Multivariate regression modeling for monitoring quality of injection moulding components using cavity sensor technology: Application to the manufacturing of pharmaceutical device components

There is an increased demand within the moulding industry to improve the quality of moulded parts by maintaining consistent tolerances and overall dimensions. This interest is more important in areas of the moulding industry that are dedicated to pharmaceutical devices, where a quality by design approach is now expected to be adopted. A pharmaceutical device is an assembly of different plastic components which are manufactured by injection moulding; many have critical quality parameters which affect not only the device appearance but also more importantly its performance for drug delivery. Hence, the need of better understanding and control of injection moulding processes. This study presents the use of multivariate regression modeling approach to monitor the quality of the final product using cavity sensor technology (CST). The influence of the injection moulding process parameters on the quality of the final parts have been investigated using a design of experiment approach. The results demonstrate that the Partial Least Squares (PLS) regression model based on cavity pressure sensor data could be successfully used to monitor the quality (weight, dimensions) of the final product in plastic injection moulding.     

Graph-based feature recognition for injection moulding based on a mid-surface approach

This paper presents a novel CAD feature recognition approach for thin-walled injection moulded and cast parts in which moulding features are recognised from a mid-surface abstraction of the part geometry. The motivation for the research has been to develop techniques to help designers of moulded parts to incorporate manufacturing considerations into their designs early in the design process. The main contribution of the research has been the development of an attributed mid-surface adjacency graph to represent the mid-surface topology and geometry, and a feature recognition methodology for moulding features. The conclusion of the research is that the mid-surface representation provides a better basis for feature recognition for moulded parts than a B-REP solid model. A demonstrator that is able to identify ribs, buttresses, bosses, holes and wall junctions has been developed using C++, with data exchange to the CAD system implemented using ISO 10303 STEP. The demonstrator uses a commercial algorithm (I-DEAS) to create the mid-surface representation, but the feature recognition approach is generic and could be applied to any mid-surface abstraction. The software has been tested on a range of simple moulded parts and found to give good results.     

A Data-drivenParameter Planning Method for Structural Parts NC Machining

Structural parts are generallyused to compose the main load-bearing components in various mechanical products, and are usuallyproduced by NC machining where the machining parameters heavily determine the final production quality, efficiency and cost. Due to the complex structures and high precision requirements, a large amount of human interactions are usually required to modify the machining parameters generated by existing optimisation model-based or expert system-based methods, which will induce unstable machining quality and low efficiency. This paper proposes a data-driven methodfor machining parameter planning by learningthe parameter planning knowledge from thehigh-qualityhistorical processing files. An attribute graph is first defined to represent the part model. Then for each of the machining operations in the historical processing files, the machining parameters are correlated to a sub-graph that refers to the faces to be machined in this operation. By this way, a graph dataset of machining parameters could beconstructed from the historical processing files, and graph neural networks (GNN) are established to learn the planning models for machining parameters. The proposed method provides an end-to-end strategy for constructing machining parameter planning models thus human interactions can be greatly reduced and the performance of the models are able to be improved as the increase in historical processing files. In the case study, the historical processing files of aircraft structural parts machining are used to train the GNN models for planning cutting width, cutting depth and machining feedrate, and the prediction accuracies reach 95.50%, 94.79%, 95.02% respectively.     

FDM复合式路径填充的生成与优化

熔融沉积制造(FDM)是一种用填充方式来得到每层截面的快速成型工艺,由于成型轨迹的走向直接影响到成型件的外观和成型效率,因此选择一种好的成型算法格外重要。在目前现有的成型轨迹中,复合式扫描法由于在制件精度和加工效率上的诸多优势,成为研究的热点。基于分形填充和偏置填充本身所具有的优点,提出了一种复合优化轨迹的方法,并用分而治之算法对生成的路径进行了最大程度的优化,以减少喷头的开关次数和拉丝现象,保证制件的成型精度和强度,并且已成功应用在实际加工中。     

Manufacturing of polymer micro parts by ultrasonic plasticization and direct injection

In ultrasonic plasticizing, energetic ultrasound is used to heat and to plasticize thermoplastic polymers. The basic idea of the process is to deform a material cyclically at ultrasonic frequencies. The deformations are applied on the material by a common ultrasound sonotrode; the plasticization takes place in a plasticizing chamber. The generated melt is directly injected into micro cavities, and hence, micro parts can be moulded easily with the system. In this paper, micro parts being moulded with the process variation “direct injection” are analysed with regard to their weight resulting from the process parameter settings and with regard to their morphology. Furthermore, mixing effects in the plasticizing chamber are being looked at.     

