Machines

Research

Jump to: Review

16 pages, 4532 KiB

Open AccessArticle

Recognition of Human Face Regions under Adverse Conditions—Face Masks and Glasses—In Thermographic Sanitary Barriers through Learning Transfer from an Object Detector

by Joabe R. da Silva, Gustavo M. de Almeida, Marco Antonio de S. L. Cuadros, Hércules L. M. Campos, Reginaldo B. Nunes, Josemar Simão and Pablo R. Muniz

Machines 2022, 10(1), 43; https://doi.org/10.3390/machines10010043 - 7 Jan 2022

Cited by 8 | Viewed by 2890

Abstract

The COVID-19 pandemic has detrimentally affected people’s lives and the economies of many countries, causing disruption in the health, education, transport, and other sectors. Several countries have implemented sanitary barriers at airports, bus and train stations, company gates, and other shared spaces to [...] Read more.

The COVID-19 pandemic has detrimentally affected people’s lives and the economies of many countries, causing disruption in the health, education, transport, and other sectors. Several countries have implemented sanitary barriers at airports, bus and train stations, company gates, and other shared spaces to detect patients with viral symptoms in an effort to contain the spread of the disease. As fever is one of the most recurrent disease symptoms, the demand for devices that measure skin (body surface) temperature has increased. The thermal imaging camera, also known as a thermal imager, is one such device used to measure temperature. It employs a technology known as infrared thermography and is a noninvasive, fast, and objective tool. This study employed machine learning transfer using You Only Look Once (YOLO) to detect the hottest temperatures in the regions of interest (ROIs) of the human face in thermographic images, allowing the identification of a febrile state in humans. The algorithms detect areas of interest in the thermographic images, such as the eyes, forehead, and ears, before analyzing the temperatures in these regions. The developed software achieved excellent performance in detecting the established areas of interest, adequately indicating the maximum temperature within each region of interest, and correctly choosing the maximum temperature among them. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

26 pages, 5070 KiB

Open AccessFeature PaperArticle

Blending Colored and Depth CNN Pipelines in an Ensemble Learning Classification Approach for Warehouse Application Using Synthetic and Real Data

by Paulo Henrique Martinez Piratelo, Rodrigo Negri de Azeredo, Eduardo Massashi Yamao, Jose Francisco Bianchi Filho, Gabriel Maidl, Felipe Silveira Marques Lisboa, Laercio Pereira de Jesus, Renato de Arruda Penteado Neto, Leandro dos Santos Coelho and Gideon Villar Leandro

Machines 2022, 10(1), 28; https://doi.org/10.3390/machines10010028 - 31 Dec 2021

Cited by 5 | Viewed by 2894

Abstract

Electric companies face flow control and inventory obstacles such as reliability, outlays, and time-consuming tasks. Convolutional Neural Networks (CNNs) combined with computational vision approaches can process image classification in warehouse management applications to tackle this problem. This study uses synthetic and real images [...] Read more.

Electric companies face flow control and inventory obstacles such as reliability, outlays, and time-consuming tasks. Convolutional Neural Networks (CNNs) combined with computational vision approaches can process image classification in warehouse management applications to tackle this problem. This study uses synthetic and real images applied to CNNs to deal with classification of inventory items. The results are compared to seek the neural networks that better suit this application. The methodology consists of fine-tuning several CNNs on Red–Green–Blue (RBG) and Red–Green–Blue-Depth (RGB-D) synthetic and real datasets, using the best architecture of each domain in a blended ensemble approach. The proposed blended ensemble approach was not yet explored in such an application, using RGB and RGB-D data, from synthetic and real domains. The use of a synthetic dataset improved accuracy, precision, recall and f1-score in comparison with models trained only on the real domain. Moreover, the use of a blend of DenseNet and Resnet pipelines for colored and depth images proved to outperform accuracy, precision and f1-score performance indicators over single CNNs, achieving an accuracy measurement of 95.23%. The classification task is a real logistics engineering problem handled by computer vision and artificial intelligence, making full use of RGB and RGB-D images of synthetic and real domains, applied in an approach of blended CNN pipelines. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

17 pages, 6489 KiB

Open AccessArticle

Data Analytics for Noise Reduction in Optical Metrology of Reflective Planar Surfaces

by Cody Berry, Marcos S. G. Tsuzuki and Ahmad Barari

Machines 2022, 10(1), 25; https://doi.org/10.3390/machines10010025 - 29 Dec 2021

Cited by 4 | Viewed by 2301

Abstract

On-line data collection from the manufactured parts is an essential element in Industry 4.0 to monitor the production’s health, which required strong data analytics. The optical metrology-based inspection of highly reflective parts in a production line, such as parts with metallic surfaces, is [...] Read more.

