scholarly journals A Guideline for Implementing a Robust Optimization of a Complex Multi-Stage Manufacturing Process

2021 ◽  
Vol 11 (4) ◽  
pp. 1418
Author(s):  
Francesco Bertocci ◽  
Andrea Grandoni ◽  
Monica Fidanza ◽  
Rossella Berni
Keyword(s):  
Medical Imaging ◽  
Manufacturing Process ◽  
Optimization Techniques ◽  
Acoustic Microscopy ◽  
Successful Implementation ◽  
High Definition ◽  
Destructive Testing ◽  
Multi Stage ◽  
Multidisciplinary Analysis ◽  
Six Sigma Approach

In the industrial production scenario, the goal of engineering is focused on the continuous improvement of the process performance by maximizing the effectiveness of the manufacturing and the quality of the products. In order to address these aims, the advanced robust process optimization techniques have been designed, implemented, and applied to the manufacturing process of ultrasound (US) probes for medical imaging. The suggested guideline plays a key role for improving a complex multi-stage manufacturing process; it consists of statistical methods applied for improving the product quality, and for achieving a higher productivity, jointly with engineering techniques oriented to problem solving. Starting from the Six Sigma approach, the high definition of the production process was analyzed through a risk analysis, and thus providing a successful implementation of the PDCA (plan-do-check-act) methodology. Therefore, the multidisciplinary analysis is carried out by applying statistical models and by detecting the latent failures by means of NDT (non-destructive testing), i.e., scanning acoustic microscopy (SAM). The presented approach, driven by the statistical analysis, allows the engineers to distinguish the potential weak points of the complex manufacturing, in order to implement the corrective actions. Furthermore, in this paper we illustrate this approach by considering a pilot study, e.g., a process of US probes for medical imaging, by detailing all the guideline steps.

scholarly journals Scanning Acoustic Microscopy (SAM): A Robust Method for Defect Detection during the Manufacturing Process of Ultrasound Probes for Medical Imaging

Sensors ◽  
2019 ◽  
Vol 19 (22) ◽  
pp. 4868 ◽  
Author(s):  
Francesco Bertocci ◽  
Andrea Grandoni ◽  
Tatjana Djuric-Rissner
Keyword(s):  
Medical Imaging ◽  
Defect Detection ◽  
Manufacturing Process ◽  
Ad Hoc ◽  
Acoustic Microscopy ◽  
Scanning Acoustic Microscopy ◽  
Destructive Testing ◽  
Multilayered Structures ◽  
Non Destructive ◽  
Ultrasound Probes

The main aim of this paper is to provide the feasibility of non-destructive testing (NDT) method, such as scanning acoustic microscopy (SAM), for damage detection in ultrasound (US) probes for medical imaging during the manufacturing process. In a highly competitive and demanding electronics and biomedical market, reliable non-destructive methods for quality control and failure analysis of electronic components within multi-layered structures are strongly required. Any robust non-destructive method should be capable of dealing with the complexity of miniaturized assemblies, such as the acoustic stack of ultrasonic transducers. In this work, the application of SAM in an industrial scenario was studied for 24 samples of a phased array probe, in order to investigate potential internal integrity, to detect damages, and to assess the compliance of high-demanding quality requirements. Delamination, non-homogeneous layers with micron-thickness, and entrapped air bubbles (blisters) in the bulk of US probe acoustic stacks were detected and studied. Analysis of 2D images and defects visualization by means of ultrasound-based NDT method were compared with electroacoustic characterization (also following as pulse-echo test) of the US probe through an ad-hoc measurement system. SAM becomes very useful for defect detection in multilayered structures with a thickness of some microns by assuring low time-consuming (a limit for other NDT techniques) and quantitative analyses based on measurements. The study provides a tangible contribution and identifies an advantage for manufacturers of ultrasound probes that are oriented toward continuous improvement devoted to the process capability, product quality, and in-process inspection.

Quantifying Design and Manufacturing Robustness Through Stochastic Optimization Techniques

1996 ◽  
Author(s):  
David Kazmer ◽  
Philip Barkan ◽  
Kosuke Ishii
Keyword(s):  
Manufacturing Process ◽  
Process Variation ◽  
Optimization Techniques ◽  
Design Stage ◽  
Tool Geometry ◽  
Detailed Design ◽  
Process Dynamics ◽  
Molded Parts ◽  
Industry Practice ◽  
End Use

Abstract Critical design decisions are often made during the detailed design stage assuming known material and process behavior. However, in net shape manufacturing processes such as stamping, injection molding, and metals casting, the final part properties depend upon the specific tool geometry, material properties, and process dynamics encountered during production. As such, the end-use performance can not be accurately known in the detailed design stage. Moreover, slight random variations during manufacture can inadvertently result in inferior or unacceptable product performance and reduced production yields. These characteristics make it difficult for the designer to select the tooling, material, and processing details which will deliver the desired functional properties, let alone achieve a robust design which is tolerant to process variation. This paper describes a methodology for assessing the design/manufacturing robustness of candidate designs at the detailed design stage. In the design evaluation, the fundamental sources of variation are explicitly modeled and the effects conveyed through the manufacturing process to predict the distribution of end-use part properties. This is accomplished by utilizing optimization of manufacturing process variables within Monte Carlo simulation of stochastic process variation, which effectively parallels the industry practice of tuning and optimizing the process once the tool reaches the production floor. The resulting estimates can be used to evaluate the robustness of the candidate design relative to the product requirements and provide guidance for design and process modifications before tool steel is cut, as demonstrated by the application of the methodology for dimensional control of injection molded parts.

