Research

Jump to: Other

14 pages, 7019 KiB

Open AccessArticle

Paperboard Coating Detection Based on Full-Stokes Imaging Polarimetry

by Javier Brugés Martelo, Jan Lundgren and Mattias Andersson

Sensors 2021, 21(1), 208; https://doi.org/10.3390/s21010208 - 31 Dec 2020

Cited by 2 | Viewed by 2536

The manufacturing of high-quality extruded low-density polyethylene (PE) paperboard intended for the food packaging industry relies on manual, intrusive, and destructive off-line inspection by the process operators to assess the overall quality and functionality of the product. Defects such as cracks, pinholes, and [...] Read more.

The manufacturing of high-quality extruded low-density polyethylene (PE) paperboard intended for the food packaging industry relies on manual, intrusive, and destructive off-line inspection by the process operators to assess the overall quality and functionality of the product. Defects such as cracks, pinholes, and local thickness variations in the coating can occur at any location in the reel, affecting the sealable property of the product. To detect these defects locally, imaging systems must discriminate between the substrate and the coating. We propose an active full-Stokes imaging polarimetry for the classification of the PE-coated paperboard and its substrate (before applying the PE coating) from industrially manufactured samples. The optical system is based on vertically polarized illumination and a novel full-Stokes imaging polarimetry camera system. From the various parameters obtained by polarimetry measurements, we propose implementing feature selection based on the distance correlation statistical method and, subsequently, the implementation of a support vector machine algorithm that uses a nonlinear Gaussian kernel function. Our implementation achieves

99.74 %

classification accuracy. An imaging polarimetry system with high spatial resolution and pixel-wise metrological characteristics to provide polarization information, capable of material classification, can be used for in-process control of manufacturing coated paperboard. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

21 pages, 2747 KiB

Open AccessArticle

An Information Theory Inspired Real-Time Self-Adaptive Scheduling for Production-Logistics Resources: Framework, Principle, and Implementation

by Wenchao Yang, Wenfeng Li, Yulian Cao, Yun Luo and Lijun He

Sensors 2020, 20(24), 7007; https://doi.org/10.3390/s20247007 - 08 Dec 2020

Cited by 8 | Viewed by 2043

Abstract

The development of industrial-enabling technology, such as the industrial Internet of Things and physical network system, makes it possible to use real-time information in production-logistics scheduling. Real-time information in an intelligent factory is random, such as the arrival of customers’ jobs, and fuzzy, [...] Read more.

The development of industrial-enabling technology, such as the industrial Internet of Things and physical network system, makes it possible to use real-time information in production-logistics scheduling. Real-time information in an intelligent factory is random, such as the arrival of customers’ jobs, and fuzzy, such as the processing time of Production-Logistics Resources. Besides, the coordination of production and logistic resources in a flexible workshop is also a hot issue. The availability of this information will enhance the quality of making scheduling decisions. However, when and how to use this information to realize the adaptive collaboration of Production-Logistics Resources are vital issues. Therefore, this paper studies the above problems by establishing a real-time reaction scheduling framework of Production-Logistics Resources dynamic cooperation. Firstly, a real-time task triggering strategy to maximize information utilization is proposed to explore when to use real-time information. Secondly, a collaborative method for Production-Logistics Resources is studied to explore how to use real-time information. Thirdly, a real-time self-adaptive scheduling algorithm based on information entropy is utilized to obtain a stable and feasible solution. Finally, the effectiveness and advancement of the proposed method are verified by a practical case. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

23 pages, 6356 KiB

Open AccessArticle

The Use of Neural Networks and Genetic Algorithms to Control Low Rigidity Shafts Machining

by Antoni Świć, Dariusz Wołos, Arkadiusz Gola and Grzegorz Kłosowski

Sensors 2020, 20(17), 4683; https://doi.org/10.3390/s20174683 - 19 Aug 2020

Cited by 14 | Viewed by 2720

Abstract

The article presents an original machine-learning-based automated approach for controlling the process of machining of low-rigidity shafts using artificial intelligence methods. Three models of hybrid controllers based on different types of neural networks and genetic algorithms were developed. In this study, an objective [...] Read more.

The article presents an original machine-learning-based automated approach for controlling the process of machining of low-rigidity shafts using artificial intelligence methods. Three models of hybrid controllers based on different types of neural networks and genetic algorithms were developed. In this study, an objective function optimized by a genetic algorithm was replaced with a neural network trained on real-life data. The task of the genetic algorithm is to select the optimal values of the input parameters of a neural network to ensure minimum deviation. Both input vector values and the neural network’s output values are real numbers, which means the problem under consideration is regressive. The performance of three types of neural networks was analyzed: a classic multilayer perceptron network, a nonlinear autoregressive network with exogenous input (NARX) prediction network, and a deep recurrent long short-term memory (LSTM) network. Algorithmic machine learning methods were used to achieve a high level of automation of the control process. By training the network on data from real measurements, we were able to control the reliability of the turning process, taking into account many factors that are usually overlooked during mathematical modelling. Positive results of the experiments confirm the effectiveness of the proposed method for controlling low-rigidity shaft turning. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

16 pages, 5550 KiB

Open AccessArticle

Development of a High Precision Telescopic Instrument Based on Simultaneous Laser Multilateration for Machine Tool Volumetric Verification

by Juan José Aguilar, Raquel Acero, Francisco Javier Brosed and Jorge Santolaria

Sensors 2020, 20(13), 3798; https://doi.org/10.3390/s20133798 - 07 Jul 2020

Cited by 8 | Viewed by 2735

Abstract

This paper presents the design of a high precision telescopic system consisting in three lines, with measuring principle based on simultaneous laser multilateration. The system offers the high precision of the interferometer systems and allows the autonomous tracking of a sphere joined to [...] Read more.

This paper presents the design of a high precision telescopic system consisting in three lines, with measuring principle based on simultaneous laser multilateration. The system offers the high precision of the interferometer systems and allows the autonomous tracking of a sphere joined to the spindle nose of the machine tool by simultaneous contact of all the lines. The main advantage of the system is that it allows data capture to be carried out in a single cycle thanks to simultaneous operation with at least three telescopic arms using a novel multipoint kinematic coupling. This results in a significant reduction of the time taken for data capture and improves measurement accuracy due to avoiding the effect of temperature variations between cycles and machine tool repeatability. The work explains the working principle of the system, its main components, and the design parameters considered for the development of the system. The system is simple to operate, compact, agile, and suitable for the verification of small- or medium-sized machine tools with linear and/or rotary axes. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

22 pages, 4847 KiB

Open AccessArticle

Intelligent Industrial Cleaning: A Multi-Sensor Approach Utilising Machine Learning-Based Regression

by Alessandro Simeone, Elliot Woolley, Josep Escrig and Nicholas James Watson

Sensors 2020, 20(13), 3642; https://doi.org/10.3390/s20133642 - 29 Jun 2020

Cited by 15 | Viewed by 4014

Abstract

Effectively cleaning equipment is essential for the safe production of food but requires a significant amount of time and resources such as water, energy, and chemicals. To optimize the cleaning of food production equipment, there is the need for innovative technologies to monitor [...] Read more.

Effectively cleaning equipment is essential for the safe production of food but requires a significant amount of time and resources such as water, energy, and chemicals. To optimize the cleaning of food production equipment, there is the need for innovative technologies to monitor the removal of fouling from equipment surfaces. In this work, optical and ultrasonic sensors are used to monitor the fouling removal of food materials with different physicochemical properties from a benchtop rig. Tailored signal and image processing procedures are developed to monitor the cleaning process, and a neural network regression model is developed to predict the amount of fouling remaining on the surface. The results show that the three dissimilar food fouling materials investigated were removed from the test section via different cleaning mechanisms, and the neural network models were able to predict the area and volume of fouling present during cleaning with accuracies as high as 98% and 97%, respectively. This work demonstrates that sensors and machine learning methods can be effectively combined to monitor cleaning processes. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

13 pages, 3555 KiB

Open AccessArticle

Performance Evaluation and Compensation Method of Trigger Probes in Measurement Based on the Abbé Principle

by Guoying Ren, Xinghua Qu and Xiangjun Chen

Sensors 2020, 20(8), 2413; https://doi.org/10.3390/s20082413 - 23 Apr 2020

Cited by 4 | Viewed by 3838

Abstract

Trigger probes are widely used in precision manufacturing industries such as coordinate measuring machines (CMM) and high-end computer numerical control(CNC) machine tools for quality control. Their performance and accuracy often determine the measurement results and the quality of the product manufacturing. However, because [...] Read more.

Trigger probes are widely used in precision manufacturing industries such as coordinate measuring machines (CMM) and high-end computer numerical control(CNC) machine tools for quality control. Their performance and accuracy often determine the measurement results and the quality of the product manufacturing. However, because there is no accurate measurement of the trigger force in different directions of the probe, and no special measuring device to calibrate the characteristic parameters of the probe in traditional measurement methods, it is impossible to exactly compensate for the measurement error caused by the trigger force of the probe in the measurement process. The accuracy of the measurement of the equipment can be improved by abiding by the Abbé principle. Thus, in order to better evaluate the performance parameters of the probe and realize the accurate compensation for its errors, this paper presents a method which can directly measure the performance parameters of the trigger probe based on the Abbé measurement principle, expounds the measurement principle, the establishment of the mathematical model, and the calibration system, and finishes with an experimental verification and measurement uncertainty analysis. The experimental results show that this method can obtain the exact calibration errors of the performance parameters of the trigger probe intuitively, realize the compensation for the errors of the probe in the measurement process, and effectively improve the measurement accuracy. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

17 pages, 8303 KiB

Open AccessArticle

Real-Time Weld Quality Prediction Using a Laser Vision Sensor in a Lap Fillet Joint during Gas Metal Arc Welding

by Kidong Lee, Insung Hwang, Young-Min Kim, Huijun Lee, Munjin Kang and Jiyoung Yu

Sensors 2020, 20(6), 1625; https://doi.org/10.3390/s20061625 - 14 Mar 2020

Cited by 26 | Viewed by 5246

Abstract

Nondestructive test (NDT) technology is required in the gas metal arc (GMA) welding process to secure weld robustness and to monitor the welding quality in real-time. In this study, a laser vision sensor (LVS) is designed and fabricated, and an image processing algorithm [...] Read more.

Nondestructive test (NDT) technology is required in the gas metal arc (GMA) welding process to secure weld robustness and to monitor the welding quality in real-time. In this study, a laser vision sensor (LVS) is designed and fabricated, and an image processing algorithm is developed and implemented to extract precise laser lines on tested welds. A camera calibration method based on a gyro sensor is used to cope with the complex motion of the welding robot. Data are obtained based on GMA welding experiments at various welding conditions for the estimation of quality prediction models. Deep neural network (DNN) models are developed based on external bead shapes and welding conditions to predict the internal bead shapes and the tensile strengths of welded joints. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

Other

Jump to: Research

11 pages, 3723 KiB

Open AccessLetter

High-Resolution Thermal Imaging and Analysis of TIG Weld Pool Phase Transitions

by Nicholas Boone, Matthew Davies, Jon Raffe Willmott, Hector Marin-Reyes and Richard French

Sensors 2020, 20(23), 6952; https://doi.org/10.3390/s20236952 - 05 Dec 2020

Cited by 9 | Viewed by 2331

Abstract

Tungsten inert gas (TIG) welding is a well-established joining process and offers the user flexibility to weld a large range of materials. Ultra-thin turbine tipping is an important application for TIG welding that is exceptionally challenging due to the wide range of variables [...] Read more.

Tungsten inert gas (TIG) welding is a well-established joining process and offers the user flexibility to weld a large range of materials. Ultra-thin turbine tipping is an important application for TIG welding that is exceptionally challenging due to the wide range of variables needed to accurately control the process: slope times, arc control, travel speed, etc. We offer new insight into weld pool characteristics, utilizing both on- and off-line measurements of weld tracks. High-resolution thermal imaging yields spatially and temporally resolved weld pool phase transitions coupled with post-weld photographs, which gives a novel perspective into the thermal history of a weld. Our imaging system is filtered to measure a 10 nm window at 950 nm and comprises a commercial Sigma lens to produce a near-infrared (NIR) camera. The measured near-infrared radiance is calibrated for temperature over the range of from 800 to 1350 °C. Full article

(This article belongs to the Special Issue Sensors for Manufacturing Process Monitoring)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Sensors for Manufacturing Process Monitoring

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI