Gerson Flavio Mendes de Lima

VRCEMIG: A virtual reality system for real time control of electric substations

This research demonstration presents an integrated hardware and software platform developed for controlling electric substations, through a virtual environment. Each 3D substation is integrated with the supervision, data acquisition and control center of a real electric energy company. Today, this is pursued on a 2D diagram, lacking intuitiveness. VRCEMIG explores techniques to provide deeper immersion and intuitive interactions in order to support not only training for future employees, but also real time operation. During the demonstration visitors will be able to use different devices such as joystick, gamepad and VR glasses to navigate and operate an electric substation (for training purposes only). This substation belongs to the Brazilian company CEMIG, a research partner.

Exterior lighting computer-automated design based on multi-criteria parallel evolutionary algorithm

Multi-objective evolutionary algorithm to computer-automated exterior lighting design.Web client integrated to a cluster of computers to provide lighting design service.Solution to optimize both illumination quality and energy efficiency.Case study solution presents - 37.5% power consumption and +227.3% global uniformity. A proper professional lighting design implies in a continuous search for the best compromise between both low power consumption and better lighting quality. This search converts this design into a hard to solve multi-objective optimization problem. Evolutionary algorithms are widely used to attack that type of hard optimization problems. However, professionals could not benefit from that kind of assistance since evolutionary algorithms have been unexplored by several commercial lighting design computer-aided softwares. This work proposes a system based on evolutionary algorithms which implement a computer-automated exterior lighting design both adequate to irregular shaped areas and able to respect lighting pole positioning constraints. The desired lighting design is constructed using a cluster of computers supported by a web client, turning this application into an efficient and easy tool to reduce project cycles, increase quality of results and decrease calculation times. This ELCAutoD-EA system consists in a proposal for a parallel multi-objective evolutionary algorithm to be executed in a cluster of computers with a Java remote client. User must choose lighting pole heights, allowed lamps and fixtures, as well as the simplified blue print of the area to be illuminated, marking the sub-areas with restrictions to pole positioning. The desired average illuminance must also be informed as well as the accepted tolerance. Based on user informed data, the developed application uses a dynamic representation of variable size as a chromosome and the cluster executes the evolutionary algorithm using the Island model paradigm. Achieved solutions comply with the illumination standards requirements and have a strong commitment to lighting quality and power consumption. In the present case study, the evolved design used 37.5% less power than the reference lighting design provided by a professional and at the same time ensured a 227.3% better global lighting uniformity. A better lighting quality is achieved because the proposed system solves multi-objective optimization problems by avoiding power wastes which are often unclear to a professional lighting engineer in charge of a given project.

A Virtual Reality Based Approach to Improve Human Performance and to Minimize Safety Risks When Operating Power Electric Systems

Power systems require continuous operation for reasons of public safety, emergency management, national security and business continuity. Companies today control an electric system by means of 2D line diagrams, whereas a substation in the field is a 3D space. There exist situations where new control center operators have never been immersed into a real substation environment. When these operators visit a real electric substation, the environment is at minimum ‘strange’. This fact unquestionably reduces human performance when it comes to operating the electrical system, since a great deal of mental effort is required by the operator to associate both 2D and 3D worlds. There are situations where some modifications and replacements have to be executed within the real substation environment. Hence, to design such procedures on the 2D line diagram does not adequately reflect the reality of the field. For example, it is impossible, in this 2D scenario, to design the route taken by a truck carrying a huge electric component. In this case, safety factors also arise and need to be given due attention. It is important to seek new alternatives to ensure that systems are designed in a manner as to optimize human performance and minimizes risks, thus producing higher productivity, health and safety in the work place and safety in work processes. On the other hand, Virtual Reality (VR) is known as providing “the feeling of being there”. With the features provided by VR, it is possible to simulate all real operations of an electric substation with such precision that it has bearing on real world environments. For this reason, this paper proposes a Virtual Reality approach for the simulation, training and control of electric substations. In this approach, a virtual substation is realistically replicated according to its dimensions, using electric component data sheets, pictures, videos and floor plans. This is relevant as safety rules state that the distance between electrical components must be taken into account. Next, by means of a web service, data from a supervisory system is allocated to each component in the virtual substation, so the operator can attain access to all the information required for possible intervention, as is the case in real life. It is believed that all the features explored in this work have the capacity to increase human performance when operating a power electric substation.

Green public lighting design solved by a remote Genetic Algorithm application

Lighting Design is a field of engineering that often misses artificial intelligence tools and computational approaches to help designers. Genetic Algorithm (GA) is a widely used heuristic for search and optimization. This work presents results from applying GA and Web services to develop a computer-generated public lighting design remote application. This application is hosted in a cluster computing environment that supports Web services. A case study is also presented: the achieved solution shows a superior uniformity of illumination with almost 20% of economy on monthly power consumption when compared to the previous edified one.

A TEO-Based Algorithm to Detect Events Over OTDR Measurements in FTTH PON Networks

The FTTH business needs new network maintenance technologies that can, economically and effectively, cope with the massive FTTH fiber plants that are yet to come. Based on the Teager Energy Operator (TEO), we have developed a method for testing and evaluating FTTH networks from the Central Office, which allows the identification of event failures in the optical branches after the PON splitter.

