PM10 and ozone are the dominant air pollutants in the Urban Kaohsiung. Ozone is a secondary pollutant generated in the troposphere from the precursors nitrogen dioxide and non-methane hydrocarbons. The trends of ozone concentrations first statistically are summarized utilizing the monitoring data during the period 1998¡Ð2007. All data are collected from four fixed-site air quality monitoring stations in Kaohsiung City. The results show that ozone concentration in Kaohsiung has one perennial peak concentration, occurring in October and March. The highest values occur in October and the secondary high value in March. The lowest values occur in the summer. The monitor data possess timeliness of data and the non-linear dynamic tendency. Artificial Neural Network ¡]ANN¡^, a system recognition, self-study function and ability of the solution to non-linearity dynamic system problem, was used as a tool to analyze these monitor data. This work utilizing neural networks develops a model to predict the trend of ozone situations in the Urban Kaohsiung. The network was trained using meteorological factor and air quality data when the ozone concentrations are the highest. The optimum set value of five parameters including date partition, hidden layer neurons, training function, leraning rate , and momentum coefficient were obtained based on trial and error methods. The simulated results of ozone concentration have a correlation coefficient within the range 0.865¡Ð0.899 and IOA within the range 0.927¡Ð0.934. The trend results of ozone concentration reflect strong relationships in all stations. The results of this study indicate that the artificial neural network (ANN) is a promising method for air pollution modeling.

none

This dissertation is to design the operation strategy and protective scheme of micro-grid systems with dispersed generation (DG). The industrial power system with cogeneration units and the distribution feeder with wind power generators were selected as the study micro-grids for computer simulation. The mathematical models of cogeneration units and wind generators were included in the computer simulation by considering the operation control modes of DGs. The micro-grid systems and the nearby utility networks were constructed to solve the power flows of the micro-grids with various operation scenarios of power generation and load demand. For the severe external fault contingencies, the micro-grids have to be isolated from the utility power system in time to prevent the tripping of critical loads and DGs. By considering the fault ride through capability of cogenerators and voltage tolerance curves of critical loads, the critical tripping time (CTT) of tie circuit breaker of the micro-grids was determined according to the transient stability analysis. To maintain the stable operation of the micro-grids after tie line tripping, the load shedding scheme was designed by applying the under frequency and under voltage relays to disconnect the proper amount of non-critical loads according to the governor responses of cogeneration units. For the micro-grid of distribution feeder with wind power generator, the STATCOM was used to provide adaptive reactive power compensation for the mitigation of voltage fluctuation due to the variation of wind speed and feeder loading. The STATCOM can also be applied for the support of terminal voltage of wind generator (WG) to enhance the transient response of the micro-grid. The CTT of tie circuit breaker was determined by considering the low voltage ride through (LVRT) capability and the critical fault cleaning time of WG. To achieve more effective islanding operation of the micro-grids, the artificial neural network (ANN) was applied to determine the proper timing for tie line tripping and the proper amount of load shedding by using the wind speed, feeder loading and the voltage of micro-grid system as the input of ANN. To verify the effectiveness of the proposed tie line tripping and load shedding scheme, different fault contingencies of the external utility network have been simulated by using the computer program for the transient stability analysis. It is found that the critical and voltage sensitive loads of the micro-grid can be maintained when the tie circuit breaker is activated to isolate the external fault in time and followed by the execution of load shedding scheme.

