检索结果-内蒙古大学图书馆

14th International Conference on Information Society and Technology, ICIST 2024

作者： da Rocha, Luiz Gustavo Schitz Rudek, Marcelo Pontifical Catholic University of Parana PUCPR Production and System Engineering Graduate Program – PPGEPS Curitiba Brazil

ISBN: (纸本)9783031714184

This paper proposes a solution for markerless gait analysis based on point cloud data, which are three-dimensional data obtained by sensors such as LiDAR, that can capture body movements in real-time and in various environments. Gait analysis aims to evaluate the differences in symmetry between the left and right sides of the body, which can indicate diseases such as Parkinson’s and Alzheimer’s. The point cloud is a sparse matrix with N points in 3D space and the intensity of reflected light, which does not have an ordering between the points and the minimum distance between them is responsible for the density of the cloud. In the proposed method the point cloud is transformed into voxels, which are cubic units that facilitate data processing, and each set of points in the voxel is used for person detection. The points of the person are used to segment the body parts, and each part is used to estimate the joint position. The joint position is used to construct a rigid body model, where a person is represented by their segments. The rotations and translations of the segment over time are used to build the gait analysis graph. By comparing the rotation of each segment over time, it is possible to calculate the difference between the left and right sides and detect at what moment of the movement the difference is large enough to indicate the onset of pathology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Multiobjective Robust PI Synthesis in Plants with Uncertain Poles

引用

IFAC-PapersOnLine 2024年第7期58卷 174-179页

作者： Ricardo Massao Kagami Roberto Zanetti Freire Gilberto Reynoso-Meza Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifícia Universidade Católica do Paraná (PUCPR) Brazil Industrial and Systems Engineering Graduate Program (PPGEPS) Universidade Tecnológica Federal do Paraná (UTFPR) Brazil Control Systems Optimization Laboratory (LOSC) PUCPR Brazil

The use of multiobjective optimization procedures for control tuning has been constantly explored, presenting satisfactory results, and generating significant contributions to control engineering. In this way, the field of robust control can benefit significantly from the integration of multiobjective optimization design procedures for robust Proportional-Integral-Derivative (RPID) controller synthesis, enabling innovative solutions to complex control challenges. Due to this fact, this paper explores an approach to utilize multiobjective optimization algorithms in a simplified procedure, considering uncertain systems in the form of interval plants with uncertain poles, the Kharitonov theorem is used to obtain a region of stability as search space for the multiobjective algorithm, being the optimization process performed over a nominal system model. Two numerical cases and a flexible actuator model were used to demonstrate the procedure for RPI synthesis, resulting in robustly stable controllers with optimized performance over error and control signal effort measures.

关键词： Robust control multiobjective optimization robust stability Kharitonov theorem PI controller

来源：评论

学校读者我要写书评

暂无评论

Framework for Automated Synthetic Image Generation for Vehicle Detection 23

Framework for Automated Synthetic Image Generation for Vehic...

引用

Proceedings of the 2023 6th International Conference on Sensors, Signal and Image Processing

作者： Vitória Biz Cecchetti Bruno José Souza Roberto Zanetti Freire Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Brazil and Pumatronix Electronic Equipment Ltd. Brazil Industrial and Systems Engineering Graduate Program (PPGEPS) Universidade Tecnológica Federal do Paraná (UTFPR) Brazil

ISBN: (纸本)9798400707995

The use of synthetic images has been highlighted within the computer vision field as a more practical option that helps reduce the time and cost spent on vehicle detection tasks in urban environments. This paper presents a framework for automated synthetic image generation, aiming at the detection of vehicles in urban environments. The creation of the 3D scenario is carried out through the Blender software. Some adverse conditions of the scenes were developed, including: rain, fog, occlusion by tree branches and electrical power lines, and low lighting. Then the algorithm for the automated generation of images was developed based on parameters chosen by the user to generate the scene and to generate the annotations of the images. Additionally, a convolutional neural network with YOLOv5 architecture along with a cross-validation technique was applied to carry out vehicle detections on the developed synthetic dataset, on both real and mixed datasets. The proposed framework generated a consistent dataset that can be used in vehicle detection networks, obtaining a mAP 0.5 above 96% and mAP 0.5:0.95 above 82%, also the precision values remained above 92%, and recall above 95%. It was also observed that the combination of synthetic images with real images can improve the performance of the model.

关键词： Computer vision Convolutional neural networks Object detection Synthetic images Vehicle detection.

