Assessment of variance & distribution in data for effective use of statistical methods for product quality prediction

2018 ◽  
Vol 66 (4) ◽  
pp. 344-355 ◽  
Author(s):  
Iris Weiß ◽  
Birgit Vogel-Heuser
Keyword(s):  
Data Mining ◽  
Product Quality ◽  
Statistical Methods ◽  
Analysis Of Variance ◽  
Production System ◽  
Production Systems ◽  
High Potential ◽  
Quality Prediction ◽  
Automated Production ◽  
Effective Use

AbstractData mining in automated production systems provide high potential to increase the Overall Equipment Effectiveness. Nevertheless, data of such machines/plants include specific characteristics regarding the variance and distribution of the dataset. For modelling product quality prediction, these characteristics have to be analysed to interpret the results correctly. Therefore, an approach for the analysis of variance and distribution of datasets is proposed. The evaluation of this approach validates the developed guidelines, which identify the reasons for inconsistent prediction results based on two different datasets of the same production system.

Intelligent Processes in Automated Production Involving Industry 4.0 Technologies and Artificial Intelligence

2021 ◽  
pp. 634-655
Author(s):  
Alessandro Massaro ◽  
Nicola Contuzzi ◽  
Angelo Galiano
Keyword(s):  
Artificial Intelligence ◽  
Data Mining ◽  
Process Simulation ◽  
Industry 4.0 ◽  
Process Reengineering ◽  
Quality Prediction ◽  
Automated Production ◽  
Industry Research ◽  
Processing Techniques ◽  
Technology Upgrading

The chapter presents different case studies involving technology upgrading involving Industry 4.0 technologies and artificial intelligence. The work analyzes four cases of study of industry projects related to manufacturing process of kitchen, tank production, pasta production, and electronic welding check. All the cases of study concern the analysis of engineered processes and the inline implementation of image vision techniques. The chapter discusses other topics involved in the production process such as augmented reality, quality prediction and predictive maintenance. The classic methodologies to map production processes are matched with innovative technologies of image segmentation and data mining predicting defects, machine failures, and product quality. The goal of the chapter is to prove how the combination of image processing techniques, data mining approaches, process simulation, chart process modeling, and process reengineering can constitute a scientific research project in industry research.

Application of Enterprise Modelling (EM) Principles to Improving the Performance of a Semi-Automated Production System

2009 ◽  
Vol 62-64 ◽  
pp. 293-302 ◽  
Author(s):  
J.O. Ajaefobi ◽  
R.H. Weston
Keyword(s):  
Production System ◽  
Dynamic Models ◽  
Production Systems ◽  
Discrete Event ◽  
Business Environment ◽  
Automated Production ◽  
Manufacturing Enterprises ◽  
Event Simulation ◽  
Enterprise Modelling ◽  
And Performance

To cope with high levels of complexity, competition and change requirements, manufacturing enterprises (MEs) need to continuously improve their process and resource system performances. Enterprise Modelling (EM) is considered a prerequisite for enterprise integration and performance improvement because it can be used to capture relatively enduring knowledge about any specific business environment in which production systems will be deployed. With this prerequisite in mind, EM principles were deployed to capture and develop ‘static’ models of an SME. This provided detailed descriptions of enterprise production operations and their precedence relationships. A discrete event simulation tool was then used to develop time dependent ‘dynamic’ models of selected process segments of the specific case Enterprise Model. This allowed the computer execution of alternative production system designs to be assessed under SME specific changing scenarios and enabled suggestions for potential improvements to be made.

