[Show abstract][Hide abstract] ABSTRACT: In this paper, a fast target maneuver detection technique and high accu-rate tracking scheme is proposed with the use of a new hybrid Kalman filter-fuzzy logic architecture. Due to the stressful environment of target tracking problem such as inac-curate detection and target maneuver, most of existing trackers do not represent desired performance in different situations. In practice, while the conventional Kalman filters (KF) perform well in tracking a target with constant velocity, their performance may be seriously degraded in the presence of maneuver. To reach an accurate target track-ing system in such a stressful environment, fuzzy logic-based algorithms with intelligent adaptation capabilities have recently been issued. Although these methods yield reasonable performance in tracking maneuvering targets, their accuracy in non-maneuvering mode was not satisfactory. In this research, based on information about the target maneuver dynamics, a new hybrid tracker (HT) is introduced. The proposed algorithm combines two methodologies into one architecture synergistically. In other words, the KF is used when the target velocity is approximately constant, whereas fuzzy estimator is used when the target maneuvers. Simulation results show that the proposed method is superior to some conventional approaches in tracking accuracy.
International Journal of Innovative Computing. 03/2011; 2:501-510.
[Show abstract][Hide abstract] ABSTRACT: The deregulation of electric power supply industries has raised many challenging problems. One of the most important ones is forecasting the market clearing price (MCP) of electricity. Decisions on various issues, such as to buy or sell electricity and to offer a transaction to the market, require accurate knowledge of the MCP. Another problem, which has also been an important issue of the traditional power systems, is load forecasting for both short and long terms. In this paper, a new forecasting method is introduced to predict the next day electricity price and load. The proposed method is based on cooperative co-evolutionary (Co-Co) approach and has been applied to the real power market. Most of the conventional forecasting methods are based on a single neural network prediction. These methods might misrepresent parts of the input–output data mapping that could have been correctly represented by cooperation of multiple networks. In this paper, a new Co-Co adaptive algorithm with adjustable connections in a recursive procedure is proposed. The obtained results show significant improvement in both price and load forecasting.
International Journal of Electrical Power & Energy Systems. 06/2010;
[Show abstract][Hide abstract] ABSTRACT: The two-stage filtering methods, such as the wellknown augmented state Kalman estimator (AUSKE) and the optimal two-stage Kalman estimator (OTSKE), suffer from some major drawbacks. These drawbacks stem from assuming constant acceleration and assuming the input term is observable from the measurement equation. In addition, these methodologies are usually computationally expensive. The innovative optimal partitioned state Kalman estimator (OPSKE) developed to overcome these drawbacks of traditional methodologies. In this paper, we compare performance of the OPSKE with the OTSKE and the AUSKE in the maneuvering target tracking (MTT) problem. We provide some analytic results to demonstrate the computational advantages of the OPSKE.
[Show abstract][Hide abstract] ABSTRACT: A new general two-stage algorithm was originally proposed to reduce the computational effort of the augmented state Kalman estimator. The conventional input estimation techniques assume constant input level and there are not covered a generalized input modeling. In this paper an innovative scheme is developed to overcome these drawbacks by using a new partitioned input dynamic modeling. In addition, authors propose a modified two-stage Kalman estimator with a new structure, which is an extension of the conventional input estimation techniques and is optimal for general, linear discrete-time systems.
[Show abstract][Hide abstract] ABSTRACT: A new input estimation (IE) model for problems in tracking manoeuvring targets is proposed. The proposed model is constructed by combining the two models of uncertainties, Bayesian and Fisher. The conventional model, which describes targets with manoeuvre, is based on the state vector of target position and velocity. The acceleration is treated as an additive input term in the corresponding state equation. The proposed method is a Kalman filter-based tracking scheme with the IE approach. The proposed model is a special augmentation in the state-space model which considers both the state vector and the unknown input vector as a new augmented state vector. In the proposed scheme, the original state and acceleration vectors are estimated simultaneously with a standard Kalman filter. The proposed tracking algorithm operates in both the non-manoeuvring and the manoeuvring modes and the manoeuvre detection procedure is eliminated. The theoretical development is verified by simulation results, which also contain some examples of tracking typical target manoeuvres. The results are compared with a traditional IE method. A comparison based on the Monte-Carlo simulation is also made to evaluate the performances of the proposed method in three scenarios: low, medium and high manoeuvring target.