Associating Holography Techniques with BIM Practices for Electrical Substation Design

The emerging of BIM (Building Information Modeling) techniques will change traditional procedures of design and maintenance for electric substations. In addition, Computational Holography, supported by wearable computers, has the potential to allow simultaneous engineering work, based on mixed reality and computer vision capabilities. It is believed that this set of tools will increase engineering design decisions. In this work, we propose a set of techniques to support a complete substation design, which is created by using BIM concepts that explore the Holographic world benefices. Experiments have shown that the coupling of these techniques has the potential to reduce the learning curve of the users, since it changes the way of collaboration among different professional specialists considering simulation intents.

VRCEMIG: a novel approach to power substation control

In this work, we propose a Virtual Reality based solution to provide a more natural and intuitive environment for controlling electrical operation centers. The research is being carried out with the collaboration of one electric company called Cemig. The novelty of this approach is the ability operators will have to manage the electric system and its electric components by being immersed within a 3D world, reflecting the very true arrangement found in the real electrical substation. Besides, the solution has been designed in a way to provide the operator with all supervisory data in the same virtual environment. We have conducted experiments with the electric company operators Mental efforts to understand the reality of the field have been reduced, according to Cemigs employees. They also claim that a unique environment with all data integrated is very important for taking engineering decisions.

A methodology for reducing the time necessary to generate virtual electric substations

In this work, an electric power energy utility company, called CEMIG, is a research partner with more than 50 electric substations, whose operation can be improved by using virtual environments. Therefore, time to model all these substations, with a high-level of required photorealism, is a critical issue. To achieve this goal, this paper presents a pertinent and appropriate methodology. First, data is retrieved from field components (CADs, satellite images, manufacturer sheets etc.) to model suitable electric components by means of dimensioning and angles. Next, rules such as cable connectors positioning and monitoring of the quantity of polygons (low-poly) are established. In addition, since each electric substation has circuit arrangements composed of different electric components, a pattern recognition tool is applied to extract information from 2D basic plants in order to generate automatic positioning of components within a virtual substation. Also, considering the need for control and monitoring of the electric system, in real time, a set of interface templates are provided to support direct access to data from supervisory system (SCADA), without the loss of immersion and navigation which are imperative for Virtual Reality applications. In the very first trials used for generating a virtual electric substation a lot of work and time was spent by our research team. After the establishment of the proposed methodology, results show that the time to generate new substations was reduced by the order of 83%.

A Statistical Scheme to Support Performance Comparisons between Different Designs of Evolutionary Algorithms

Evolutionary algorithms are stochastic heuristics which can optimize over special functions, known as fitness functions, by manipulating the structure of candidate solutions known as individuals. Multi-objective evolutionary algorithms can deal with many objectives to be optimized, whether concurrent or divergent, ending by returning an optimal frontier, i.e. a set of solutions all defined as Pareto optimal. The idea behind using evolutionary algorithms to perform computer automated design is to be able to formulate a fitness function that, starting from a candidate solution, could reflect the impact the evaluated individual has on those objectives to be optimized. The case study presented in this work is an application for computer automated exterior lighting design which has some concurrent objectives to be optimized: the energy efficiency and the illumination quality. This work investigates four metrics to illumination quality and two metrics for energy efficiency as possible proposals to the fitness function formulation. Eight variations were designed as combinations of pairs from those metrics. To help in the decision process, the statistical hypothesis test known as difference of means is then used to enable comparisons between those variations. This test is performed two by two and three decision matrices is then derived, the ones about global uniformity, mean electrical power, and mean efficiency class index. The concept of Paretos “statistical dominance”, defined in this work and based on statistical evidences, indicates a final decision about which one from the previous designed variations of fitness function is the more appropriated for the presented problem.

A Robust TEO-Based Speech Segmentation Method For Automatic Speech Recognition

Based on the Teager Energy Operator (TEO), the “TEO-based method for Spoken Word Segmentation” (TSWS) is presented and compared with two widely used speech segmentation methods: “Classical”, that uses energy and zero-crossing rate computations, and “Bottom-up”, based on the concepts of adaptive level equalization, energy pulse detection and endpoint ordering. The implemented Automatic Speech Recognition (ASR) system uses Mel-frequency Cepstral Coefficients (MFCC) as the parametric representation of the speech signal, and a standard multilayer feed-forward network (MLP) as the recognizer. A database of 17 different words was used, with a total of 3,519 utterances from 69 different speakers. Two in three of those utterances constituted the training set for the MLP, and one in three, the testing set. The tests were conducted for each of the TSWS, Classical or Bottom-up methods, used in the ASR speech segmentation stage. TSWS has enabled the ASR to achieve 99.0% of success on generalization tests, against 98.6% for Classical and Bottom-up methods. After, a white Gaussian noise was artificially added to the ASR inputs to reach a signal-to-noise ratio of 15dB. The noise presence alters the ASR performances to 96.5%, 93.6%, and 91.4% on generalization tests when using TSWS, Classical and Bottom-up methods, respectively.