Decomposing deviations of scanned surfaces of sheet metal assemblies

We present a finite-element-based approach to support quality assurance for assembly processes of non-rigid sheet metal parts in the automotive and aerospace industries. These parts have adjustable mechanical boundaries, making it possible to compensate geometrical deviations caused by the production process of components. Every part produced must be adjusted individually. Determining what boundaries to adjust to and in what direction is challenging and requires experience. Our goal was to identify sources of measured surface deviations after part assembly and provide valuable information to the quality assurance engineer. We solve the corresponding parameter estimation problem via a least-squares approach. From the estimated parameter states that led to measured deviations, additional visualizations are calculated to support the inspection engineer when deriving countermeasures.     

高分辨图像区域填充的并行计算方法

针对传统种子填充算法无法充分利用多核处理器性能以及需要人工指定种子的不足,提出基于动态连接和并查集的并行随机种子反向填充算法。将填充任务分为随机种子生成、并行填充、连通区域识别、并行合并与反转步骤,并采用C++和CUDA-C语言分别实现各步骤的CPU和GPU版本。在此基础上,从众多参数组合中选择能发挥硬件最佳性能的参数。实验结果表明,相比传统反向填充算法,并行随机种子反向填充算法能充分利用多核、异构处理器的多线程并行能力,在处理6种不同分辨率的单张和批量图像时获得了平均3.84倍和4.43倍的加速比,其中在处理8 KB高分辨图像时,最高取得6.05倍和7.09倍的加速比。     

A Hybrid Method for Quality Evaluation in the Context of Use for Mobile (3D) Television

Controlled psychoperceptual quality evaluation experiments are used to assess the excellence of produced audiovisual quality from fundamental signal processing algorithms to consumer services. When compromising produced quality for consumer services, used in dynamic and heterogeneous mobile contexts, the ecological validity of conventional quality evaluation methods can be questioned. The goal of this paper is to develop a method for evaluating the experienced multimedia quality in the context of use. We conducted three studies where the quality of mobile 2D and 3D television was assessed in three different field contexts, one simulated context and one controlled laboratory situation when audio-video compression and transmission parameters were varied. We propose a hybrid method for the design, data-collection and analysis of the experiments in the contexts of use. Its novelty is to complement conventional quantitative quality evaluation with concrete tools to identify factors that surround the assessment in the context. The methodological framework is part of our long-term aim to measure and understand the user-centered quality of experience.     

A sub-space artificial neural network for mold cooling in injection molding

The applications of artificial intelligence (AI) have considerably expanded over recent years. A new class of industrial systems is beginning to evolve that incorporates using high volume data and advanced analytics to better optimize product quality while reducing energy consumption. Artificial neural networks (ANN) when combined with advanced modeling and control, begins to form an AI platform that can be further enhanced for factories of the future. This paper provides a demonstration of such initial work that can be further developed for future systems in a generic way. When considering polymer processing such as plastic injection molding, the mold cavity temperature (MCT) profile directly relates to part quality and part reject rates. Therefore, it is desirable to optimize the mold cooling process using real time control of MCT as it directly affect part quality. However, MCT is affected by a number of interacting nonlinear dynamic parameters that are often neglected due to the challenge of quantifying such parameters. Advanced model based control algorithms are often used for providing improved control of complex systems. However, they depend on good model formulations that are analytically insufficient. An online intelligent system identification approach for the mold cooling process is developed and tested. An ANN is designed to adjust online sub-space parameters that govern a mold cooling model. Results demonstrate that this online ANN approach can be used to accurately predict the dynamic behavior of mold cavity surface temperature. This is key to many industrial systems where their states are not directly observable and uncertainties are unknown. The methodology can be readily adapted for different operating conditions as in this case of polymer processing and has good potential for its integration with advanced model based control schemes and cloud computing approaches for the next generation of machines.     

Characterization of closed-loop measurement accuracy in precision CNC milling

This study investigates the closed-loop measurement error in computer numerical controlled (CNC) milling as they relate to the different inspection techniques. The on-line inspection of machining accuracy using a spindle probe has an inherent shortcoming because the same machine-produced parts are used for inspection. In order to use the spindle probe measurement as a means of correcting deviations in machining, the magnitude of measurement errors needs to be quantified. The empirical verification was made by conducting three sets of cutting experiments, followed by a design of experiment with three levels and three factors on a state-of-the-art CNC machining center. Three different material types and parameter settings were selected to simulate a diverse cutting condition. During the cutting, the cutting force and spindle vibration sensor signals were collected and a tool wear was recorded using a computer vision system. The bore tolerance was gauged by a spindle probe as well as a coordinate-measuring machine. The difference between the two measurements was defined as a closed-loop measurement error and the subsequent analysis was performed to determine the significant factors affecting the errors. The analysis results showed the potential of improving production efficiency and improved part quality.     

