Anna L. Buczak

A control switching theory for supervisory control of discrete event systems

In this paper, we introduce the concept of switching from one supervisory control to another one when changes in the state of an embedded sensory network occur. The sensory devices are assumed to be single functional, that is, they are programmed to observe and report only one event. The switching model is built based on the two criteria of language observability and state synchronization. Switching model is the basis for a megacontroller, which monitors the state of the sensory network embedded in the plant as well as the state of the supervisor in charge. Every time the state of this network changes, the megacontroller reconfigures the control system by finding an appropriate supervisor.

Genetic algorithm convergence study for sensor network optimization

Abstract This paper describes optimization of a sensor network by a Genetic Algorithm (GA). The system developed automatically generates the optimization problems depending on the events happening in the environment and constructs a GA with the appropriate internal structure for the problem at hand. GA finds the quasioptimal combination of sensors that can detect and/or locate the targets. An optimal combination is the one that minimizes the power consumption of the entire sensor network and gives the best accuracy of location of desired targets. The paper attempts to determine the percentage of the total search space (PTSS) that should be covered by GA in order to obtain consistent quasioptimal solutions in different runs. The second goal is to determine the relationship between the population size and the GA stopping criteria that for a given PTSS ensures the best performance of GA. The study is performed for the sensor network optimization problem with three targets.

Hybrid fuzzy-genetic technique for multisensor fusion

This paper describes a novel hierarchical fuzzy-genetic information fusion technique. The reasoning takes place by means of fuzzy aggregation functions, capable of combining information by compensatory connectives that better mimic the human reasoning process than union and intersection, employed in traditional set theories. The parameters of the connectives are found by genetic algorithms. The distinctive feature of the algorithm developed is its capability of fusing data in a near optimal manner when no information about the reliability of the information sources, the degree of redundancy/ complementarity of the information sources, and the structure of the hierarchy exists.

Self-organizing cooperative sensor network for remote surveillance: current results

The capabilities of unattended ground sensors (UGSs) have steadily improved and have been shown to be of value in various military missions. Todays UGS are multi-functional, integrated sensor platforms that can detect and locate a wide variety of ground-based and airborne targets. The rather large size (> 1 cubic foot) and relatively expensive cost of these integrated platforms are two main drawbacks for remote surveillance applications that support rapidly deployable, small unit operations. As an alternative, remote surveillance may be possible with smaller, less costly sensors that work cooperatively together as a network. The objective of this study was to develop algorithms that can optimally organized and adaptively control a network of UGSs in order to achieve a surveillance mission. In the present study, the sensor network, a random distribution of acoustic sensors over a surveillance area, is tasked to detect and track any targets entering into the surveillance area. In addition, the sensor network is required to maximize its tracking accuracy and minimize its power utilization.

Self-organizing cooperative sensor network for remote surveillance

The capabilities of unattended ground sensors (UBSs) have steadily improved and have been shown to be of value in various military missions. Todays UGS are multifunctional, integrated sensor platforms that can detect and locate a wide variety of ground-based and airborne targets. Due primarily to cost and size constraints of these UGS, they have not been widely used for law enforcement surveillance applications. As an alternative to a single, monolithic sensor platform, remote surveillance may be possible with smaller, less obtrusive sensors that work cooperatively together as a network. The objective of this study was to develop algorithms that can optimally organize and adaptively control a network of UGSs in order to achieve a surveillance mission. In the present study, the sensor network, a random distribution of sensors over a surveillance area (emulates airborne sensor deployment), determines an optimal combination of its sensors that will detect multiple targets and consume the lease amount of power. This problem is considered a multiobjective optimization problem to which there is no unique solution. Furthermore, for a linearly increasing number of sensors, the combinatorial search space increases exponentially. To reduce the search space, a novel clustering method was developed based on whether the sensor can sense the target rather than on similarities between the sensors. A genetic algorithm (GA) was used to obtain a quasioptimal solution for the sensor combination problem. To evaluate the effectiveness of the optimization, figures of merit were developed that are applicable to a sensor network tasked with a surveillance problem. Software-simulated data was used to test software implementation of the clustering, optimization and figure of merit functions. The clustering method reduced the search space by an average of ten orders of magnitude. For a sensor population of 100 sensors that was tasked to detect 24 targets, the GA was able to select optimal sets of sensors for detection and minimization of power consumption. The results demonstrate the feasibility of optimally configuring and controlling a network of sensors for remote surveillance applications.

Neural-networks-based sensor validation and recovery methodology for advanced aircraft engines

Within the context of preventive health maintenance in complex engineering systems, novel sensor fault detection methodologies are developed for an aircraft auxiliary power unit. Promising results at operational and sensor failure conditions are obtained for temperature and pressure sensors. In the methodology proposed, first covariance and noise analyses of sensor data are performed. Next, auto- associative and hetero-associative neural networks for sensor validation are designed and trained. These neural networks are used together to provide validation for pressure and temperature sensors. The last step consists of development of detection and identification logic for sensor faults. In spite o high noise levels, the methodology is shown to be very robust. More than 90% correct sensor failure detection is achieved when noise on the order of noise inherently present in sensor readings is added.