In the present study syngas-air diffusion flames are simulated using LES with artificial neural network (ANN) based chemical kinetics modeling and the results are compared with previous direct numerical simulation (DNS) study, which exhibits significant extinction-reignition and forms a challenging problem for ANN. The objective is to obtain speed-up in chemistry computation while still having the accuracy of stiff ODE solver. The ANN methodology is used in two ways: 1) to compute the instantaneous source term in the linear eddy mixing (LEM) subgrid combustion model used within LES framework, i.e., laminar-ANN used within LEMLES framework (LANN-LEMLES), and 2) to compute the filtered source terms directly within the LES framework, i.e., turbulent-ANN used within LES (TANN-LES), which further dicreases the computational speed. A thermo-chemical database is generated from a standalone one-dimensional LEM simulation and used to train the LANN for species source terms on grid-size of Kolmogorov scale. To train the TANN coefficients the thermo-chemical database from the standalone LEM simulation is filtered over the LES grid-size and then used for training. To evaluate the performance of the TANN methodology, the low Re test case is simulated with direct integration for chemical kinetics modeling in LEM subgrid combustion model within the LES framework (DI-LEMLES), LANN-LEMLES andTANN-LES. The TANN is generated for a low range of Ret in order to simulate the specific test case. The conditional statistics and pdfs of key scalars and the temporal evolution of the temperature and scalar dissipation rates are compared with the data extracted from DNS. Results show that the TANN-LES methodology can capture the extinction-reignition physics with reasonable accuracy compared to the DNS. Another TANN is generated for a high range of Ret expected to simulate test cases with different Re and a range of grid resolutions. The flame structure and the scalar dissipation rate statistics are analyzed to investigate success of the same TANN in simulating a range of test cases. Results show that the TANN-LES using TANN generated fora large range of Ret is capable of capturing the extinction-reignition physics with a very little loss of accuracy compared to the TANN-LES using TANN generated for the specific test case. The speed-up obtained by TANN-LES is significant compared to DI-LEMLES and LANN-LEMLES.

<p>The emerging need for dynamically scheduled real-time systems requires methods for handling transient overloads. Current methods have in common that they deal with transient overloads as they occur, which gives the real-time system limited time to react to the overload. In this work we enable new approaches to overload management. Our work shows that artificial neural networks (ANNs) can predict future transient overloads. This way the real-time system can prepare for a transient overload before it actually occurs. Even though the artificial neural network is not yet integrated into any system, the results show that ANNs are able to satisfactory distinguish different workload scenarios into those that cause future overloads from those that do not. Two ANN architectures have been evaluated, one standard feed-forward ANN and one recurrent ANN. These ANNs were trained and tested on sporadic workloads with different average arrival rates. At best the ANNs are able to predict up to 85% of the transient overloads in the test workload, while causing around 10% false alarms.</p>

<p>Admission controllers in dynamic real-time systems perform traditional schedulability tests in order to determine whether incoming tasks will meet their deadlines. These tests are computationally expensive and typically run in n * log n time where n is the number of tasks in the system. An incoming task might therefore miss its deadline while the schedulability test is being performed, when there is a heavy load on the system. In our work we evaluate a new approach for admission control in firm real-time systems. Our work shows that ANNs can be used to perform a schedulability test in order to work as an admission controller in firm real-time systems. By integrating the ANN admission controller to a real-time simulator we show that our approach provides feasible performance compared to a traditional approach. The ANNs are able to make up to 86% correct admission decisions in our simulations and the computational cost of our ANN schedulability test has a constant value independent of the load of the system. Our results also show that the computational cost of a traditional approach increases as a function of n log n where n is the number of tasks in the system.</p>

<p>This dissertation evaluates evolutionary methods for evolving cooperative teams of robots. Cooperative robotics is a challenging research area in the field of artificial intelligence. Individual and autonomous robots may by cooperation enhance their performance compared to what they can achieve separately. The challenge of cooperative robotics is that performance relies on interactions between robots. The interactions are not always fully understood, which makes the designing process of hardware and software systems complex. Robotic soccer, such as the RoboCup competitions, offers an unpredictable dynamical environment for competing robot teams that encourages research of these complexities. Instead of trying to solve these problems by designing and implement the behavior, the robots can learn how to behave by evolutionary methods. For this reason, this dissertation evaluates evolution of neural controllers for a team of two robots in a competitive soccer environment. The idea is that evolutionary methods may be a solution to the complexities of creating cooperative robots. The methods used in the experiments are influenced by research of evolutionary algorithms with single autonomous robots and on robotic soccer. The results show that robot teams can evolve to a form of cooperative behavior with simple reactive behavior by relying on self-adaptation with little supervision and human interference.</p>