匹配滤波在SAR目标单个散射部件检测中的应用

目的目标部分缺失是SAR(synthetic aperture radar)ATR(automatic target recognition)中的难点问题,实现SAR目标散射部件级别的检测可以有效解决这一问题。方法基于目标的部件级别3维电磁散射模型提出了一种基于匹配滤波的单个散射部件检测方法。该方法通过模型预测单个散射部件的图像构造匹配滤波器,并通过在模型3维参数域的调整实现了匹配滤波器在3维空间的滑动,得到最佳的部件检测位置和最大相关系数。为克服方位角估计不准的限制,采用了领域搜索寻找最佳检测结果。按照散射部件的强度由强至弱序惯检测各个散射部件。采用CLEAN算法去除部件之间的相互干扰。结果在简易坦克部件级3维电磁散射模型基础上,利用电磁仿真数据、暗室数据以及MSTAR(moving and stationary target acquisition and recognition)干扰数据进行了单个散射部件检测实验,实验结果表明,本文方法可以很好地检测出实测图像中存在的目标散射部件,并且可以检测出缺失的散射部件。结论本文提出了基于匹配滤波器的散射部件检测方法,实验证明了该方法的有效性。     

Simulation and experimental study in determining injection molding process parameters for thin-shell plastic parts via design of experiments analysis

This paper deals with the application computer-aided engineering integrating with statistical technique to reduce warpage variation depended on injection molding process parameters during production of thin-shell plastic components. For this purpose, a number of Mold-Flow analyses are carried out by utilizing the combination of process parameters based on three level of L₁₈ orthogonal array table. In the meantime, apply the design of experiments (DOE) approach to determine an optimal parameter setting. In addition, a side-by-side comparison of two different approaches of simulation and experimental is provided. In this study, regression models that link the controlled parameters and the targeted outputs are developed, and the identified models can be utilized to predict the warpage at various injection molding conditions. The melt temperature and the packing pressure are found to be the most significant factors in both the simulation and the experimental for an injection molding process of thin-shell plastic parts.     

A sequential refinement approach for parameter optimization in continuous dynamic models

The determination of the optimal values for parameters in a continuous dynamic system model is normally a computationally intensive task. Two separate numerical processes are involved; namely, the mechanism for solving the ordinary differential equations that comprise the system model, and the function minimization procedure used to search for the optimal parameter values. Both these processes typically have embedded parameters which control their respective operations. In this paper a general approach is described for adjusting these parameters in a way which allows the two processes to function in a more integrated and hence more efficient way in solving the parameter optimization problem. A specific implementation of the approach is described and the results of an extensive set of numerical experiments are given, These results indicate that the approach can provide a significant advantage in reducing the computational effort.     

Automated process parameter resetting for injection moulding: a fuzzy-neuro approach

Optimal process parameter setting for injection moulding is difficult to achieve due to a large number of factors involved. Current practice in industry is to adjust the parameters based on the products' defects of test-run through trial and error. This process, however, requires enormous experience and is often time consuming. This paper reports an intelligent system employing fuzzy sets and neural networks which is able to predict the process parameter resetting automatically to achieve better product quality. The system is designed to be used in the test-run of injection moulding. Seven commonly encountered injection moulded product defects (short shot, flash, sink-mark, flow-mark, weld line, cracking, and warpage) and two key injection mould parameters (part flow length and flow thickness) are used as system input which are described using fuzzy terms. On the other hand, nine process parameter adjusters (pressure, speed, resin temperature, clamping force, holding time, mould temperature, injection holding pressure, back pressure, and cooling time) are the system output. A back-propagation neural network has been constructed and trained using a large number of {defects} {parameter adjusters} expert rules. The system is able to predict the exact amount to be adjusted for each parameter towards reducing or eliminating the observed defects. Testing in several real cases showed that the system produced satisfying results.     

Auction-based cooperation mechanism to parts scheduling for flexible job shop with inter-cells

This paper addresses cell part scheduling (CPS) problem. In this problem, parts may need to visit machines in different cells with consideration Inter-cell transportation time. The processing route of parts can be flexible. The objective is to minimize the overall process make-span. An integer nonlinear programming (INLP) model is formulated to determine the schedule scheme of all parts. An auction-based heuristic approach is proposed to solve it, which focuses on dealing with cooperation between different cells. In this approach, each cell can act as an auctioneer or a bidder. In an auction, it contains call for auction, bid construction, modify bids and winner announcement. A reference matrix is also applied in the auction to guarantee parts to finish as early as possible. Numerical experiments were conducted to test the auction-based approach. The results demonstrate the effectiveness, sensitivity and stability of the proposed auction-based approach, especially suitable for instances in large scale within a short calculating time.     