Overall equipment effectiveness (OEE) evaluation for an automated ice cream production line

2019 ◽  
Vol 69 (5) ◽  
pp. 1009-1032 ◽  
Author(s):  
Panagiotis H. Tsarouhas
Keyword(s):  
Operations Management ◽  
Production System ◽  
Production Line ◽  
Production Systems ◽  
Ice Cream ◽  
Management Tools ◽  
Content Type ◽  
Pareto Analysis ◽  
Automated Production ◽  
Working Day

Purpose As overall equipment effectiveness (OEE) is a metric to estimate equipment effectiveness of production systems, the purpose of this paper is to identify strategic management tools and techniques based on OEE assessment of the ice cream production line. Design/methodology/approach This paper presents the collection and the analysis of data for ice cream production under real working conditions. The data cover a period of eight months. A framework process to improve the OEE of an automated production system was proposed. Six major stoppage losses, i.e. equipment failure, setup and adjustment, idling and minor stoppage, reduced speed, defects in the process, and reduced yield, were examined with the help of Pareto analysis. In addition, the actual availability (A), performance efficiency (PΕ) and quality rate (QR) measures, together with the complete OEE for each working day, week and month of the production line were shown. Findings The main goal of the study is to identify major stoppage losses, in order to examine and improve the overall equipment efficiency (OEE) of the ice cream production line through the application of an adequate management, i.e. TPM approach. Based on the obtained results, maintenance management strategy and production planning have been suggested to improve their maintenance procedures and the productivity as well. Originality/value The proposed method can be applied to each automated production system. The main benefits of this method are the improvement of productivity, quality enhancement of products, the reduction of sudden breakdowns and the cost of maintenance. Moreover, the analysis provides a useful perspective and helps managers/engineers make better decisions on the operations management of the line, and suggestions for improvement were proposed and will be implemented accordingly.

scholarly journals Product Quality Monitoring in Hydraulic Presses Using a Minimal Sample of Sensor and Actuator Data

2021 ◽  
Vol 21 (2) ◽  
pp. 1-23
Author(s):  
Iris Weiss ◽  
Birgit Vogel-Heuser ◽  
Emanuel Trunzer ◽  
Simon Kruppa
Keyword(s):  
Product Quality ◽  
Production Systems ◽  
True Positive Rate ◽  
Quality Parameters ◽  
Quality Monitoring ◽  
Automated Production ◽  
Minimal Sample ◽  
Positive Rate ◽  
Dynamic Time ◽  
Data Driven Modeling

Machine learning and artificial intelligence provide methods and algorithms to take advantage of sensor and actuator data in automated production systems. Product quality monitoring is one of the promising applications available for data-driven modeling, particularly in cases where the quality parameters cannot be measured with reasonable effort. This is the case for defects such as cracks in workpieces of hydraulic metal powder presses. However, the variety of shapes produced at a powder press requires training of individual models based on a minimal sample size of unlabeled data to adapt to changing settings. Therefore, this article proposes an unsupervised product quality monitoring approach based on dynamic time warping and non-linear regression to detect anomalies in unlabeled sensor and actuator data. A preprocessing step that isolates only the relevant intervals of the process is further introduced, facilitating efficient product quality monitoring. The evaluation on an industrial dataset with 37 samples, generated in test runs, shows a true-positive rate for detected product quality defects of 100% while preserving an acceptable accuracy. Moreover, the approach achieves the output within less than 10 seconds, assuring that the result is available before the next workpiece is processed. In this way, efficient product quality management is possible, reducing time- and cost-intensive quality inspections.

scholarly journals Quality Evaluation Based on Multivariate Statistical Methods

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Shen Yin ◽  
Xiangping Zhu ◽  
Hamid Reza Karimi
Keyword(s):  
Product Quality ◽  
Least Squares ◽  
Partial Least Squares ◽  
Statistical Methods ◽  
Partial Least Squares Regression ◽  
Prediction Models ◽  
Quality Prediction ◽  
Least Squares Regression ◽  
Multivariate Statistical Methods ◽  
Multivariate Statistical

Quality prediction models are constructed based on multivariate statistical methods, including ordinary least squares regression (OLSR), principal component regression (PCR), partial least squares regression (PLSR), and modified partial least squares regression (MPLSR). The prediction model constructed by MPLSR achieves superior results, compared with the other three methods from both aspects of fitting efficiency and prediction ability. Based on it, further research is dedicated to selecting key variables to directly predict the product quality with satisfactory performance. The prediction models presented are more efficient than tradition ones and can be useful to support human experts in the evaluation and classification of the product quality. The effectiveness of the quality prediction models is finally illustrated and verified based on the practical data set of the red wine.

