scholarly journals AI for in-line vehicle sequence controlling: development and evaluation of an adaptive machine learning artifact to predict sequence deviations in a mixed-model production line

2021 ◽  
Author(s):  
Maximilian Stauder ◽  
Niklas Kühl
Keyword(s):  
Automotive Industry ◽  
Mixed Model ◽  
Manufacturing Sector ◽  
Early Stage ◽  
Classification Model ◽  
Control Mechanisms ◽  
Body Type ◽  
Algorithm Selection ◽  
Special Equipment ◽  
Sequence Scrambling

AbstractCustomers in the manufacturing sector, especially in the automotive industry, have a high demand for individualized products at price levels comparable to traditional mass-production. The contrary objectives of providing a variety of products and operating at minimum costs have introduced a high degree of production planning and control mechanisms based on a stable order sequence for mixed-model assembly lines. A major threat to this development is sequence scrambling, triggered by both operational and product-related root causes. Despite the introduction of Just-in-time and fixed production times, the problem of sequence scrambling remains partially unresolved in the automotive industry. Negative downstream effects range from disruptions in the Just-in-sequence supply chain, to a discontinuation of the production process. A precise prediction of sequence deviations at an early stage allows the introduction of counteractions to stabilize the sequence before disorder emerges. While procedural causes are widely addressed in research, the work at hand requires a different perspective involving a product-related view. Built on unique data from a real-world global automotive manufacturer, a supervised classification model is trained and evaluated. This includes all the necessary steps to design, implement, and assess an AI-artifact, as well as data gathering, preprocessing, algorithm selection, and evaluation. To ensure long-term prediction stability, we include a continuous learning module to counter data drifts. We show that up to 50% of the major deviations can be predicted in advance. However, we do not consider any process-related information, such as machine conditions and shift plans, but solely focus on the exploitation of product features like body type, power train, color, and special equipment.

scholarly journals Characterization of Thin Chromium Coatings Produced by PVD Sputtering for Optical Applications

Coatings ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 215
Author(s):  
Andreia A. Ferreira ◽  
Francisco J. G. Silva ◽  
Arnaldo G. Pinto ◽  
Vitor F. C. Sousa
Keyword(s):  
Automotive Industry ◽  
Vapor Deposition ◽  
Physical Vapor Deposition ◽  
Early Stage ◽  
Chemical Vapor ◽  
Experimental Tests ◽  
Scratch Test ◽  
Industrial Sectors ◽  
Deposition Processes ◽  
Optical Applications

PVD (physical vapor deposition) and CVD (chemical vapor deposition) have gained greater significance in the last two decades with the mandatory shift from electrodeposition processes to clean deposition processes due to environmental, public safety, and health concerns. Due to the frequent use of coatings in several industrial sectors, the importance of studying the chromium coating processes through PVD–sputtering can be realized, investing in a real alternative to electroplated hexavalent chromium, usually denominated by chromium 6, regularly applied in electrodeposition processes of optical products in the automotive industry. At an early stage, experimental tests were carried out to understand which parameters are most suitable for obtaining chromium coatings with optical properties. To study the coating in a broad way, thickness and roughness analysis of the coatings obtained using SEM and AFM, adhesion analyzes with the scratch-test and transmittance by spectrophotometry were carried out. It was possible to determine that the roughness and transmittance decreased with the increase in the number of layers, the thickness of the coating increased linearly, and the adhesion and resistance to climatic tests remained positive throughout the study. Thus, this study allows for the understanding that thin multilayered Cr coatings can be applied successfully to polymeric substrates regarding optical applications in the automotive industry.

Kit preparation for mixed-model assembly: efficiency impact of confirmation methods

2019 ◽  
Vol 119 (3) ◽  
pp. 547-560 ◽  
Author(s):  
Patrik Fager
Keyword(s):  
Learning Curve ◽  
Design Methodology ◽  
Mixed Model ◽  
Early Stage ◽  
Time Efficiency ◽  
Content Type ◽  
Order Batching ◽  
The Impact ◽  
Mixed Model Assembly ◽  
Practical Implications

PurposeConfirmations are applied in kit preparation for mixed-model assembly to promote quality, but research that explains the impact on time efficiency has been lacking. The purpose of this paper is to determine the extent to which the type of confirmation method relates to time-efficient kit preparation when order batching is applied.Design/methodology/approachAn industrially relevant laboratory experiment is applied, simulating kit preparation with order batching for mixed-model assembly. The time efficiency is studied as associated with four confirmation methods – barcode ring scanner, button presses, voice commands and RFID-reading wristbands – when applied as pick-from and place-to confirmation. Furthermore, the paper also considers the quality outcome.FindingsEfficiency is promoted by methods that minimise interrupting the picker’s motions when performing pick-from confirmations and with methods that allow each hand to place components and perform place-to confirmations simultaneously – here represented by button presses and RFID-reading wristbands. Moreover, combining various methods for the tasks of pick-from or place-to confirmation can benefit efficiency.Research limitations/implicationsPickers at an early stage of the learning curve (one shift of training) were considered.Practical implicationsThe findings promote the customised applications of picking information systems in industry.Social implicationsCombining various methods for the tasks of pick-from and place-to confirmation can provide more fitting applications that better align with the picker’s preferences.Originality/valueCombinations of various methods when applied as either pick-from or place-to confirmation, or both, are studied.