<p>Artificial intelligence is a broad research area and there are many different reasons why it is interesting to study artificial intelligence. One of the main reasons is to understand how information might be represented in the human brain. The Recursive Auto Associative Memory (RAAM) is a connectionist architecture that with some success has been used for that purpose since it develops compact distributed representations for compositional structures.</p><p>A lot of extensions to the RAAM architecture have been developed through the years in order to improve the performance of RAAM; Bi coded RAAM (B-RAAM) is one of those extensions. In this work a modified B-RAAM architecture is tested and compared to RAAM regarding: Training speed, ability to learn with smaller internal representations and generalization ability. The internal representations of the two network models are also analyzed and compared. This dissertation also includes a discussion of some theoretical aspects of B-RAAM.</p><p>It is found here that the training speed for B-RAAM is considerably lower than RAAM, on the other hand, RAAM learns better with smaller internal representations and is better at generalize than B-RAAM. It is also shown that the extracted internal representation of RAAM reveals more structural information than it does for B-RAAM. This has been shown by hieratically cluster the internal representation and analyse the tree structure. In addition to this a discussion is added about the justifiability to label B-RAAM as an extension to RAAM.</p>

Includes vita. / Title from PDF of title page. / Document formatted into pages; contains 139 pages. / Thesis (Ph.D.)--University of South Florida, 1998. / Includes bibliographical references. / Text (Electronic thesis) in PDF format. / ABSTRACT: Non-recurring congestion caused by incidents is a major source of traffic delay in freeway systems. With the objective of reducing these traffic delays, traffic operation managers are focusing on detecting incident conditions and dispatching emergency management teams to the scene quickly. During the past few decades, a few number of conventional algorithms and artificial neural network models were proposed to automate the process of detecting incident conditions on freeways. These algorithms and models, known as automatic incident detection methods (AIDM), have experienced a varying degree of detection capability. Of these AIDMs, artificial neural network-based approaches have illustrated better detection performance than the conventional approaches such as filtering techniques, decision tree method, and catastrophe theory. So far, a few neural network model structures have been tested to detect freeway incidents. / ABSTRACT: Since the freeway incidents directly affect the freeway traffic flow, majority of these models have used only traffic flow variables as model inputs. However, changes in traffic flow may also be stimulated by the other features (e.g., freeway geometry) to a greater extent. Many AIDMs have also used a conventional detection rate as a performance measure to assess the detection capability. Yet the principle function of incident detection model, which is to identify whether an incident condition exists for a given traffic pattern, is not measured in its entirety by this conventional measure. In this study, new input feature sets, including freeway geometry information, were proposed for freeway incident detection. Sixteen different artificial neural network (ANN) models based on feed forward and recurrent architectures with a variety of input feature sets were developed. ANN models with single and double hidden layers were investigated for incident detection performance. / ABSTRACT: A modified form of a conventional detection rate was introduced to capture full capability of AIDMs in detecting incident patterns in the freeway traffic flow. Results of this study suggest that double hidden layer networks are better than single hidden layer networks. The study has demonstrated the potential of ANNs to improve the reliability using double layer networks when freeway geometric information is included in the model. / System requirements: World Wide Web browser and PDF reader. / Mode of access: World Wide Web.

Siemens gas turbines are monitored and controlled by a large number of sensors and actuators. Process information is stored in a database and used for offline calculations and analyses. Before storing the sensor readings, a compression algorithm checks the signal and skips the values that explain no significant change. Compression of 90 % is not unusual. Since data from the database is used for analyses and decisions are made upon results from these analyses it is important to have a system for validating the data in the database. Decisions made on false information can result in large economic losses. When this project was initiated no sensor validation system was available. In this thesis the uncertainties in measurement chains are revealed. Methods for fault detection are investigated and finally the most promising methods are put to the test. Linear relationships between redundant sensors are derived and the residuals form an influence structure allowing the faulty sensor to be isolated. Where redundant sensors are not available, a gas turbine model is utilized to state the input-output relationships so that estimates of the sensor outputs can be formed. Linear parametric models and an ANN (Artificial Neural Network) are developed to produce the estimates. Two techniques for the linear parametric models are evaluated; prediction and simulation. The residuals are also evaluated in two ways; direct evaluation against a threshold and evaluation with the CUSUM (CUmulative SUM) algorithm. The results show that sensor validation using compressed data is feasible. Faults as small as 1% of the measuring range can be detected in many cases.