Intelligent Processes in Automated Production Involving Industry 4.0 Technologies and Artificial Intelligence

2020 ◽  
pp. 97-122 ◽  
Author(s):  
Alessandro Massaro ◽  
Nicola Contuzzi ◽  
Angelo Galiano
Keyword(s):  
Artificial Intelligence ◽  
Data Mining ◽  
Process Simulation ◽  
Industry 4.0 ◽  
Process Reengineering ◽  
Quality Prediction ◽  
Automated Production ◽  
Industry Research ◽  
Processing Techniques ◽  
Technology Upgrading

The chapter presents different case studies involving technology upgrading involving Industry 4.0 technologies and artificial intelligence. The work analyzes four cases of study of industry projects related to manufacturing process of kitchen, tank production, pasta production, and electronic welding check. All the cases of study concern the analysis of engineered processes and the inline implementation of image vision techniques. The chapter discusses other topics involved in the production process such as augmented reality, quality prediction and predictive maintenance. The classic methodologies to map production processes are matched with innovative technologies of image segmentation and data mining predicting defects, machine failures, and product quality. The goal of the chapter is to prove how the combination of image processing techniques, data mining approaches, process simulation, chart process modeling, and process reengineering can constitute a scientific research project in industry research.

scholarly journals Soil Bacterial Community Diversity and Composition as Affected by Tillage Intensity Treatments in Corn-Soybean Production Systems

2021 ◽  
Vol 12 (1) ◽  
pp. 157-172
Author(s):  
Shankar G. Shanmugam ◽  
Normie W. Buehring ◽  
Jon D. Prevost ◽  
William L. Kingery
Keyword(s):  
Microbial Community ◽  
Bacterial Community ◽  
Community Composition ◽  
Production System ◽  
Soil Microbial Community ◽  
Production Systems ◽  
Bacterial Community Composition ◽  
Soybean Production ◽  
Soil Microbial ◽  
Soil Bacterial

Our understanding on the effects of tillage intensity on the soil microbial community structure and composition in crop production systems are limited. This study evaluated the soil microbial community composition and diversity under different tillage management systems in an effort to identify management practices that effectively support sustainable agriculture. We report results from a three-year study to determine the effects on changes in soil microbial diversity and composition from four tillage intensity treatments and two residue management treatments in a corn-soybean production system using Illumina high-throughput sequencing of 16S rRNA genes. Soil samples were collected from tillage treatments at locations in the Southern Coastal Plain (Verona, Mississippi, USA) and Southern Mississippi River Alluvium (Stoneville, Mississippi, USA) for soil analysis and bacterial community characterization. Our results indicated that different tillage intensity treatments differentially changed the relative abundances of bacterial phyla. The Mantel test of correlations indicated that differences among bacterial community composition were significantly influenced by tillage regime (rM = 0.39, p ≤ 0.0001). Simpson’s reciprocal diversity index indicated greater bacterial diversity with reduction in tillage intensity for each year and study location. For both study sites, differences in tillage intensity had significant influence on the abundance of Proteobacteria. The shift in the soil bacterial community composition under different tillage systems was strongly correlated to changes in labile carbon pool in the system and how it affected the microbial metabolism. This study indicates that soil management through tillage intensity regime had a profound influence on diversity and composition of soil bacterial communities in a corn-soybean production system.

scholarly journals Production rescheduling through product quality prediction

2021 ◽  
Vol 54 ◽  
pp. 142-147
Author(s):  
Maik Frye ◽  
Dávid Gyulai ◽  
Júlia Bergmann ◽  
Robert H. Schmitt
Keyword(s):  
Product Quality ◽  
Quality Prediction
Sign in / Sign up

Export Citation Format

Share Document