Multiple Sound Sensors And Fusion In Modern CNN-Based Machine State Prediction

2021 ◽  
Author(s):  
Eunseob Kim ◽  
Huitaek Yun ◽  
Martin Byung-Guk Jun ◽  
Kyunghyun Kim ◽  
Suk Won Cha
Keyword(s):  
Sensor Fusion ◽  
Machine Tools ◽  
Time Course ◽  
Irregular Sampling ◽  
Machine Learning Techniques ◽  
Smart Manufacturing ◽  
New Era ◽  
Machine Monitoring ◽  
Factory Of The Future ◽  
Auditory Monitoring

Abstract In the new era of manufacturing with Industry 4.0, Smart Manufacturing (SM) is growing in popularity as a potential for the factory of the future. A critical component of SM is effective machine monitoring. Legacy machines indirect monitoring using Internet of Things (IoT) sensors are preferred instead of modifying hardware directly. Machine tools are composed of rotary components, resulting in machine tools emitting acoustic and vibratory signals. However, sound data cannot easily function as a direct representation for machine status due to its noise, variable time course, and irregular sampling. In this paper, we attempt to bridge this gap through machine learning techniques and auditory monitoring of auxiliary components (i.e., coolant, chip conveyor, and mist collector) as well as the main spindle running state of machine tools. Multi-label classification and Convolutional Neural Network (CNN) were utilized to train models for monitoring machine tools from the sound features. An external microphone and three internal sound sensors were attached to both mill and lathe machines. As a sound feature, Mel-frequency cepstrum (MFCC) features were extracted. The classification task performance was compared between each sensor location and early sensor fusion. The results showed that the sensor fusion approach resulted in the highest F1 score on both machine system.

scholarly journals Feasibility of Machine Learning Algorithms for Predicting the Deformation of Anodic Titanium Films by Modulating Anodization Processes

Materials ◽  
2021 ◽  
Vol 14 (5) ◽  
pp. 1089
Author(s):  
Sung-Hee Kim ◽  
Chanyoung Jeong
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Multiclass Classification ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Smart Manufacturing ◽  
Gradient Boosting ◽  
Experimental Conditions ◽  
Learning Techniques ◽  
Tio2 Nanostructures

This study aims to demonstrate the feasibility of applying eight machine learning algorithms to predict the classification of the surface characteristics of titanium oxide (TiO2) nanostructures with different anodization processes. We produced a total of 100 samples, and we assessed changes in TiO2 nanostructures’ thicknesses by performing anodization. We successfully grew TiO2 films with different thicknesses by one-step anodization in ethylene glycol containing NH4F and H2O at applied voltage differences ranging from 10 V to 100 V at various anodization durations. We found that the thicknesses of TiO2 nanostructures are dependent on anodization voltages under time differences. Therefore, we tested the feasibility of applying machine learning algorithms to predict the deformation of TiO2. As the characteristics of TiO2 changed based on the different experimental conditions, we classified its surface pore structure into two categories and four groups. For the classification based on granularity, we assessed layer creation, roughness, pore creation, and pore height. We applied eight machine learning techniques to predict classification for binary and multiclass classification. For binary classification, random forest and gradient boosting algorithm had relatively high performance. However, all eight algorithms had scores higher than 0.93, which signifies high prediction on estimating the presence of pore. In contrast, decision tree and three ensemble methods had a relatively higher performance for multiclass classification, with an accuracy rate greater than 0.79. The weakest algorithm used was k-nearest neighbors for both binary and multiclass classifications. We believe that these results show that we can apply machine learning techniques to predict surface quality improvement, leading to smart manufacturing technology to better control color appearance, super-hydrophobicity, super-hydrophilicity or batter efficiency.

scholarly journals Personalized Health and the Coronavirus Vaccines --Do Individual Genetics Matter?

2021 ◽  
Author(s):  
Bianca N Valdés-Fernández ◽  
Jorge Duconge ◽  
Ana M Espino ◽  
Gualberto Ruaño
Keyword(s):  
Chemokine Receptors ◽  
Viral Vectors ◽  
Time Course ◽  
New Era ◽  
Vaccine Responses ◽  
Histocompatibility Complex ◽  
Technology Platforms ◽  
Preventative Interventions ◽  
Personalized Health

This article assesses the role of recipient genetics to COVID-19 vaccine responses. Vaccines represent preventative interventions suitable to an immunogenetic perspective to predict how human variability will influence their safety and efficacy. The genetic polymorphism among individuals within any population can make possible that the immunity elicited by a vaccine is variable in length and strength. The same immune challenge (either virus or vaccine) could provoke partial, complete or even failed protection for some individuals treated under the same conditions. We review genetic variants and mechanistic relationships among chemokines, chemokine receptors, interleukins, interferons, interferon receptors, toll-like receptors, histocompatibility antigens, various immunoglobulins and major histocompatibility complex antigens. These are the targets for variation among macrophages, dendritic cells, Natural Killer cells, T- and B- lymphocytes, and complement. The acute nature of vaccine reactogenicity is reminiscent of the time course of adverse drug reaction mediated by the immune system. The variety of technology platforms (mRNA, viral vectors) utilized currently to produce vaccines against SARS-CoV-2 infections may each also trigger genetically distinct immune reactogenic profiles. With biobanking of recipient genomic DNA and serum immunoprofiling, global COVID-19 vaccinations could launch a new era of research and clinical translation in personalized health.

scholarly journals A general end-to-end diagnosis framework for manufacturing systems

2019 ◽  
Vol 7 (2) ◽  
pp. 418-429 ◽  
Author(s):  
Ye Yuan ◽  
Guijun Ma ◽  
Cheng Cheng ◽  
Beitong Zhou ◽  
Huan Zhao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Manufacturing Systems ◽  
Time Course ◽  
Manufacturing Sector ◽  
Smart Manufacturing ◽  
Data Sets ◽  
Learning Techniques ◽  
General Data ◽  
End To End ◽  
Manufacturing Applications

Abstract The manufacturing sector is envisioned to be heavily influenced by artificial-intelligence-based technologies with the extraordinary increases in computational power and data volumes. A central challenge in the manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications. Here, we propose a general data-driven, end-to-end framework for the monitoring of manufacturing systems. This framework, derived from deep-learning techniques, evaluates fused sensory measurements to detect and even predict faults and wearing conditions. This work exploits the predictive power of deep learning to automatically extract hidden degradation features from noisy, time-course data. We have experimented the proposed framework on 10 representative data sets drawn from a wide variety of manufacturing applications. Results reveal that the framework performs well in examined benchmark applications and can be applied in diverse contexts, indicating its potential use as a critical cornerstone in smart manufacturing.

scholarly journals 10,000 km course in search of machine tools – a report from the Taipei International Machine Tool Show in Taiwan

Mechanik ◽  
2017 ◽  
Vol 90 (5-6) ◽  
pp. 366-371
Author(s):  
Norbert Kępczak
Keyword(s):  
Machine Tool ◽  
Machine Tools ◽  
Smart Manufacturing ◽  
Machinery Industry

26th Taipei International Machine Tool Show – TIMTOS 2017 was held from 7 to 12 of March 2017. The keynote of this year show was “Smart Manufacturing”. The schedule included press conferences. Visitors were encouraged to get acquainted with the offers from production companies and to speak to the leading persons in Taiwan machinery industry.

scholarly journals A computational strategy for finding novel targets and therapeutic compounds for opioid dependence

2018 ◽  
Author(s):  
Xiaojun Wu ◽  
Siwei Xie ◽  
Lirong Wang ◽  
Peihao Fan ◽  
Songwei Ge ◽  
...  
Keyword(s):  
Opioid Dependence ◽  
Time Course ◽  
Early Stage ◽  
The United States ◽  
Opioid Addiction ◽  
Machine Learning Techniques ◽  
Analgesic Effects ◽  
Transcription Regulators ◽  
Novel Targets ◽  
Computational Strategy

AbstractOpioids are widely used for treating different types of pains, but overuse and abuse of prescription opioids have led to opioid epidemic in the United States. Besides analgesic effects, chronic use of opioid can also cause tolerance, dependence, and even addiction. Effective treatment of opioid addiction remains a big challenge today. Studies on addictive effects of opioids focus on striatum, a main component in the brain responsible for drug dependence and addiction. Some transcription regulators have been associated with opioid addiction, but relationship between analgesic effects of opioids and dependence behaviors mediated by them at the molecular level has not been thoroughly investigated. In this paper, we developed a new computational strategy that identifies novel targets and potential therapeutic molecular compounds for opioid dependence and addiction. We employed several statistical and machine learning techniques and identified differentially expressed genes over time which were associated with dependence-related behaviors after exposure to either morphine or heroin, as well as potential transcription regulators that regulate these genes, using time course gene expression data from mouse striatum. Moreover, our findings revealed that some of these dependence-associated genes and transcription regulators are known to play key roles in opioid-mediated analgesia and tolerance, suggesting that an intricate relationship between opioid-induce pain-related pathways and dependence may develop at an early stage during opioid exposure. Finally, we determined small compounds that can potentially target the dependence-associated genes and transcription regulators. These compounds may facilitate development of effective therapy for opioid dependence and addiction. We also built a database (http://daportals.org) for all opioid-induced dependence-associated genes and transcription regulators that we discovered, as well as the small compounds that target those genes and transcription regulators.

scholarly journals Special Issue on the Latest Machine Tool Technologies and Manufacturing Processes

2019 ◽  
Vol 13 (5) ◽  
pp. 573-573 ◽  
Author(s):  
Yohichi Nakao ◽  
Hayato Yoshioka
Keyword(s):  
Internet Of Things ◽  
Machine Tool ◽  
Machine Tools ◽  
Manufacturing Systems ◽  
Tool Path ◽  
Industrie 4.0 ◽  
Smart Manufacturing ◽  
Manufacturing Processes ◽  
Special Issue ◽  
Excellent Research

With the 2011 launch of Industrie 4.0, a German project aiming to promote the computerization of manufacturing, the integration of physical or actual manufacturing systems with cyber-physical systems (CPS) using various technologies, such as the Internet of things (IoT), industrial Internet of things (IIOT), and artificial intelligence, is considered to be more important than ever before. One of the goals of the Industrie 4.0 is to realize smart factories or smart manufacturing using advanced digital technologies. However, the core component in the manufacturing systems is still machine tools. This special issue, composed of eleven excellent research papers, focuses on the latest research advances in machine tools and manufacturing processes. It covers various topics, including machine tool control, tool path generation for multi-axis machining, and machine tool components. Furthermore, this special issue includes innovative machining technologies, including not only cutting and grinding processes but also the EDM process and burnishing process connected effectively with force control techniques. All the research contributions were presented at IMEC2018, a joint event with JIMTOF2018, held in Tokyo, Japan in 2018. The editors would like to sincerely thank the authors for their dedication and for their well written and illustrated manuscripts. We are also profoundly grateful for the efforts of all the reviewers who ensured their quality. Finally, we sincerely hope that studies on machine tools and related manufacturing technologies will further contribute to the development of our global society.

scholarly journals Adoption of Big Data by Global Chemical Industries

2021 ◽  
Author(s):  
Ashiff Khan ◽  
A Seetharaman ◽  
Abhijit Dasgupta
Keyword(s):  
Big Data ◽  
Data Science ◽  
Data Driven ◽  
Smart Manufacturing ◽  
Time Data ◽  
New Era ◽  
Potential Applications ◽  
Data Driven Approach ◽  
Process Plants ◽  
The Right

The new era of Big Data (BD) is influencing the chemical industries tremendously, providing several opportunities to reshape the way they operate and for shifting towards smart manufacturing. Given the availability of free software, and the large amount of real-time data generated and stored in process plants why many chemical industries are still not fully adopting BD? The industry is just starting to realize the importance of a large amount of data that they own to make the right decisions and to support their strategies. This article is exploring the importance of professional competencies and data science that influence BD in chemical industries for shifting towards smart manufacturing in a fast and reliable manner. This article utilizes a literature review and identifies potential applications in the chemical industry to shift from conventional methods towards a data-driven approach.

Rapidly Deployable MTConnect-Based Machine Tool Monitoring Systems

2017 ◽  
Author(s):  
Roby Lynn ◽  
Wafa Louhichi ◽  
Mahmoud Parto ◽  
Ethan Wescoat ◽  
Thomas Kurfess
Keyword(s):  
Data Collection ◽  
Open Source ◽  
Machine Tools ◽  
Large Scale ◽  
Machining Process ◽  
Medium Size ◽  
Time Data ◽  
Machine Monitoring ◽  
Tool Monitoring ◽  
Data Collection And Analysis

The amount of data that can be gathered from a machining process is often misunderstood, and even if these data are collected, they are frequently underutilized. Intelligent uses of data collected from a manufacturing operation can lead to increased productivity and lower costs. While some large-scale manufacturers have developed custom solutions for data collection from their machine tools, small- and medium-size enterprises need efficient and easily deployable methods for data collection and analysis. This paper presents three broad solutions to data collection from machine tools, all of which rely on the open-source and royalty-free MTConnect protocol: the first is a machine monitoring dashboard based on Microsoft Excel; the second is an open source solution using Python and MTConnect; and the third is a cloud-based system using Google Sheets. Time studies are performed on these systems to determine their capability to gather near real-time data from a machining process.

scholarly journals Spectral Analysis on Time-Course Expression Data: Detecting Periodic Genes Using a Real-Valued Iterative Adaptive Approach

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Kwadwo S. Agyepong ◽  
Fang-Han Hsu ◽  
Edward R. Dougherty ◽  
Erchin Serpedin
Keyword(s):  
Time Course ◽  
Hypothesis Test ◽  
Expression Profiles ◽  
Real Data ◽  
Small Sample ◽  
Irregular Sampling ◽  
Periodic Signal ◽  
Expression Data ◽  
Adaptive Approach ◽  
Iterative Adaptive Approach

Time-course expression profiles and methods for spectrum analysis have been applied for detecting transcriptional periodicities, which are valuable patterns to unravel genes associated with cell cycle and circadian rhythm regulation. However, most of the proposed methods suffer from restrictions and large false positives to a certain extent. Additionally, in some experiments, arbitrarily irregular sampling times as well as the presence of high noise and small sample sizes make accurate detection a challenging task. A novel scheme for detecting periodicities in time-course expression data is proposed, in which a real-valued iterative adaptive approach (RIAA), originally proposed for signal processing, is applied for periodogram estimation. The inferred spectrum is then analyzed using Fisher’s hypothesis test. With a proper -value threshold, periodic genes can be detected. A periodic signal, two nonperiodic signals, and four sampling strategies were considered in the simulations, including both bursts and drops. In addition, two yeast real datasets were applied for validation. The simulations and real data analysis reveal that RIAA can perform competitively with the existing algorithms. The advantage of RIAA is manifested when the expression data are highly irregularly sampled, and when the number of cycles covered by the sampling time points is very reduced.

Sign in / Sign up

Export Citation Format

Share Document