Papers by Ragu Athinarayanan
MODAPTS and Human Data Simulation
SAE Technical Paper Series, 2000
To achieve optimal operational capabilities across the manufacturing value chain by leveraging th... more To achieve optimal operational capabilities across the manufacturing value chain by leveraging the sensor networks and the IoT platform connecting activities at the Machine-, Factory-, and Enterprise-levels. • Enterprise-Level CPS-"Horizontally Integrated" Cyber Physical Systems (CPS) connecting Machine-, Factory-(MES & FEMS), and Enterprise-level operations (ERP) that are managed and optimized using a network of intelligent systems and IoT devices that collect and share data over the Cloud & Edge • Factory-Level CPS-"Vertically Integrated" Factory-level operations such as product development, production planning, process control, quality control, facility management and logistics management managed and optimized using a network of intelligent systems and IoT devices that collect and share data over the Cloud & Edge. • Machine-Level CPS-Management of Machine-level operations achieved through the automation of critical machine functions using digital twin and machine learning.
A Sustainability Framework for Smart Learning Factories Based on Using Structured Information as Semantic Models
Social Science Research Network, 2022
To achieve optimal operational capabilities across the manufacturing value chain by leveraging th... more To achieve optimal operational capabilities across the manufacturing value chain by leveraging the sensor networks and the IoT platform connecting activities at the Machine-, Factory-, and Enterprise-levels. • Enterprise-Level CPS-"Horizontally Integrated" Cyber Physical Systems (CPS) connecting Machine-, Factory-(MES & FEMS), and Enterprise-level operations (ERP) that are managed and optimized using a network of intelligent systems and IoT devices that collect and share data over the Cloud & Edge • Factory-Level CPS-"Vertically Integrated" Factory-level operations such as product development, production planning, process control, quality control, facility management and logistics management managed and optimized using a network of intelligent systems and IoT devices that collect and share data over the Cloud & Edge. • Machine-Level CPS-Management of Machine-level operations achieved through the automation of critical machine functions using digital twin and machine learning.
This paper focuses on the implementation of the integrated laboratory using identified equipments... more This paper focuses on the implementation of the integrated laboratory using identified equipments and elaborate how it can provide students an integrated network environment where traditional telephone network, VoIP, data network and backbone fiber optic network coexist with data, voice and video traffic. Our preliminary study indicates that our students show much more interest in working in such a lab environment. No matter what individual course they are taking, the students can always see a big picture of the network, which shows great resemblance of the real world Internet and applications. In the meanwhile, more research work, such as the topics require a mixed type network and traffic, can be conducted conveniently.
Procedia Manufacturing, 2020
This project demonstrates the application of Artificial Intelligence (AI) and machine vision for ... more This project demonstrates the application of Artificial Intelligence (AI) and machine vision for the identification of Personal Protective Equipment (PPE), particularly safety glasses in zones of the Learning Factory, where safety risks exist. The objective is to design and implement an automated system for ensuring the safety of personnel when they are in the vicinity of machinery that presents potential risks to the eyes. Microsoft Azure Custom Vision AI and Intelligent AI Services, in conjunction with low-cost vision devices with lightweight onboard AI capability, provide a platform for a deep learning neural network model using publicly available images under the Creative Commons License. A combination of cloud-based and on-premises AI is used in this proof of concept system to provide a real-time vision-based safety system capable of detecting and recording potential safety breaches, promoting compliance, and ultimately preventing accidents before they happen. This system can be used to initiate different control actions in the event of safety violations and can detect multiple forms of protective wear. The flexibility of the system offers multiple benefits to learning factories and manufacturing organizations such as improved user safety, reduced insurance costs, and better detection and recording of safety violations. The hybrid AI architecture approach allows for flexibility in training and deployment based on the capability of local computing resources.
2008 Annual Conference & Exposition Proceedings
She received her Ph.D. degree from the University of Pittsburgh. Her current teaching and researc... more She received her Ph.D. degree from the University of Pittsburgh. Her current teaching and research interests include telecommunications and computer networking, IP and overlay multicast, system design and analysis, and wireless ad hoc networks.
2011 ASEE Annual Conference & Exposition Proceedings
He received his PhD in Engineering Science (Electrical Engineering Concentration) from Southern I... more He received his PhD in Engineering Science (Electrical Engineering Concentration) from Southern Illinois University. He is also the Associate Dean of the School of Polytechnic Studies. His research interests include modeling and control of underactuated robotic manipulators, self organizing systems, and machine vision. He received "2009 Governors Award for Excellence in Education" and "SME 2002 Educator of the Year Award".
Procedia Manufacturing, 2019
Procedia Manufacturing, 2019
Under the concept of "Industry 4.0", production processes will be pushed to be increasingly inter... more Under the concept of "Industry 4.0", production processes will be pushed to be increasingly interconnected, information based on a real time basis and, necessarily, much more efficient. In this context, capacity optimization goes beyond the traditional aim of capacity maximization, contributing also for organization's profitability and value. Indeed, lean management and continuous improvement approaches suggest capacity optimization instead of maximization. The study of capacity optimization and costing models is an important research topic that deserves contributions from both the practical and theoretical perspectives. This paper presents and discusses a mathematical model for capacity management based on different costing models (ABC and TDABC). A generic model has been developed and it was used to analyze idle capacity and to design strategies towards the maximization of organization's value. The trade-off capacity maximization vs operational efficiency is highlighted and it is shown that capacity optimization might hide operational inefficiency.