IET Radar Sonar ? Navigation 03/2009; · 0.92 Impact Factor
[Show abstract][Hide abstract] ABSTRACT: A new general two-stage algorithm which extends the target dynamic model to higher order time-derivatives of acceleration is proposed. The conventional input estimation techniques assume constant acceleration level and there are uncovered a generalized acceleration modeling. In contrast, the augmented algorithms, which are based on the jerk modeling, are computationally expensive. In this paper, an innovative scheme is developed to overcome these drawbacks by using a new generalized dynamic modeling of acceleration and an optimal two-stage modified Kalman filter. The proposed scheme is based on the basic Fisher and Bayesian uncertainty models. The optimality of the proposed two-stage modified Kalman filter is proved. Comparisons with two well known approaches using Monte Carlo simulation show that the proposed scheme has a computational advantage over the augmented algorithms and also more significant improvement than the input estimation techniques.
[Show abstract][Hide abstract] ABSTRACT: A new general two-stage algorithm is originally proposed to reduce the computational effort for maneuvering target tracking in mixed coordinates. The augmented state Kalman estimators, which are based on the jerk modeling, are computationally expensive. The conventional input estimation techniques assume constant acceleration level and there are not covered a generalized input modeling. In this research, an innovative scheme is developed to overcome these drawbacks by using a reduced state Kalman estimator with a new structure, which is optimal for general conditions. In addition, the proposed scheme is an unbiased filtering algorithm applied in mixed coordinates based on the pseudo linear measurements.
[Show abstract][Hide abstract] ABSTRACT: In this study, an intelligent approach is applied to reset the error covariance matrix of Kalman filter (KF) for high maneuver target tracking. In practice, the standard KF is used for non-maneuvering target tracking applications, which is optimal in the Minimum Mean Square Error (MMSE) sense. Furthermore, it has fast convergence rate. However, after some iterations the steps of the KF become very small. Because of small steps in KF, the accuracy of target tracking may be seriously degraded in presence of maneuver. This drawback can be overcome by resetting the error covariance matrix of the KF. Since the information of earlier updates will be partially lost by resetting the error covariance matrix, system should reset it just when the target maneuvers and KF steps are not large enough to track the target accurately. Moreover, resetting factor should be proportional to the maneuver. Therefore, we present an intelligent approach based on target maneuver detection to determine proper instants for resetting the error covariance matrix. In addition, the new scheme is enable to determine the optimal value of resetting factor in each iteration effectively. Simulation results illustrate that the tracking ability of the proposed scheme is more than conventional approaches, especially for high maneuvering target tracking applications.
[Show abstract][Hide abstract] ABSTRACT: A high accurate tracking technique with the use of intelligent approach on matrix covariance resetting is proposed in this paper. In practice, the conventional Kalman filters have a fast convergence rate at the beginning. However, after some iteration the Kalman filter steps become very small. To overcome this defect and to make use of Kalman filter abilities, the matrix covariance resetting idea is used. The matrix covariance presetting usually is used to improve the tracking algorithm result especially for high maneuvering targets. To determine the optimal value of the unknown resetting parameter in each step, the intelligent fuzzy block is used. In this paper, an innovative technique is presented, which resets covariance matrix by using fuzzy logic. It is demonstrated by means of numerical acceleration examples that the tracking capability of the proposed method is essentially as good as that of the traditional methods, especially for high maneuver targets.
Image and Signal Processing and Analysis, 2007. ISPA 2007. 5th International Symposium on; 10/2007
[Show abstract][Hide abstract] ABSTRACT: In the airborne vehicles, complex target tracking with more accurately is highly desirable. Conventional techniques based on augmented or batch algorithms are computationally expensive, which is the major drawback for the real time target parameter estimation. In contrast, other conventional input estimation techniques which overcome this problem, assume constant acceleration and therefore this is not a generalized modeling (T.C. Wang and P.K. Varshney, 1993). The proposed algorithm is developed to overcome these drawbacks by using a new generalized dynamic modeling of acceleration and acceleration rate (jerk) with reduction on the vector state dimension. The proposed modified Kalman filter algorithm is based on a generalized formulation including our earlier works. Results show the significant improvement for high maneuver target tracking problem.
Control and Automation, 2007. ICCA 2007. IEEE International Conference on; 07/2007
[Show abstract][Hide abstract] ABSTRACT: Ship borne targets normally maneuver on circular paths which have lead to tracking filters on circular turns. In this paper, an innovation technique is presented to transform the tracking-maneuvering target problems from Polar coordinate to Cartesian coordinate, therefore a standard linear Kalman filter can be easily applied to them. Mathematical relation between measurement noise covariance in polar coordinate and the measurement noise covariance in Cartesian coordinate for Kalman implementation is obtained in this approach via a theorem.