scholarly journals Effect of GAN-based image standardization on MR knee bone-tissue classification performance

10.29007/d18s ◽  
2020 ◽  
Author(s):  
Vincent Jaouen ◽  
Guillaume Dardenne ◽  
Florent Tixier ◽  
Éric Stindel ◽  
Dimitris Visvikis
Keyword(s):  
Machine Learning ◽  
Medical Imaging ◽  
Bone Tissue ◽  
Pulse Sequences ◽  
Image Synthesis ◽  
Magnetic Resonance Images ◽  
Machine Learning Algorithms ◽  
Pool Data ◽  
Tissue Classification ◽  
High Definition

Due to their sensitivity to acquisition parameters, medical images such as magnetic resonance images (MRI), Positron Emission tomography (PET) or Computed Tomography (CT) images often suffer from a kind of variability unrelated to diagnostic power, often known as the center effect (CE). This is especially true in MRI, where units are arbitrary and image values can strongly depend on subtle variations in the pulse sequences [1]. Due to the CE it is particularly difficult in various medical imaging applications to 1) pool data coming from several centers or 2) train machine learning algorithms requiring large homogeneous training sets. There is therefore a clear need for image standardization techniques aiming at reducing this effect.Considerable improvements in image synthesis have been achieved over the recent years using (deep) machine learning. Models based on generative adversarial neural networks (GANs) now enable the generation of high definition images capable of fooling the human eye [2]. These methods are being increasingly used in medical imaging for various cross-modality (image-to-image) applications such as MR to CT synthesis [3]. However, they have been seldom used for the purpose of image standardization, i.e. for reducing the CE [4].In this work, we explore the potential advantage of embedding a standardization step using GANs prior to knee bone tissue classification in MRI. We consider image standardization as a within-domain image synthesis problem, where our objective is to learn a mapping between a domain D constituted of heterogeneous images and a reference domain R showing one or several images of desired image characteristics.Preliminary results suggest a beneficial impact of such a standardization step on segmentation performance.

Standard Deviation Method Based PSO

2016 ◽  
Vol 7 (2) ◽  
pp. 15-35
Author(s):  
Arindam Majumder ◽  
Abhishek Majumder
Keyword(s):  
Process Parameters ◽  
Performance Index ◽  
Manufacturing Process ◽  
Pso Algorithm ◽  
Optimization Techniques ◽  
Advanced Manufacturing ◽  
Optimization Of Process Parameters ◽  
Optimal Value ◽  
Single Attribute ◽  
Deviation Method

Nowadays, optimization of process parameters in manufacturing process deals with a number of objectives. However, the optimization of such process becomes more complex if selected attributes are conflicting in nature. Therefore, to overcome this problem in this study a SDM based PSO algorithm is proposed for optimizing the manufacturing process having multi attribute. In this proposed approach the SDM is used to convert multi attributes into single attribute, named as multi performance index, while the optimal value of this multi performance index is predicted by PSO. Finally, three instances related to optimization of advanced manufacturing process parameters are solved by the proposed approach and are compared with the results of the other established optimization techniques such as Desirability based RSM, SDM-GA and SDM-CACO. From the comparison it has been revealed that the proposed approach performs better as compare to the existing approaches.

Flow Characteristics of a Novel Centrifugal Compressor Design

2016 ◽  
Author(s):  
Shashank Mishra ◽  
Shaaban Abdallah ◽  
Mark Turner
Keyword(s):  
Centrifugal Compressor ◽  
Pressure Ratio ◽  
Flow Characteristics ◽  
Axial Compressor ◽  
Low Pressure ◽  
Flow Path ◽  
Optimization Techniques ◽  
Single Stage ◽  
Multi Stage ◽  
Compressor Design