On-line data collection from the manufactured parts is an essential element in Industry 4.0 to monitor the production’s health, which required strong data analytics. The optical metrology-based inspection of highly reflective parts in a production line, such as parts with metallic surfaces, is a difficult challenge. As many on-line inspection paradigms require the use of optical sensors, this reflectivity can lead to large amounts of noise, rendering the scan inaccurate. This paper discusses a method for noise reduction and removal in datapoints resulting from scanning the reflective planar surfaces. Utilizing a global statistic-based iterative approach, noise is gradually removed from the dataset at increasing percentages. The change in the standard deviation of point-plane distances is examined, and an optimal amount of noisy data is removed to reduce uncertainty in representing the workpiece. The developed algorithm provides a fast and efficient method for noise reduction in optical coordinate metrology and scanning. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

26 pages, 2736 KiB

Open AccessArticle

A Digital Twin Architecture Model Applied with MLOps Techniques to Improve Short-Term Energy Consumption Prediction

by Tiago Yukio Fujii, Victor Takashi Hayashi, Reginaldo Arakaki, Wilson Vicente Ruggiero, Romeo Bulla, Jr., Fabio Hirotsugu Hayashi and Khalil Ahmad Khalil

Machines 2022, 10(1), 23; https://doi.org/10.3390/machines10010023 - 28 Dec 2021

Cited by 31 | Viewed by 5782

Abstract

Using extensive databases and known algorithms to predict short-term energy consumption comprises most computational solutions based on artificial intelligence today. State-of-the-art approaches validate their prediction models in offline environments that disregard automation, quality monitoring, and retraining challenges present in online scenarios. The existing [...] Read more.

Using extensive databases and known algorithms to predict short-term energy consumption comprises most computational solutions based on artificial intelligence today. State-of-the-art approaches validate their prediction models in offline environments that disregard automation, quality monitoring, and retraining challenges present in online scenarios. The existing demand response initiatives lack personalization, thus not engaging consumers. Obtaining specific and valuable recommendations is difficult for most digital platforms due to their solution pattern: extensive database, specialized algorithms, and using profiles with similar aspects. The challenges and present personalization tactics have been researched by adopting a digital twin model. This study creates a different approach by adding structural topology to build a new category of recommendation platform using the digital twin model with real-time data collected by IoT sensors to improve machine learning methods. A residential study case with 31 IoT smart meter and smart plug devices with 19-month data (measurements performed each second) validated Digital Twin MLOps architecture for personalized demand response suggestions based on online short-term energy consumption prediction. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

26 pages, 1128 KiB

Open AccessArticle

SQL and NoSQL Databases in the Context of Industry 4.0

by Vitor Furlan de Oliveira, Marcosiris Amorim de Oliveira Pessoa, Fabrício Junqueira and Paulo Eigi Miyagi

Machines 2022, 10(1), 20; https://doi.org/10.3390/machines10010020 - 27 Dec 2021

Cited by 18 | Viewed by 9682

Abstract

The data-oriented paradigm has proven to be fundamental for the technological transformation process that characterizes Industry 4.0 (I4.0) so that big data and analytics is considered a technological pillar of this process. The goal of I4.0 is the implementation of the so-called Smart [...] Read more.

