Recent Advances in Intelligent Engineering


Advanced Program

9:00 - 11:302011 Honorary Professors' Talks

9:00 - 9:30Dr. Marcelo H. Ang: Robotics in Human Environments

Robotics technology and applications have evolved from Industrial Robotics to robotics in human environments, where perhaps the new revolution is taking place and the real impact of robotics becomes evident. The talk shares a critical assessment of robotics by looking at "tasks" in general and the current state of the art in robot control. Examples will be given and the talk concludes by a discussion of important challenges ahead.

9:30 - 10:00Prof. C. L. Philip Chen: Adaptive Sensor Fault Detection and Identification and Life Extending in Health Monitoring Systems

Usually, solutions to sensor validation fall into two major categories: the data-based approaches and the model-based approaches. Model-based methods include nonparametric and parametric approaches. Belonging to the first category are neural-network-bank based approaches. The non-parametric methods are more robust, but a large number of training data are needed nevertheless. On the other hand, parametric approaches, including dynamic state space models (DSSM), provide better accuracy and tracking performance without the need of training. The price paid here is the need for high fidelity real-time system models. Particle filter (PF) is an alternative name for sequential importance sampling for DSSM. PF has been commonly employed to online processing of dynamic systems described by DSSM. We will also discuss a Markov jump DSSM (MJDSSM) for system modeling and mixture Kalman filter (MKF) solution-- a unique and efficient particle filtering detector being developed.
We have modeled and calculated the probability of failure due to component damage. Using this model, a Monte Carlo simulation is also performed to evaluate the likelihood of damage accumulation under various operating conditions. Using thermal mechanical fatigue (TMF) of a critical component as an example, it has been shown that that an intelligent acceleration algorithm can drastically reduce life usage with minimum sacrifice in performance. By means of genetic search algorithms, optimal acceleration schedules can be obtained with multiple constraints. The simulation results show that an optimized acceleration schedule can provide a significant life saving in selected engine components.
The ultimate goal of engine health monitoring is to maximize the amount of meaningful information to perform diagnostics and prognostics on engine health. To achieve highest level of intelligence in different levels and aspects, in the future work, we propose to implement the concept of data fusion that integrates data from multiple sources to obtain improved accuracy and more specific results.

10:00 - 10:30Prof. Hamido Fujita: Knowledge Reasoning based on Ontologies Alignment

My talk is to present my achievement in computer Science in several paradigm that I have worked on in the past 30 years and related to new software innovation in designing software methodologies that are Patented world wide. Also, to give a short overview, on the foundational steps that I have contributed through to build several university in Japan based on new concepts in Science Practices for Education purposes that are used as main educational streams in teaching in several Scientific Universities.
Also, other main part of the talk will present a new ideas and innovation on knowledge based systems, for solving problems in decision making for medical services and others. This talk will presents several new concepts on integrating sound and images of human users for collecting different levels and types of knowledge being represented and reformed through on alignment for reasoning purposes. Such new technology becomes the platform of several running projects supported by the Japanese Government to have such system be used as Virtual Medical Doctor for medical diagnosis based on creating medical avatars that collect knowledge from user faces and voices and attribute them to knowledge-base for reasoning taken into account different ontologies represented and reflecting on user situation on different levels in aligned manner for reasoning. The talk will be not very technical but it can help audience to observe several ideas and innovations that are taken use human knowledge to build intelligent systems.

10:30 - 11:00coffee break
11:00 - 11:30Prof. Emil M. Petriu: Bio-inspired Intelligent Machines

For many centuries, engineers have built upon mathematics and natural science principles from mechanics, electricity, and chemistry in order to develop an ever growing variety of more efficient and smarter industrial artefacts and machines, including computers. The time has now arrived to add biology – and more specifically, human anatomy, physiology and psychology – to the scientific sources of knowledge for engineers to develop a new, bio-inspired, generation of intelligent machines. Advocating this emergent trend, this presentation will discuss a number of relevant issues such as humanoid robots, human-robot interaction for symbiotic partnership, bio-inspired neural networks, techniques that enhance human natural capabilities, as well as moral, ethical, theological, legal, and social challenges in a soon to come cyborg -society world.

11:30 - 12:00Prof. Tadeusz W. Wieckowski: Laboratory of Electromagnetic Compatibility at the University of Technology in Wroclaw

Laboratory of Electromagnetic Compatibility at Wroclaw University of Technology is the biggest one, where it is possible to measure electromagnetic compatibility of electric and electronic equipment, systems and installations. Electrical and electronic devices should be tested for their immunity to electromagnetic interference, as well as for the emission they send to the environment. Interferences radiated by the device in our laboratory are measured in anechoic chambers, in a measuring set-up with three loop antennas arranged perpendicularly to one another, in TEM (Transform electromagnetic) cells of Crawford type and in GTEM (Gigahertz transform electromagnetic) cells. We also employ alternative methods of emission measurements. The alternative methods of emission measurements are based on the finding that every electrical or electronic device can be represented by equivalent dipoles (electric, magnetic). In our laboratory, we employed three different set-ups for emission measurements with the use of alternative methods. The first set-up is equipped with GTEM cell. The second one is equipped with three double-loaded loop antennas placed orthogonally to each other. The third set-up is equipped with a half loop antenna. The concept of this set-up has also been prepared in my laboratory. Laboratory of electromagnetic compatibility at Wroclaw University of Technology was equipped with set ups for measurements of the immunity different devices. Immunity of the tests is divided in direct and indirect methods. Indirect methods are used particularly for such devices that involve feeders or signal lines connecting individual parts of the object. These methods consist of the injection of currents or voltages which are similar in value and shape to those that occur during exposure of the device under test to a real electromagnetic field. Direct methods are used to investigate the influence of the fields which simulate the electromagnetic field induced by transmitters, lightnings, or nuclear explosions. They are also useful in investigating the influence of current pulses which simulate the currents produced by lightnings and electrostatic discharge. For example the set-up with the GTEM cell is used for testing immunity to continuous electromagnetic field. In this set-up, the device under test is placed in an electromagnetic field of modulated amplitude and a modulating signal frequency of 1 kHz. During the test, the response of the device is measured. Measurements are run at a frequency ranging between 30 and 1000 MHz. In this set-up, we can measure only small objects. If the objects are big, then we can use anechoic chambers. In the past few years, there has been an increasing interest in electromagnetic compatibility problems. It stems from the introduction to the environment many electric and electronic equipments, systems and installations.

12:00 - 12:30IEEE SMC Distinguished Lecturer Program

Prof. William A. Gruver: Distributed Intelligent Systems: A Paradigm Shift

Centralized systems are unsuitable for large-scale systems integration because of their high reliance on centralized communication, high complexity, lack of scalability, and high cost of integration. The use of distributed intelligence technologies avoids these weaknesses by building intelligent systems with physical and software agents that operate autonomously to independently handle specialized tasks and cooperate to satisfy system-level goals and achieve a high degree of flexibility.
This lecture provides an introduction to the technologies and applications of distributed intelligent systems for dynamically changing, networked environments. It describes how a peer-to- peer environment can be built to distribute the logistical and strategic requirements of a system, while improving robustness and scalability. The presenter will contrast centralized and distributed systems, describe development frameworks for distributed systems, present recent advances based on multi-agent and holonic systems, and survey applications involving manufacturing automation, distributed scheduling, automated decision support, RFID tracking, and distributed energy systems. Specific examples and success stories of implementations in industrial environments worldwide will be provided.

12:30 - Reception