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Data Driven for Cyber-Physical production systems in the Aerospace Industry: Current Issues and Emergent Technologies

引用

IFAC-PapersOnLine 2024年第19期58卷 1162-1167页

作者： Murillo Skrzek Anderson L. Szejka Fernando Mas Maria Jose Escalona Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil University of Seville (US) Seville Spain CT Engineering Group Spain

The aerospace manufacturing industry exhibits significant complexity in all its tasks. For instance, the aircraft’s main body comprises several components with multiple dimensions, geometries, and materials. This kind of manufacturing system is specialised in creating aerospace parts characterised by advanced technology, limited production quantities, and a high degree of customisation. The aerospace products and the corresponding manufacturing systems have extensive life cycles spanning decades and are repurposed to accommodate product variations. Any disturbance during the project progression has the potential to result in escalated expenses and time investments, leaving economic and environmental drivers. In this way, Cyber-Physical production systems (CPPS) are emerging to reduce misinterpretation and mistakes across all stages of the manufacturing process. Therefore, the main aim of this paper is to discuss the current issues and emergent technologies across the literature review to address the following Research Issue 1 (RI1): What are the current issues and emergent technologies in CPPS and KDD for the Aerospace Industry? Research Issue 2 (RI2): What is the gap in CPPS and KDD for the aerospace industry? This initial literature review is concentrated on the Knowledge data-driven (KDD) to aid in developing CPPS for Aerospace Sheet Metal (ASM) parts manufacturing and examining the use of CPPS in the aerospace sector. Finally, this research contributes to the research community with an initial overview of research trends in the domain of KDD for CPPS in the aerospace industry and finds the main research gaps in this area.

关键词： Knowledge data-driven Cyber-Physical production System Aerospace Industry Content Analysis

来源：评论

学校读者我要写书评

暂无评论

In the Search for the Balance Between Real and Synthetic Images in Multi-Class Detection systems

In the Search for the Balance Between Real and Synthetic Ima...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Vitória Biz Cecchetti Marcelo Rudek Roberto Z. Freire Industrial and Systems Engineering Pontifical Catholic University of Parana (PUCPR - PPGEPS) Curitiba Brazil Industrial and Systems Engineering Graduate Program (PPGEPS) Universidade Tecnoló gica Federal do Paraná (UTFPR) Curitiba Brazil

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

Intelligent systems focused on traffic management have been in evidence in recent years, and applications related to vehicle detection and tracking, speed estimation, and traffic flow identification have become an interesting research topic. For the previously mentioned tasks, a large number of data has to be gathered to train deep learning algorithms, but collecting that data can be a time and resource-consuming task. Therefore, the use of synthetic data has become a viable option that helps to minimize data acquisition problems, but when misused, it can negatively impact the model's quality. This paper presents a systematic literature review based on the use of synthetic images to train object detection models in urban scenarios, aiming at identifying the ideal ratio between real and synthetic images that can benefit those models and the best methods to produce synthetic images. This study identified that there is no consensus on the number of synthetic images that can help to generate a more accurate model, due to the low number of papers addressing this relationship, however, it was noted that the use of generative adversarial networks (GANs) can create synthetic images that are more similar to real images, bringing benefits for training detection models, although without identifying how the use of images generated by this method can help in the relationship between synthetic and real.

关键词： Training Analytical models Accuracy Vehicle detection Object detection Generative adversarial networks Data models

来源：评论

学校读者我要写书评

暂无评论

Controller tuning with multi-objective optimization: benchmark definitions for SISO linear systems: A PI controller case ⁎

引用

IFAC-PapersOnLine 2024年第7期58卷 126-131页

作者： Gilberto Reynoso-Meza Ricardo Massao Kagami Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná (PUCPR) Control Systems Optimization Laboratory (LOSC) Pontifícia Universidade Católica do Paraná (PUCPR)

Multi-objective optimization techniques are practical techniques for controller tuning purposes. A wide variety of papers use such an approach or propose new algorithms to approximate the Pareto front. Nevertheless, despite the expressive volume of works dealing with it, there is no standard benchmark testbed that could be used as a baseline comparison among different techniques. This work addresses such a gap, with a first step proposing a linear-SISO testbed with guidelines and rules and providing a basic example for a PI controller. Such a benchmark is expected to promote further research on the topic.

关键词： Multi-objective optimization Parametric optimization Evolutionary Algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Grey Wolf Optimizer for the Tuning Process of the FOPID Controller

Multi-Objective Grey Wolf Optimizer for the Tuning Process o...

引用

IEEE/IAS International Conference on Industry Applications (INDUSCON)

作者： Allan Christian Krainski Ferrari Gideon Villar Leandro Leandro Dos Santos Coelho Gilberto Reynoso Meza Eletrical Engineering Department Federal University of Paraná UFPR Curitiba Brazil Electrical Engineering Graduate Program (PPGEE) Federal University of Paraná (UFPR) Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná (PUCPR) Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Paraná Curitiba Brazil

