1,720,988 research outputs found
Binary Gaussian Process classification of quality in the production of aluminum alloys foams with regular open cells
Full text linkAluminum alloys foams with homogeneous and regular open cells have been frequently proposed and used as support structures for catalytic applications. In this kind of application, the quality of produced metal foam assumes primary importance. This paper presents an application of a classifier algorithm to predict quality in the manufacturing process of aluminum alloy foams with homogeneous and regular open cells. A data analysis methodology of experimental data, which is based on Binary Gaussian Process Classification, is presented. The proposed method is a Bayesian classification method, which gets away from any assumptions about the relationship between process inputs (the geometric design parameters of the regular unit cells) and process output (probability to obtain defective foam). We demonstrate that the proposed methodology can provide an effective tool to derive a model for the prediction of quality. An investment casting process, via 3D printing of wax patterns, is considered throughout the paper. Despite this specific case study, the methodology can be exploited in different processes in which the assumptions of traditional statistical approaches could not be easily verified, e.g., additive manufacturing
Logistic Regression and Response Surface Design for Statistical Modeling of Investment Casting Process in Metal Foam Production
Full text linkA metal foam represents a promising material since it keeps the high mechanical properties of the metal while reducing the weight up to 90%. Among several manufacturing processes, the investment casting is a foundry process flexible enough to be suitable both for stochastic and for regular foams. This paper presents an experimental determination of the manufacturing process of metal regular foams by investment casting. The goal is to derive experimentally an actual formability map. The use of logistic regression and response surface design is proposed as an effective tool for determining a statistical model of the metal foam casting process
Adaptive Resonance Theory-based neural algorithms for manufacturing process quality control
No full textThe demand for quality products in industry is continuously increasing. To produce products with consistent quality, manufacturing systems need to be closely monitored for any unnatural deviation in the state of the process. Neural networks
are potential tools that can be used to improve the analysis of manufacturing processes. Indeed, neural networks have been applied successfully for detecting groups of predictable unnatural patterns in the quality measurements of manufacturing processes. The feasibility of using Adaptive Resonance Theory
(ART) to implement an automatic on-line quality control method is investigated.
The aim is to analyse the performance of the ART neural network as a means for recognizing any structural change in the state of the process when predictable unnatural patterns are not available for training. To reach such a goal, a simplified ART neural algorithm is discussed then studied by means of extensive Monte
Carlo simulation. Comparisons between the performances of the proposed neural approach and those of well-known SPC charts are also presented. Results prove that the proposed neural network is a useful alternative to the existing control schemes
Detecting Changes in Autoregressive Processes with a Recurrent Neural Network for Manufacturing Quality Monitoring
No full textThe traditional use of control charts assumes the independence of data. It is widely recognized that many processes are autocorrelated thus violating the main assumption of independence. As a result, there is a need for a broader approach to quality monitoring when data are time-dependent or autocorrelated. The aim of this work is to present a new procedure for manufacturing process quality control in the case of serially correlated data. In particular, a recurrent neural network is introduced for quality control problem. Performance comparisons between the neural-based algorithm and control charts are also presented in the paper in order to validate the proposed approach. The simulation results indicate that the neural-based procedure is quite effective as it achieves improved performance over control charts
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Manufacturing quality control by means of a Fuzzy ART network trained on natural process data
No full textIn order to produce products with constant quality, manufacturing systems need to be monitored for any unnatural deviations in
the state of the process. Control charts have an important role in solving quality control problems; nevertheless, their effectiveness is strictly dependent on statistical assumptions that in real industrial applications are frequently violated. In contrast, neural networks can elaborate huge amounts of noisy data in real time, requiring no hypothesis on statistical distribution of monitored
measurements. This important feature makes neural networks potential tools that can be used to improve data analysis in
manufacturing quality control applications. In this paper, a neural network system, which is based on an unsupervised training
phase, is presented for quality control. In particular, the adaptive resonance theory (ART) has been investigated in order to
implement a model-free quality control system, which can be exploited for recognising changes in the state of a manufacturing
process. The aim of this research is to analyse the performances of ART neural network under the assumption that predictable
unnatural patterns are not available. To such aim, a simplified Fuzzy ART neural algorithm is firstly discussed, and then studied by means of extensive Monte Carlo simulation
- …