Control and Automation, 2007. ICCA 2007. IEEE International Conference on; 07/2007
[Show abstract][Hide abstract] ABSTRACT: In this paper, a new combined scheme is presented to overcome some drawbacks of the high maneuvering target tracking problems by using the mixed fuzzy logic and the standard Kalman filter. This scheme is consist of two important aspects; at first absolute value of difference between last target course and the present observation target course and the second aspect is the absolute value of measurement residual. The results compared with the augmented method and another combined fuzzy logic method which have been reported respectively. Simulation results show a high performance of the proposed innovation method and effectiveness of this scheme in high maneuvering targets tracking problems.
Information, Decision and Control, 2007. IDC '07; 03/2007
[Show abstract][Hide abstract] ABSTRACT: The deregulation of electric power supply industries has raised many challenging problems. One of the most important ones is forecasting the Market Clearing Price (MCP) of electricity. Decisions on various issues, such as to buy or sell electricity and to offer a transaction to the market, require accurate knowledge of the MCP. Another problem, which has also been an important issue of the traditional power systems, is load forecasting for both short and long terms. The extended kalman filter has been widely adopted for state estimation of nonlinear systems, machine learning applications and neural network training. In the EKF, the state distribution is approximated by the first-order linearization of the nonlinear system. Therefore this can introduce large errors in the load and price forecasting as two Chaotic, nonstationary and nonlinear time-series. The unscented Kalman filter (UKF), in contrast, achieves third-order accuracy, by using a minimal set of MCP and load sigma points. In this paper an improved dual unscented Kalman filter (DUKF), which estimate state and parameter simultaneously has been applied to the real New England power market. The numerical stability and more accurate predictions of our method is comparable to the EKF, and traditional neural network training methods. Remarkably, the computational complexity of the DUKF is the same order as that of the EKE. The obtained results show significant improvement in both price and load forecasting.
Control and Automation, 2007. ICCA 2007. IEEE International Conference on; 01/2007
[Show abstract][Hide abstract] ABSTRACT: In this paper, a new approach for maintenance scheduling of generating units of GENCOs in competitive environment is presented. In this environment, management of GENCOs and grid is separated, each maximizing its own benefit. The objective function for the GENCO is to sell electricity as much as possible, at proper time according to the market clearing price forecast. Various technical constraints such as generation capacity, duration of maintenances and maintenance continuity are being taken into account. The objective function of ISO is to maximize the reliability throughout the year; provided the energy purchase cost should be smaller than a predetermined amount when the units of GENCOs are out for maintenance. Therefore there are two objective functions for finding an optimum maintenance schedule in restructured power systems. In this paper we apply genetic algorithm methodology for finding the optimum preventive maintenance schedule of generating units
[Show abstract][Hide abstract] ABSTRACT: Many electric power systems around the world have introduced deregulated markets where suppliers of electricity can freely compete. Deregulation of the electric power industry worldwide raises many challenging issues. Under this environment there will be new tasks to be solved. In the traditional and also new structure of the power industry, accurate short and long term load forecasting have been crucial to the efficient and economic operation of the system. However in the environment of a deregulated power market, various decisions require accurate knowledge of future spot prices for electricity. To buy or sell physical electricity, to offer a transaction to the market, or to analyze security of the network are examples of transactions that can rationally be made only with an idea of future electricity prices. Therefore, forecasting of the market clearing price (MCP) is becoming increasingly relevant to different market players and system operator. This paper introduces a new forecasting method that forecasts the next-day electricity price and the electricity load based on cooperative co-evolutionary (Co-Co) approach. The proposed method is applied to predict the MCP and the load in a real power market. The results of the new method show significant improvement in the load and price forecasting process
[Show abstract][Hide abstract] ABSTRACT: The designer of the airborne defense missile system is interested in defining the fire control system (FCS) error, and the seeker detection probability to make the defense system more powerful. This paper develops one radar error statistical mathematics model for the airborne defense and determined the distribution of errors for each error, which can affect the probability of hit (PH). Furthermore, the errors in radar as the important subsystem of fire control system are determined, simulated and analysis. Then a new statistical mathematics approach based on Monte Carlo Method suggestion for error analysis of radar
Systems and Control in Aerospace and Astronautics, 2006. ISSCAA 2006. 1st International Symposium on; 02/2006
[Show abstract][Hide abstract] ABSTRACT: High maneuvering targets normally maneuver on circular paths which have lead to tracking filters on circular turns. In this paper, an innovation technique is presented to combine the tracking-maneuvering target problems using fuzzy logic and augmented Kalman filter. The proposed combined filter is composed of two automatic switching modes: one for the mild maneuver using augmented Kalman filter and the other for the high maneuver using fuzzy acceleration prediction method. It is demonstrated by means of numerical acceleration examples that the tracking capability of the proposed mixed method is essentially as good as that of the augmented method, especially at high maneuver target