Mohammad Bodruzzaman

Nanosensor Data Processor in Quantum-Dot Cellular Automata

Quantum-dot cellular automata (QCA) is an attractive nanotechnology with the potential alterative to CMOS technology. QCA provides an interesting paradigm for faster speed, smaller size, and lower power consumption in comparison to transistor-based technology, in both communication and computation. This paper describes the design of a 4-bit multifunction nanosensor data processor (NSDP). The functions of NSDP contain (i) sending the preprocessed raw data to high-level processor, (ii) counting the number of the active majority gates, and (iii) generating the approximate sigmoid function. The whole system is designed and simulated with several different input data.

Speaker recognition using neural network and adaptive wavelet transform

The same word uttered by different people has different waveforms. It has also been observed that the same word uttered by the same person has different waveform at different times. This difference can be characterized by some time domain dilation effects in the waveform. In our experiment a set of words was selected and each word was uttered eight times by five different speakers. The objective of this work is to extract a wavelet basis function for the speech data generated by each individual speaker. The wavelet filter coefficients are then used as a feature set and fed into a neural network-based speaker recognition system. This is an attempt to cascade a wavelet network (wavenet) and a neural network (neural-net) for feature extraction and classification respectively and applied for speaker recognition. The results show very high promise and good prospects to couple a wavelet network and neural networks.

Estimation of micro-crack lengths using eddy current C-scan images and neural-wavelet transform

The work reported in this paper is concerned with the development of neural network-based methods for estimating the size of cracks in the range of mum occurring around a hole on or beneath the surface of metal plate using eddy-current based C-scan images. The developed software includes wavelet transform-based feature extraction from C-scan images with known crack length and computing the energy associated with wavelet coefficient feature data. The feature data were then nonlinearly modeled using feed-forward neural network for the estimation of crack lengths. The results obtained are very promising and the method can be applied for online monitoring and estimation of micro crack sizes. The smallest crack size estimated was 200 mum within 10% estimation error. Due to limitation of resolution of the sensors, all measurements were performed in the millimeter range and images were resized again to simulate crack sizes in the micro-meter scale.

Information and decision fusion systems for aircraft Structural Health Monitoring

Structural Health Monitoring (SHM) is the process of continuous and autonomous monitoring of the physical condition of a structure by means of sensors. It is a mean of Non-Destructive-Inspection for monitoring and ensuring the structural integrity of aircraft. SHM techniques have been explored to reduce air vehicle maintenance and repair costs while maintaining safety and reliability. This research investigated the benefits provided by developing and applying decision fusion algorithms to SHM systems. These algorithms should provide means for incorporating prior knowledge about the structure to improve the overall SHM system performance. The decisions of classifiers are combined using decision fusion methods to arrive at unified final decisions regarding the state of the monitored structure. The Dempster-Shafer theory of evidence was used for development of the decision-fusion algorithm. The fusion algorithm was implemented in Matlab and was tested on experimental data. The testing and evaluation results showed significant improvement due to fusion‥ The testing results reported in this paper compared performance of individual classifier decisions with the decision produced by the decision-fused algorithm.

Two-level fuzzy inference system for aircraft's structural health monitoring

Structural health monitoring is the process of detecting damages in an engineering structure and identifying location and type of the damage. This paper focuses on the development and implementation of clustering and classification software system for monitoring aircraft structure health status. The integrated software system was broken down into three modules namely; feature extraction, clustering and classification, and decision-fusion module. The feature extraction module was used to extract frequency features from the structural vibration data. The clustering and classification module was used to group the extracted sets of features into homogeneous classes of similar features. Finally, the decision-fusion module was used to fuse decisions made by multiple monitoring systems and produce more trustworthy decisions than the decisions made by a single clustering and classification module. The software system was developed based on fuzzy system with multiple inference engines. Finally, the developed health monitoring system was tested on data collected from experimental setup conducted on a simple structure with four bolts and four sensors. The test results of the developed software system will be reported and presented in this paper.

Multistage Fuzzy Inference System for Decision Making and Fusion in Crack Detection of Aircraft Structures

Automated methods for detecting damage in structural components across a wide range of structures have been investigated and developed over at least the past decade. Although many successes and promising advances have been reported, none of the results to date have been accurate or reliable enough to motivate the US Air Force to remove, or even reduce, the reliance on human inspections. One approach to improving the performance of automated inspection methods is to fuse information gathered by multiple heterogeneous sources of sensors, and from decisions generated by multiple decision-making subsystems. This paper investigates the benefits provided by integrating decision making and decision fusion algorithms into structural health monitoring systems. Decisions made by fuzzy inference algorithms acting on local information extracted from multi-sensors data were combined using a decision fusion algorithm to arrive at a unified final decision regarding the status of monitored structures. The decision-making and decision-fusion software systems were integrated and tested on features extracted from experimental data to validate their performances. Development and implementation steps of the decision-making and decision-fusion algorithms are presented in this paper. Test results and evaluation of the developed integrated software system are reported and discussed at the end of the paper.