Procedia - Social and Behavioral Sciences, 2013
The development of a scholarly model of technology leadership necessitates a global component for... more The development of a scholarly model of technology leadership necessitates a global component for the modern technology and technology education organization. The authors conduct qualitative research of four key concepts around globalization and innovation Via a process of on-site visits for observation and face-to-face interviews with both academic and industry organizations in multiple countries, participant scholars utilized ethnographic research methods (Lindlof & Taylor, 2002) to gather detailed qualitative data on the development and status of implementing technology innovation and global technology leadership strategies. Results of content analysis conducted manually and via NVivo qualitative data analysis software revealed bifurcation in programmatic approaches and conceptualizations on these topics between established and relatively younger higher educational programs, as well as critical considerations in industry-academic partnerships and the role of leadership and management scientific training in higher education.
A dynamical system approach to classification and recognition of analog input information
This dissertation focusses on the design of an adaptive dynamical system for use in an unsupervis... more This dissertation focusses on the design of an adaptive dynamical system for use in an unsupervised environment for pattern recognition and classification of analog input information. In particular the goal of this work is to develop a dynamical system by which the processes of recognition and classification of pattern information is controlled by a set of dynamics, namely the recall and the encoding dynamics. The proposed method circumvents the need for rule based decisions found in most conventional algorithms. Its other salient features include its capacity to couple the dynamical characteristics of Grossberg's adaptive resonance theory, Kohonen's feature mapping, and Hopfield's content addressable memory dynamics into a single system. Among its primary advantages include its unlimited memory capacity for storage and recall of pattern information, and the convergence of the system dynamics to a fixed given finite set of limit points, therefore generation of spurious l...
The Relevance of Concurrent Engineering in Industrial Technology Programs
Carbondale, all in electrical engineering. He is currently assistant professor in Electrical Engi... more Carbondale, all in electrical engineering. He is currently assistant professor in Electrical Engineering Technology at Northern Illinois University (NIU). His area of specialization is digital systems and industrial controls. He has developed and delivered numerous courses in these areas for both industry and academia. Dr. Athinarayanan's research has been published in various professional journals and he has delivered presentations at both national and international conferences. He recently received the " Faculty of the Year " award from NIU's College of Engineering and Engineering Technology.
This study presents a linearization technique for transducers by using software solutions program... more This study presents a linearization technique for transducers by using software solutions programmed into a microcontroller. Existing data acquisition systems linearize nonlinear transducer characteristics in real time using analog linearizing circuitry, which are susceptible to errors due fluctuations in power supply voltage, temperature, and interference from correlated and uncorrelated noise sources in the system. The goal of this work is to replace analog hardware techniques for linearization using software solutions provided by microcontrollers, which also has inherent capabilities for performing signal conditioning and data acquisition among others. The methodology for linearization is the piecewise- linear software approximation technique using the one-sixth and five-sixth operating points on each segment, and results show an improvement over the end point approximations. This technique is successfully used in an existing microcontroller to monitor the temperature of a microw...
A Collaboratively Developed Platform to Introduce Fundamentals of IoT and IIoT
SSRN Electronic Journal
New Design and Control of Precise Piezoelectric Robots with Active Multi-Degree of Freedom Kinematic Pairs
This work features the design and a control scheme for an active multi-degree of freedom kinemati... more This work features the design and a control scheme for an active multi-degree of freedom kinematic pair piezoelectric robot manipulator. The objective is to design a lightweight, fault-tolerant, and energy efficient underactuated precision micromanipulator whereby only one joint of the robot is fitted with an actuator. We propose a robot design that uses active multi-degree-of-freedom kinematic pairs, constructed using piezoelectric materials to increase the precision of positioning micromanipulators in robot joint space. The piezoelectric material offers a lightweight, high resolution, and a low time constant operation as required by the specific manipulator applications. Positioning of the manipulator is achieved by controlling the high frequency resonant mechanical oscillation of the piezoelectric material in the contact zone of the kinematic pairs, and the dynamic coupling forces generated from the single actuated joint mounted in the base of the robot. We propose a sequential c...
A biologically based competition model for self-organizing neural networks
SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218), 1998
This work presents the design of an unsupervised neural network system, CSNN (competitive self-or... more This work presents the design of an unsupervised neural network system, CSNN (competitive self-organizing neural network), for pattern recognition and classification. The CSNN model is based on a system of ordinary differential equations, motivated by Volterra and Lotka's models of interacting species in biology. The CSNN features a continuous time system dynamics that is free of auxiliary control mechanisms, complex
<title>Generating good design from bad design: dynamical network approach</title>
Applications of Optical Engineering: Proceedings of OE/Midwest '90, 1991
ABSTRACT This paper discusses a dynamical network for mapping of interciass members without perfo... more ABSTRACT This paper discusses a dynamical network for mapping of interciass members without performing a learning process. This allows a member of class A to be mapped to a member of class B. Given sample members of each class a backpropagation network is trained to form the corresponding class boundaries. Upon completion of the training process the weights obtained are used in a recurrent network which performs the interclass member mapping without any further training. This mapping is achieved as the recurrent network evolves In time. The Initial state of the network is mapped to its equilibrium state. The interclass member mapping network (IMMN) has many applications in selfcorrecting systems. In this paper the IMMN is developed to represent two classes namely class B (for instance a class for representing members with desirable and correct features) and class A (members with incorrect features). An example is given in which two categories are used namely poorly and well-designed manufacturing parts. Given a poorly-designed part the network wifi suggest corrections resulting in a well-designed part. This example has nonlinear decision regions and shows the generalization capability of the network.
Image texture segmentation using a neural network
In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to seg... more In this paper we use a neural network called the Lyapunov associative memory (LYAM) system to segment image texture into different categories or clusters. The LYAM system is constructed by a set of ordinary differential equations which are simulated on a digital computer. The clustering can be achieved by using a single tuning parameter in the simplest model. Pattern classes
A Software Linearization Technique Using Embedded Applications for Measuring Microwave Dielectric Response of Materials
Uploads
Papers by Ragu Athinarayanan