Minimizing staircase errors in the orthogonal layered manufacturing system

The factors that generally affect the slicing error in layered manufacturing (LM) processes are first analyzed, and issues pertaining to the current methods to deal with the slicing error are discussed in this paper. A method based on a recently developed and implemented orthogonal LM system to reduce the overall slicing error is presented. In this method, the flat region is separated from the stereolithography (STL) model and different processing methods are applied to the different areas in the part geometry. In addition, the mathematical model for calculating the slicing error is derived and an approach based on a genetic algorithm has been developed to optimize the build orientation in terms of minimizing the slicing error. Case studies are given to demonstrate the effectiveness and efficiency of the method. Note to Practitioner-The staircase effect has been the major concern for industry to widely adopt rapid prototyping technologies. It will not only worsen the surface quality but also create errors on the parts built. This paper introduces a novel approach to minimizing staircase errors based on a multidirectional deposition approach. A mathematical method combined with a generic algorithm is used to minimize the slicing errors. From the case study given, the approach has been proven to be effective in minimizing staircase errors and thus improving the rapid prototyping (RP) built part quality.     

A signal convolution method for estimation of controller parameter sensitivity functions for tuning of feedback control systems by an iterative process

Optimisation of controller parameters can be achieved through the use of parameter sensitivity functions in an iterative tuning process. Unlike some other methods for the generation of sensitivity functions, the approach described in this paper avoids the need for explicit a priori knowledge of the plant model structure or parameters, systematic adjustments of controller parameters being made entirely through the processing of signals obtained from tests on the closed-loop system. The methods, based on convolution, may be applied to the estimation of controller parameter sensitivity functions in linear closed-loop systems using simple test inputs, such as step signals. This approach differs from the Iterative Feedback Tuning algorithm in that it does not involve repeated experiments involving system outputs from one test being used as reference inputs in a second test. The signal convolution approach is illustrated through an example involving a simple two-input two-output liquid-level control system involving two coupled tanks.     

Disassembly sequence structure graphs: An optimal approach for multiple-target selective disassembly sequence planning

Modern green products must be easy to disassemble. Specific target components must be accessed and removed for repair, reuse, recycling, or remanufacturing. Prior studies describe various methods for removing selective targets from a product. However, solution quality, model complexity, and searching time have not been considered thoroughly. The goal of this study is to improve solution quality, minimize model complexity, and reduce searching time. To achieve the goal, this study introduces a new ‘disassembly sequence structure graph’ (DSSG) model for multiple-target selective disassembly sequence planning, an approach for creating DSSGs, and methods for searching DSSGs. The DSSG model contains a minimum set of parts that must be removed to remove selected targets, with an order and direction for removing each part. The approach uses expert rules to choose parts, part order, and part disassembly directions, based upon physical constraints. The searching methods use rules to remove all parts, in order, from the DSSG. The DSSG approach is an optimal approach. The approach creates a high quality minimum-size model, in minimum time. The approach finds high quality, practical, realistic, physically feasible solutions, in minimum time. The solutions are optimized for number of removed parts, part order, part disassembly directions, and reorientations. The solutions remove parts in practical order. The solutions remove parts in realistic directions. The solutions consider contact, motion, and fastener constraints. The study also presents eight new design rules. The study results can be used to improve the product design process, increase product life-cycle quality, and reduce product environmental impact.     

非直线排列剥叶元件的疲劳寿命分析

阐述了整杆式甘蔗收获机械非直线排列剥叶元件疲劳分析的总体思路．利用计算机仿真分析的方法分析了剥叶元件装夹参数及其注塑加工过程中产生的缺陷对元件寿命的影响，提出了不同工况剥叶元件疲劳分析的有限元计算模型．通过仿真分析，方便、快捷地得出剥叶元件疲劳寿命预估值，并用试验证明了其有效性．     

A hybrid method based on genetic algorithm and dynamic programming for solving a bi-objective cell formation problem considering alternative process routings and machine duplication

Cell formation is one of the first and most important steps in designing a cellular manufacturing system. It consist of grouping parts with similar design features or processing requirements into part families and associated machines into machine cells. In this study, a bi-objective cell formation problem considering alternative process routings and machine duplication is presented. Manufacturing factors such as part demands, processing times and machine capacities are incorporated in the problem. The objectives of the problem include the minimization of the total dissimilarity between the parts and the minimization of the total investment needed for the acquisition of machines. A normalized weighted sum method is applied to unify the objective functions. Due to the computational complexity of the problem, a hybrid method combining genetic algorithm and dynamic programming is developed to solve it. In the proposed method, the dynamic programming is implemented to evaluate the fitness value of chromosomes in the genetic algorithm. Computational experiments are conducted to examine the performance of the hybrid method. The computations showed promising results in terms of both solution quality and computation time.