Multistage axial compressor has an advantage of lower stage loading as compared to a single stage. Several stages with low pressure ratio are linked together which allows for multiplication of pressure to generate high pressure ratio in an axial compressor. Since each stage has low pressure ratio they operate at a higher efficiency and the efficiency of multi-stage axial compressor as a whole is very high. Although, single stage centrifugal compressor has higher pressure ratio compared with an axial compressor but multistage centrifugal compressors are not as efficient because the flow has to be turned from radial at outlet to axial at inlet for each stage. The present study explores the advantages of extending the axial compressor efficient flow path that consist of rotor stator stages to the centrifugal compressor stage. In this invention, two rotating rows of blades are mounted on the same impeller disk, separated by a stator blade row attached to the casing. A certain amount of turning can be achieved through a single stage centrifugal compressor before flow starts separating, thus dividing it into multiple stages would be advantageous as it would allow for more flow turning. Also the individual stage now operate with low pressure ratio and high efficiency resulting into an overall increase in pressure ratio and efficiency. The baseline is derived from the NASA low speed centrifugal compressor design which is a 55 degree backward swept impeller. Flow characteristics of the novel multistage design are compared with a single stage centrifugal compressor. The flow path of the baseline and multi-stage compressor are created using 3DBGB tool and DAKOTA is used to optimize the performance of baseline as well novel design. The optimization techniques used are Genetic algorithm followed by Numerical Gradient method. The optimization resulted into improvements in incidence and geometry which significantly improved the performance over baseline compressor design. The multistage compressor is more efficient with a higher pressure ratio compared with the base line design for the same work input and initial conditions.

An Agent Based Optimization Approach to Manufacturing Process Planning

2001 ◽  
Author(s):  
Saurabh Deshpande ◽  
Jonathan Cagan
Keyword(s):  
Stochastic Optimization ◽  
Process Planning ◽  
Manufacturing Process ◽  
Optimization Problems ◽  
Search Space ◽  
Optimization Techniques ◽  
Process Models ◽  
Optimization Approach ◽  
Agent Based ◽  
Manufacturing Process Planning

Abstract Many optimization problems, such as manufacturing process planning optimization, are difficult problems due to the large number of potential configurations (process sequences) and associated (process) parameters. In addition, the search space is highly discontinuous and multi-modal. This paper introduces an agent based optimization algorithm that combines stochastic optimization techniques with knowledge based search. The motivation is that such a merging takes advantage of the benefits of stochastic optimization and accelerates the search process using domain knowledge. The result of applying this algorithm to computerized manufacturing process models is presented.

Genetic Algorithm to Solve Multi-Period, Multi-Product, Bi-Echelon Supply Chain Network Design Problem

2009 ◽  
Vol 2 (4) ◽  
pp. 24-42 ◽  
Author(s):  
R. Dhanalakshmi ◽  
P. Parthiban ◽  
K. Ganesh ◽  
T. Arunkumar
Keyword(s):  
Supply Chain ◽  
Supply Chains ◽  
Raw Materials ◽  
Optimization Techniques ◽  
Network Design Problem ◽  
Production Plant ◽  
Two Stage ◽  
Cost Structures ◽  
Multi Stage ◽  
Product Costs

In many multi-stage manufacturing supply chains, transportation related costs are a significant portion of final product costs. It is often crucial for successful decision making approaches in multi-stage manufacturing supply chains to explicitly account for non-linear transportation costs. In this article, we have explored this problem by considering a Two-Stage Production-Transportation (TSPT). A two-stage supply chain that faces a deterministic stream of external demands for a single product is considered. A finite supply of raw materials, and finite production at stage one has been assumed. Items are manufactured at stage one and transported to stage two, where the storage capacity of the warehouses is limited. Packaging is completed at stage two (that is, value is added to each item, but no new items are created), and the finished goods inventories are stored which is used to meet the final demand of customers. During each period, the optimized production levels in stage one, as well as transportation levels between stage one and stage two and routing structure from the production plant to warehouses and then to customers, must be determined. The authors consider “different cost structures,” for both manufacturing and transportation. This TSPT model with capacity constraint at both stages is optimized using Genetic Algorithms (GA) and the results obtained are compared with the results of other optimization techniques of complete enumeration, LINDO, and CPLEX.

A Selective Multiclass Support Vector Machine Ensemble Classifier for Engineering Surface Classification Using High Definition Metrology

2015 ◽  
Vol 137 (1) ◽  
Author(s):  
Shichang Du ◽  
Changping Liu ◽  
Lifeng Xi
Keyword(s):  
Support Vector Machine ◽  
Wavelet Transform ◽  
Manufacturing Process ◽  
Classification Accuracy ◽  
Support Vector ◽  
Ensemble Classifiers ◽  
Complex Wavelet Transform ◽  
High Definition ◽  
Workpiece Surface ◽  
Surface Patterns

The surface appearance is sensitive to change in the manufacturing process and is one of the most important product quality characteristics. The classification of workpiece surface patterns is critical for quality control, because it can provide feedback on the manufacturing process. In this study, a novel classification approach for engineering surfaces is proposed by combining dual-tree complex wavelet transform (DT-CWT) and selective ensemble classifiers called modified matching pursuit optimization with multiclass support vector machines ensemble (MPO-SVME), which adopts support vector machine (SVM) as basic classifiers. The dual-tree wavelet transform is used to decompose three-dimensional (3D) workpiece surfaces, and the features of workpiece surface are extracted from wavelet sub-bands of each level. Then MPO-SVME is developed to classify different workpiece surfaces based on the extracted features and the performance of the proposed approach is evaluated by computing its classification accuracy. The performance of MPO-SVME is validated in case study, and the results demonstrate that MPO-SVME can increase the classification accuracy with only a handful of selected classifiers.

Sign in / Sign up

Export Citation Format

Share Document