The data-oriented paradigm has proven to be fundamental for the technological transformation process that characterizes Industry 4.0 (I4.0) so that big data and analytics is considered a technological pillar of this process. The goal of I4.0 is the implementation of the so-called Smart Factory, characterized by Intelligent Manufacturing Systems (IMS) that overcome traditional manufacturing systems in terms of efficiency, flexibility, level of integration, digitalization, and intelligence. The literature reports a series of system architecture proposals for IMS, which are primarily data driven. Many of these proposals treat data storage solutions as mere entities that support the architecture’s functionalities. However, choosing which logical data model to use can significantly affect the performance of the IMS. This work identifies the advantages and disadvantages of relational (SQL) and non-relational (NoSQL) data models for I4.0, considering the nature of the data in this process. The characterization of data in the context of I4.0 is based on the five dimensions of big data and a standardized format for representing information of assets in the virtual world, the Asset Administration Shell. This work allows identifying appropriate transactional properties and logical data models according to the volume, variety, velocity, veracity, and value of the data. In this way, it is possible to describe the suitability of relational and NoSQL databases for different scenarios within I4.0. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

17 pages, 4717 KiB

Open AccessArticle

Unmanned Aerial Vehicles Motion Control with Fuzzy Tuning of Cascaded-PID Gains

by Fabio A. A. Andrade, Ihannah P. Guedes, Guilherme F. Carvalho, Alessandro R. L. Zachi, Diego B. Haddad, Luciana F. Almeida, Aurélio G. de Melo and Milena F. Pinto

Machines 2022, 10(1), 12; https://doi.org/10.3390/machines10010012 - 23 Dec 2021

Cited by 21 | Viewed by 4874

Abstract

One of the main challenges of maneuvering an Unmanned Aerial Vehicle (UAV) to keep a stabilized flight is dealing with its fast and highly coupled nonlinear dynamics. There are several solutions in the literature, but most of them require fine-tuning of the parameters. [...] Read more.

One of the main challenges of maneuvering an Unmanned Aerial Vehicle (UAV) to keep a stabilized flight is dealing with its fast and highly coupled nonlinear dynamics. There are several solutions in the literature, but most of them require fine-tuning of the parameters. In order to avoid the exhaustive tuning procedures, this work employs a Fuzzy Logic strategy for online tuning of the PID gains of the UAV motion controller. A Cascaded-PID scheme is proposed, in which velocity commands are calculated and sent to the flight control unit from a given target desired position (waypoint). Therefore, the flight control unit is responsible for the lower control loop. The main advantage of the proposed method is that it can be applied to any UAV without the need of its formal mathematical model. Robot Operating System (ROS) is used to integrate the proposed system and the flight control unit. The solution was evaluated through flight tests and simulations, which were conducted using Unreal Engine 4 with the Microsoft AirSim plugin. In the simulations, the proposed method is compared with the traditional Ziegler-Nichols tuning method, another Fuzzy Logic approach, and the ArduPilot built-in PID controller. The simulation results show that the proposed method, compared to the ArduPilot controller, drives the UAV to reach the desired setpoint faster. When compared to Ziegler-Nichols and another different Fuzzy Logic approach, the proposed method demonstrates to provide a faster accommodation and yield smaller errors amplitudes. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

15 pages, 423 KiB

Open AccessCommunication

Safety Control Architecture for Ventricular Assist Devices

by André C. M. Cavalheiro, Diolino J. Santos Filho, Jônatas C. Dias, Aron J. P. Andrade, José R. Cardoso and Marcos S. G. Tsuzuki

Machines 2022, 10(1), 5; https://doi.org/10.3390/machines10010005 - 22 Dec 2021

Cited by 1 | Viewed by 2807

Abstract

In patients with severe heart disease, the implantation of a ventricular assist device (VAD) may be necessary, especially in patients with an indication for heart transplantation. For this, the Institute Dante Pazzanese of Cardiology (IDPC) has developed an implantable centrifugal blood pump that [...] Read more.

In patients with severe heart disease, the implantation of a ventricular assist device (VAD) may be necessary, especially in patients with an indication for heart transplantation. For this, the Institute Dante Pazzanese of Cardiology (IDPC) has developed an implantable centrifugal blood pump that will be able to help a diseased human heart to maintain physiological blood flow and pressure. This device will be used as a totally or partially implantable VAD. Therefore, performance assurance and correct specification of the VAD are important factors in achieving a safe interaction between the device and the patient’s behavior or condition. Even with reliable devices, some failures may occur if the pumping control does not keep up with changes in the patient’s behavior or condition. If the VAD control system has no fault tolerance and no system dynamic adaptation that occurs according to changes in the patient’s cardiovascular system, a number of limitations can be observed in the results and effectiveness of these devices, especially in patients with acute comorbidities. This work proposes the application of a mechatronic approach to this class of devices based on advanced control, instrumentation, and automation techniques to define a method to develop a hierarchical supervisory control system capable of dynamically, automatically, and safely VAD control. For this methodology, concepts based on Bayesian networks (BN) were used to diagnose the patient’s cardiovascular system conditions, Petri nets (PN) to generate the VAD control algorithm, and safety instrumented systems to ensure the safety of the VAD system. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

26 pages, 3650 KiB

Open AccessArticle

A Model-Based and Goal-Oriented Approach for the Conceptual Design of Smart Grid Services

by Miguel Angel Orellana, Jose Reinaldo Silva and Eduardo L. Pellini

Machines 2021, 9(12), 370; https://doi.org/10.3390/machines9120370 - 20 Dec 2021

Cited by 5 | Viewed by 3222

Abstract

A solid demand to integrate energy consumption and co-generation emerged worldwide, motivated, on one hand, by the need to diversify and enhance energy supply, and, one the other hand, by the pressure to attend to the requirements of a heterogeneous class of users. [...] Read more.

A solid demand to integrate energy consumption and co-generation emerged worldwide, motivated, on one hand, by the need to diversify and enhance energy supply, and, one the other hand, by the pressure to attend to the requirements of a heterogeneous class of users. The coupling between energy service provision and final users also includes balancing user needs, eliminating excesses, and optimizing energy supply while avoiding blackouts. Another motivation is the challenge of having sustainable sources and many adapted to the user ecosystem. Altogether, these motivations lead to more abstract design approaches to co-generation-distributed systems, such as those based on goal-oriented requirements used to model smart grids. This work considers the available design practices and its difficulties in proposing a new method capable of producing a flexible requirement model that could serve for design and maintenance purposes. We suggest coupling the approach based on goal-oriented requirements with model-based engineering to support such a model. The expected result is a sound and flexible requirements model, including a model for the interaction with the final user (now being considered a producer and consumer simultaneously). A case study is presented, wherein a small energy service system in an isolated community in the Amazon rain forest was designed. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

13 pages, 3656 KiB

Open AccessArticle

Industrial Upper-Limb Exoskeleton Characterization: Paving the Way to New Standards for Benchmarking

by Vitor Neves Hartmann, Décio de Moura Rinaldi, Camila Taira and Arturo Forner-Cordero

Machines 2021, 9(12), 362; https://doi.org/10.3390/machines9120362 - 17 Dec 2021

Cited by 10 | Viewed by 3348

Abstract

Exoskeletons have been introduced in industrial environments to prevent overload or repetitive stress injuries in workers. However, due to the lack of public detailed information about most of the commercial exoskeletons, it is necessary to further assess their load capacity and evolution over [...] Read more.

Exoskeletons have been introduced in industrial environments to prevent overload or repetitive stress injuries in workers. However, due to the lack of public detailed information about most of the commercial exoskeletons, it is necessary to further assess their load capacity and evolution over time, as their performance may change with use. We present the design and construction of a controlled device to measure the torque of industrial exoskeletons, along with the results of static and dynamic testing of an exoskeleton model. A step motor in the test bench moves the exoskeleton arm in a pre-defined path at a prescribed speed. The force measured with a beam load cell located at the interface between the exoskeleton arm and the test bench is used to derive the torque. The proposed test bench can be easily modified to allow different exoskeleton models to be tested under the same conditions. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

11 pages, 886 KiB

Open AccessArticle

Water Content Monitoring in Water-in-Oil Emulsions Using a Piezoceramic Sensor

by Carlos A. B. Reyna, Ediguer E. Franco, Alberto L. Durán, Luiz O. V. Pereira, Marcos S. G. Tsuzuki and Flávio Buiochi

Machines 2021, 9(12), 335; https://doi.org/10.3390/machines9120335 - 6 Dec 2021

Cited by 7 | Viewed by 3818

Abstract

This work deals with a transmission-reception ultrasonic technique for the real-time estimation of the water content in water-in-crude oil emulsions. The working principle is the measurement of the propagation velocity, using two in-house manufactured transducers designed for water coupling, with a central frequency [...] Read more.