Picturing the Indian Automotive Sector's Slowdown

2021 ◽  
pp. 16-25
Author(s):  
Rajat Deb
Keyword(s):  
Automotive Industry ◽  
Manufacturing Sector ◽  
Contributing Factors ◽  
Double Digit ◽  
Stimulus Package

The Indian automotive industry has remained a significant driver of the manufacturing sector and contributed to the GDP around 7% in 2018, but it is confronting its biggest slump in last 19 years with a double digit downfall in revenues across all segments. Such slowdown has caused job cuts of around 0.2 million workers, particularly contractual labourers, and shut down of around 300 dealers' shops in the last few months. A number of cyclical and structural contributing factors for the slowdown have been identified. Measures for turnaround are suggested, highlighting a recently announced stimulus package for reviving the industry.

scholarly journals Truck Body-Type Classification using Single-Beam Lidar Sensors

2019 ◽  
Vol 2673 (1) ◽  
pp. 26-40 ◽  
Author(s):  
Magdalena I. Asborno ◽  
Collin G. Burris ◽  
Sarah Hernandez
Keyword(s):  
Model Development ◽  
True Positive Rate ◽  
Classification Model ◽  
Proof Of Concept ◽  
Body Type ◽  
Commodity Flow ◽  
Single Beam ◽  
Loop Detectors ◽  
Low Profile ◽  
Type Classification

Understanding commodity flow through a region is key for estimating the demand for freight transportation facilities and services, forecasting energy consumption, analyzing safety risks, and addressing environmental concerns. Transportation planners and decision makers use commodity flow data to develop and implement long-term freight plans and manage infrastructure. State-of-the-practice commodity flow estimations based on regional socioeconomic data and periodic surveys have limited spatial and temporal coverage. Moreover, no existing methods tie vehicles to commodity movements at the link level. Although intrusive inductive loop detectors can identify the industry served (or commodity carried) by trucks based on the truck’s body type, intrusive sensor performance is limited by pavement quality. Unfortunately, poor pavement conditions are common in locations with high truck volumes. This paper investigates the use of a non-intrusive traffic sensor, Lidar, for high-resolution truck body-type classification. This paper develops a proof-of-concept Lidar sensor and a truck body-type classification model capable of classifying five-axle tractor-trailers into distinct body types: van and container, platform, low-profile trailer, tank, and hopper and end dump. These body-class groups link to commodity movements and provide insight into link-level commodity flows. Data for model development and validation were collected along a major interstate corridor and a low-speed local road. The classification model achieves an 81% true positive rate (TPR) with class-specific TPR as high as 94% and average volume accuracy of 87% for the primary test location. Overall, the proposed sensor represents an adequate proof of concept to evaluate the industry served by trucks on a network link.

scholarly journals Development of an in silico prediction system of human renal excretion and clearance from chemical structure information incorporating fraction unbound in plasma as a descriptor

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Reiko Watanabe ◽  
Rikiya Ohashi ◽  
Tsuyoshi Esaki ◽  
Hitoshi Kawashima ◽  
Yayoi Natsume-Kitatani ◽  
...  
Keyword(s):  
Renal Clearance ◽  
In Silico ◽  
Regression Models ◽  
Chemical Structure ◽  
Prediction Models ◽  
Renal Excretion ◽  
Early Stage ◽  
Classification Model ◽  
Prediction System ◽  
Structure Information

AbstractPrediction of pharmacokinetic profiles of new chemical entities is essential in drug development to minimize the risks of potential withdrawals. The excretion of unchanged compounds by the kidney constitutes a major route in drug elimination and plays an important role in pharmacokinetics. Herein, we created in silico prediction models of the fraction of drug excreted unchanged in the urine (fe) and renal clearance (CLr), with datasets of 411 and 401 compounds using freely available software; notably, all models require chemical structure information alone. The binary classification model for fe demonstrated a balanced accuracy of 0.74. The two-step prediction system for CLr was generated using a combination of the classification model to predict excretion-type compounds and regression models to predict the CLr value for each excretion type. The accuracies of the regression models increased upon adding a descriptor, which was the observed and predicted fraction unbound in plasma (fu,p); 78.6% of the samples in the higher range of renal clearance fell within 2-fold error with predicted fu,p value. Our prediction system for renal excretion is freely available to the public and can be used as a practical tool for prioritization and optimization of compound synthesis in the early stage of drug discovery.

scholarly journals Control and Coordination of Design-Driven Innovation Processes: Case Evidence from the Automotive Industry

2018 ◽  
Vol 30 (3) ◽  
pp. 75-94 ◽  
Author(s):  
Nico Peter Berhausen ◽  
Sof Thrane
Keyword(s):  
Technological Innovation ◽  
Automotive Industry ◽  
Technological Development ◽  
The Other ◽  
Control Mechanisms ◽  
Aesthetic Value ◽  
Technical Performance ◽  
Separate Control ◽  
Innovation Processes ◽  
Over Time

ABSTRACT The control and coordination of design and technological innovation pose a dilemma for design-driven organizations because the measurability of design and technological innovation differ. On one hand, a product's aesthetic value might increase if its design is separated from technological innovation and if design is controlled by means other than those used in technological innovation. On the other hand, tight integration is warranted because a product's design affects its cost, technical performance, and manufacturability. This dilemma is the focus of the paper. The paper contributes to extant literature in several ways. First, it conceptualizes control as a process that manages design and technological innovation through distinct, separate control mechanisms. Second, it analyzes and develops three modes of convergence through which the potentially contradictory concerns of design and technological development can be compared and evaluated. Finally, the paper suggests that coordination can be achieved through convergence processes that unfold and develop over time.

scholarly journals Mapping the Wave of Industry Digitalization by Co-Word Analysis: An Exploration of Four Disruptive Industries

2021 ◽  
Author(s):  
Levan Bzhalava ◽  
Sohaib S. Hassan ◽  
Jari Kaivo-oja ◽  
Bengt Köping Olsson ◽  
Javed Imran
Keyword(s):  
Strategic Planning ◽  
Stock Exchange ◽  
Manufacturing Sector ◽  
Early Stage ◽  
Elderly Care ◽  
Digital Technologies ◽  
Finance Industry ◽  
Word Analysis ◽  
Industrial Landscape ◽  
Emerging Trends

This paper aims to identify global digital trends across industries and to map emerging business areas by co-word analysis. As the industrial landscape has become complex and dynamic due to the rapid pace of technological changes and digital transformation, identifying industrial trends can be critical for strategic planning and investment policy at the firm and regional level. For this purpose, the paper examines industry and technology profiles of top startups across four industries (i.e. education, finance, healthcare, manufacturing) using CrunchBase metadata for the period 2016–2018 and studies in which subsector early-stage firms bring digital technologies on a global level. In particular, we apply word co-occurrence analysis to reveal which subindustry and digital technology keywords/keyphrases appear together in startup company classification. We also use network analysis to visualize industry structure and to identify digitalization trends across sectors. The results obtained from the analysis show that gamification and personalization are emerging trends in the education sector. In the finance industry, digital technologies penetrate in a wide set of services such as financial transactions, payments, insurance, venture capital, stock exchange, asset and risk management. Moreover, the data analyses indicate that health diagnostics and elderly care areas are at the forefront of the healthcare industry digitalization. In the manufacturing sector, startup companies focus on automating industrial processes and creating smart interconnected manufacturing. Finally, we discuss the implications of the study for strategic planning and management.

scholarly journals Development of an Autism Screening Classification Model for Toddlers

2021 ◽  
Author(s):  
Afef Saihi ◽  
Hussam Alshraideh
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Early Stage ◽  
Neurodevelopmental Disorder ◽  
Autism Spectrum ◽  
Repetitive Behaviors ◽  
Therapeutic Interventions ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Early Screening

Autism spectrum disorder ASD is a neurodevelopmental disorder associated with challenges in communication, social interaction, and repetitive behaviors. Getting a clear diagnosis for a child is necessary for starting early intervention and having access to therapy services. However, there are many barriers that hinder the screening of these kids for autism at an early stage which might delay further the access to therapeutic interventions. One promising direction for improving the efficiency and accuracy of ASD detection in toddlers is the use of machine learning techniques to build classifiers that serve the purpose. This paper contributes to this area and uses the data developed by Dr. Fadi Fayez Thabtah to train and test various machine learning classifiers for the early ASD screening. Based on various attributes, three models have been trained and compared which are Decision tree C4.5, Random Forest, and Neural Network. The three models provided very good accuracies based on testing data, however, it is the Neural Network that outperformed the other two models. This work contributes to the early screening of toddlers by helping identify those who have ASD traits and should pursue formal clinical diagnosis.

scholarly journals INFORMATION TECHNOLOGY FOR THE EARLY DIAGNOSYS OF PNEUMONIA USING CONVOLUTIONAL NEURAL NETWORKS

2021 ◽  
Vol 3 ◽  
pp. 101-114
Author(s):  
Pavel Radyuk ◽  
◽  
Alexander Barmak ◽  
Yuri Krak ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Information Technology ◽  
Visual Analysis ◽  
Early Stage ◽  
False Negative ◽  
Receptive Fields ◽  
Classification Model ◽  
X Ray ◽  
Automated Method ◽  
Clinical Recommendation

Over the past few years, pneumonia has become one of the most common and severe lung diseases globally, and its treatment is vital nowadays. Clinical practice has proved that early diagnosis of pneumonia is a crucial factor in its successful treatment. An efficient approach to diagnosing pulmonary diseases, including pneumonia, is automated chest X-ray analysis implemented in clinical recommendation systems. However, it is still unclear what features of pneumonia in an X-ray image correspond to the early stage of the disease according to the automated method of diagnosis. The question of interpreting the results of digital diagnostics also remains open and needs further investigation. Therefore, to address an urgent issue of interpretation in digital diagnosis, we propose an information technology for the visual analysis of X-ray images to explain the results of diagnosing pneumonia. The technology comprises a classification model based on a convolutional neural network to extract mild features of early viral pneumonia and a modified method of distinctive localization to interpret the classification results. The neural network used in the study contains an effective dilated convolutional operation to combine features of various receptive fields. Our method of interpretation is based on applying weighted gradients to class activation maps. It distinguishes lung masks in the X-ray image and imposes thermal maps with a color gradient from blue to bright red. The red color corresponds to the most probable location of the pneumonia features in the radiograph. Such a modification provides excellent localization of abnormal areas on radiographs, removing the mild target features of early pneumonia. According to the computational results, our model surpassed other neural architectures in precision (98,5 %) but slightly conceded in classification accuracy (96,1 %) and recall (93,6 %). Moreover, it shows relatively low false positive and false negative rates, with 1,4 and 6,4 %, respectively. Overall, according to computational experiments, the proposed information technology can be an effective tool for instant diagnosis in the first suspicion of pneumonia.

scholarly journals The Design of Early-Stage Plant Breeding Trials Using Genetic Relatedness

2020 ◽  
Vol 25 (4) ◽  
pp. 553-578 ◽  
Author(s):  
Brian R. Cullis ◽  
Alison B. Smith ◽  
Nicole A. Cocks ◽  
David G. Butler
Keyword(s):  
Plant Breeding ◽  
Mixed Model ◽  
Linear Mixed Model ◽  
Genetic Relatedness ◽  
Early Stage ◽  
Genetic Effects ◽  
Breeding Programs ◽  
Model Based ◽  
Selection Decisions ◽  
Design Generation

Abstract The use of appropriate statistical methods has a key role in improving the accuracy of selection decisions in a plant breeding program. This is particularly important in the early stages of testing in which selections are based on data from a limited number of field trials that include large numbers of breeding lines with minimal replication. The method of analysis currently recommended for early-stage trials in Australia involves a linear mixed model that includes genetic relatedness via ancestral information: non-genetic effects that reflect the experimental design and a residual model that accommodates spatial dependence. Such analyses have been widely accepted as they have been found to produce accurate predictions of both additive and total genetic effects, the latter providing the basis for selection decisions. In this paper, we present the results of a case study of 34 early-stage trials to demonstrate this type of analysis and to reinforce the importance of including information on genetic relatedness. In addition to the application of a superior method of analysis, it is also critical to ensure the use of sound experimental designs. Recently, model-based designs have become popular in Australian plant breeding programs. Within this paradigm, the design search would ideally be based on a linear mixed model that matches, as closely as possible, the model used for analysis. Therefore, in this paper, we propose the use of models for design generation that include information on genetic relatedness and also include non-genetic and residual models based on the analysis of historic data for individual breeding programs. At present, the most commonly used design generation model omits genetic relatedness information and uses non-genetic and residual models that are supplied as default models in the associated software packages. The major reasons for this are that preexisting software is unacceptably slow for designs incorporating genetic relatedness and the accuracy gains resulting from the use of genetic relatedness have not been quantified. Both of these issues are addressed in the current paper. An updating scheme for calculating the optimality criterion in the design search is presented and is shown to afford prodigious computational savings. An in silico study that compares three types of design function across a range of ancillary treatments shows the gains in accuracy for the prediction of total genetic effects (and thence selection) achieved from model-based designs using genetic relatedness and program specific non-genetic and residual models. Supplementary materials accompanying this paper appear online.

Sign in / Sign up

Export Citation Format

Share Document