This article implements the multi-objective grey wolf optimizer (MOGWO) in the tuning process of the gains of the Fractional-Order Proportional-Integral-Derivative (FOPID) controller applied in the control of a boiler system. For a sequence of 100 runs, this application had compared and analyzed with other implementation that uses MOGWO to optimize the gains of the classical Proportional-Integral-Derivative (PID) controller. In the computational simulation, the value hypervolume metric had used to analyze the performance of the controllers. In the results, the implementation of the FOPID showed superior to PID, where the comparison had validated by a hypothesis test. Despite the higher computational cost concerning the tuning process of the PID controller, this study proved that the FOPID controller can be advantageous for industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards a smart reconfiguration process for complex product manufacturing based on industrial robot cells

引用

IFAC-PapersOnLine 2022年第2期55卷 108-113页

作者： Murillo Skrzek Leandro L. da Silva Anderson L. Szejka Industrial and Systems Engineering Graduate Program (PPGEPS) Pontifical Catholic University of Parana (PUCPR) Curitiba Brazil

The cost for companies that can custom their production line with precision and quality, through machining centres and laser cutting machines, is expensive, as the degree of machining freedom increases. Furthermore, the greater the complexity of the product to be manufactured, the more processes and equipment are needed to manufacture it. In this context, this research proposes a smart reconfiguration process for complex product manufacturing, based on industrial robotic manipulators, with 6 or more degrees of freedom, superior to conventional methods. With the integration of SolidWorks and PowerMill software, it was possible to apply the solution in an experimental case of blisk manufacturing milling and laser cutting of an engine head gasket. With CAD, CAM and robot simulation by the PowerMill tool, it was possible to validate the proposed solution, obtaining process data and information of milling and laser cutting. With the analysis of the simulation results, it was possible to identify the limitations of the project, such as (i) restriction in the precision of the machining of the product; (ii) amount of real-time supervision and monitoring information; and (iii) work area limit. However, the project can integrate two manufacturing processes to machine and cut complex parts with flexibility.

关键词： Robotic manipulator Milling Laser Cutting Reconfigurable Manufacturing systems Complex Product Computer-Aided Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Recommendation System for Detecting and Diagnosing Broken Bars in Induction Motors Under Transient Operation

引用

IFAC-PapersOnLine 2024年第19期58卷 1156-1161页

作者： Narco A.R. Maciejewski Roberto Z. Freire Anderson L. Szejka Thiago P.M. Bazzo Sofia M.A. Lopes Rogério A. Flauzino Department of Electrical Engineering - DAELT-CT Universidade Tecnológica Federal do Paraná - UTFPR Curitiba PR 80230-90 Brazil Production and Systems Engineering - PPGEPS-PB Energy Systems - PPGSE-CT Industrial and Systems Engineering Graduate Program - PPGEPS Pontifical Catholic University of Parana - PUCPR Curitiba PR 80215-901 Brazil Electrical Engineering - PPGEE-SC São Carlos School of Engineering - EESC Universidade de São Paulo - USP São Carlos SP 13566-590 Brazil

Three-phase induction motors are the main elements for converting electrical energy into mechanical energy and are extensively used in industry. Reducing maintenance costs becomes an incentive for developing systems capable of identifying defects. This research proposes a framework for recommending machine learning algorithms that diagnose and detect broken bar defects in three-phase induction motors under transient operation based on artificial intelligence. Employing experimental data, features were extracted and selected based on current, voltage, and vibration. A protocol of insertion of white noise showed that the proposed framework admitted 80% of noise without losing the predictive capacity based on a multicriteria performance measure.

关键词： condition monitoring fault detection fault classification machine learning maintenance engineering smart systems three-phase induction motor

来源：评论

学校读者我要写书评

暂无评论

Towards an integrated MCDM and BSC method to support the digital transformation strategy in railway companies 28

Towards an integrated MCDM and BSC method to support the dig...

引用

28th ISTE International Conference on Transdisciplinary engineering, TE 2021

作者： Zanon, Gabriel Nogueira Szejka, Anderson Luis De Freitas Rocha Loures, Eduardo Industrial and Systems Engineering Graduate Program - PPGEPS Pontifical Catholic University of Paraná - PUCPR Curitiba Brazil

ISBN: (纸本)9781643682082

Digital transformation is now widely discussed and applied in different enterprises and under various organizational aspects. Traditional industries recognize the need to innovate and digitalize their business processes and models. Among these industries, the railway sector presents a vast space for digital transformation. The railway has several operational, regulatory, regional and technological specificities that must be taken into account in the digitalization processes. Given the multiple aspects involved and the transdisciplinarity, the digital transformation strategy and roadmap of companies must be defined in a way that fits it to the corporate strategy, allowing digital transformation program to be implemented effectively, prioritizing internal sectors with the greatest strategic impact, generating greater productivity, business models improvement, security and, above all, competitiveness for the sector. This research aims to propose a model for the definition of the digital transformation strategy in the railway companies using the Balanced Scorecard (BSC) as a tool for strategic organizational analysis and multi-criteria decision-making (MCDM) to define the drivers for digital transformation in the railway. Finally, to demonstrate the proposal, a case study will be carried out at a Brazilian railway company. © 2021 The authors and IOS Press.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：