This work deals with a transmission-reception ultrasonic technique for the real-time estimation of the water content in water-in-crude oil emulsions. The working principle is the measurement of the propagation velocity, using two in-house manufactured transducers designed for water coupling, with a central frequency of about 3 MHz. Water-in-crude oil emulsions with a water volume concentration from

0 %

to

40 %

were generated by mechanical emulsification. Tests were carried out at three temperatures. The results showed that the propagation velocity is a sensitive parameter that is able to determine the water content, allowing for differentiating the concentrations of up to

40 %

of water. The main motivation is the development of techniques for non-invasive and real-time monitoring of the water content of emulsions in petrochemical processes. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

24 pages, 6266 KiB

Open AccessArticle

Speed Control with Indirect Field Orientation for Low Power Three-Phase Induction Machine with Squirrel Cage Rotor

by Robert R. Gomes, Luiz F. Pugliese, Waner W. A. G. Silva, Clodualdo V. Sousa, Guilherme M. Rezende and Fadul F. Rodor

Machines 2021, 9(12), 320; https://doi.org/10.3390/machines9120320 - 27 Nov 2021

Cited by 5 | Viewed by 4481

Abstract

Induction machines are widely used in the industry due to their many advantages compared to other industrial machines. This article presents the study and implementation of speed control applied to a Three-phase Induction Machine (MIT) of the squirrel cage type. The induction motor [...] Read more.

Induction machines are widely used in the industry due to their many advantages compared to other industrial machines. This article presents the study and implementation of speed control applied to a Three-phase Induction Machine (MIT) of the squirrel cage type. The induction motor was modeled using the rotor flux in the synchronous reference to design Proportional-Integral (PI) type controllers for the current and velocity control loops. It is the objective of the article also to present in detail the development of converter hardware that comprises the stages of power, acquisition, and conditioning of engine signals. The system was simulated using computational tools and validated using a prototype designed, constructed, and commissioned. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

Review

Jump to: Research

36 pages, 2382 KiB

Open AccessReview

Review of Artificial Intelligence-Based Failure Detection and Diagnosis Methods for Solar Photovoltaic Systems

by Ahmad Abubakar, Carlos Frederico Meschini Almeida and Matheus Gemignani

Machines 2021, 9(12), 328; https://doi.org/10.3390/machines9120328 - 1 Dec 2021

Cited by 49 | Viewed by 9851

Abstract

In recent years, the overwhelming growth of solar photovoltaics (PV) energy generation as an alternative to conventional fossil fuel generation has encouraged the search for efficient and more reliable operation and maintenance practices, since PV systems require constant maintenance for consistent generation efficiency. [...] Read more.

In recent years, the overwhelming growth of solar photovoltaics (PV) energy generation as an alternative to conventional fossil fuel generation has encouraged the search for efficient and more reliable operation and maintenance practices, since PV systems require constant maintenance for consistent generation efficiency. One option, explored recently, is artificial intelligence (AI) to replace conventional maintenance strategies. The growing importance of AI in various real-life applications, especially in solar PV applications, cannot be over-emphasized. This study presents an extensive review of AI-based methods for fault detection and diagnosis in PV systems. It explores various fault types that are common in PV systems and various AI-based fault detection and diagnosis techniques proposed in the literature. Of note, there are currently fewer literatures in this area of PV application as compared to the other areas. This is due to the fact that the topic has just recently been explored, as evident in the oldest paper we could obtain, which dates back to only about 15 years. Furthermore, the study outlines the role of AI in PV operation and maintenance, and the main contributions of the reviewed literatures. Full article

(This article belongs to the Special Issue Industrial Applications: New Solutions for the New Era)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Industrial Applications: New Solutions for the New Era

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (12 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI