in this study.