Analysis of decision fusion algorithms in handling uncertainties for integrated health monitoring systems

It has been widely accepted that data fusion and information fusion methods can improve the accuracy and robustness of decision-making in structural health monitoring systems. It is arguably true nonetheless, that decision-level is equally beneficial when applied to integrated health monitoring systems. Several decisions at low-levels of abstraction may be produced by different decision-makers; however, decision-level fusion is required at the final stage of the process to provide accurate assessment about the health of the monitored system as a whole. An example of such integrated systems with complex decision-making scenarios is the integrated health monitoring of aircraft. Thorough understanding of the characteristics of the decision-fusion methodologies is a crucial step for successful implementation of such decision-fusion systems. In this paper, we have presented the major information fusion methodologies reported in the literature, i.e., probabilistic, evidential, and artificial intelligent based methods. The theoretical basis and characteristics of these methodologies are explained and their performances are analyzed. Second, candidate methods from the above fusion methodologies, i.e., Bayesian, Dempster-Shafer, and fuzzy logic algorithms are selected and their applications are extended to decisions fusion. Finally, fusion algorithms are developed based on the selected fusion methods and their performance are tested on decisions generated from synthetic data and from experimental data. Also in this paper, a modeling methodology, i.e. cloud model, for generating synthetic decisions is presented and used. Using the cloud model, both types of uncertainties; randomness and fuzziness, involved in real decision-making are modeled. Synthetic decisions are generated with an unbiased process and varying interaction complexities among decisions to provide for fair performance comparison of the selected decision-fusion algorithms. For verification purposes, implementation results of the developed fusion algorithms on structural health monitoring data collected from experimental tests are reported in this paper.

Modeling and Simulation Studies of a Decentralized Architecture for a Distributed Turbine Engine Controls

An aircraft engine is a multidimensional and highly parametric complex system with dynamics and strong non-linear behavior with stochastic properties. Many modern gas turbine engines today are centralized and specialized design by a highly integrated dual channel engine-mounted controller, such as a Full Authority Digital Electronic Controls (FADEC) to control all functions of the aircraft engines. In contrast to the centralized approach of the FADEC, the control architectures have been designed in which the functionality is more distributed around the engine to smart sensors, smart actuators and other subcomponents. The intent of these alternative architectures is to reduce overall system weight and improve reliability and diagnostics. Using fewer cables, the intent is also to reduce the functionality within the FADEC and to improve life cycle costs using improved fault diagnostics. Implementation of a distributed control of turbine engines constitutes practical realization of decentralized control architecture on a dedicated hardware. Such hardware realization of decentralized control architecture poses a new set of challenges. This paper provides an overview of solutions to some challenges associated with real world realization of decentralized control architecture on turbine engines in the form of a distributed hardware system. It also provides methodology used for the development and integration of a distributed control and diagnostics software for turbine engines. Developmental steps, implementation architecture and preliminary simulation results of the proposed distributed control system are reported in this paper. Preliminary results showed potential success of implementing distributed control of turbine engines.

Distributed Onboard Diagnostic Methodology for Next Generation Turbine Engines

Diagnosis of turbine engines involves extracting relevant information regarding present and past states of the engine. This paper provides an overview of system approach methodology used for the development of distributed diagnostic software for turbine engines which include developmental steps, implementation architecture and the testing results of the proposed diagnostic software. The testing results showed potential success of implementing the software for the purpose of assessing conditions of turbine engine components and tracking their operational performance for onboard diagnostics and prognostics

Predictive Control Strategy in Distributed Networked Control Systems for Turbine Engine Under Faulty Communication Network

Future turbine engines will require more efficient consumption of energy and greater reliability. A reduction in weight of turbine engine control systems and increased robustness will be critical in achieving said requirements. This paper presents the development of an advanced control strategy to replace the Full Authority Digital Electronic Control (FADEC) system (commonly used by turbine engines) with a lighter weight, Distributed Networked Control System (DNCS) that uses smart nodes (SN) architecture to enhance robustness. The concept of Distributed Networked Control Systems (DNCS) is rooted in the idea that the sum of the parts can be designed to weigh less than the whole, thereby allowing a single control system to be replaced by a set of sub-controller components that interact effectively through a network with improved functionality. The addition of artificial intelligent techniques employed to overcome the challenges inherent in DNCS operating under faulty communication networks are included. Specifically, an Artificial Neural Fuzzy Inference System (ANFIS) is employed to function as a state estimator within the distributed control nodes. The full implementation of the developed DNCS consists of distributed controllers, state estimators (ANFIS), and a simulated network interface. The focus of this paper is to report the development and test results related to the implementation of the described advanced distributed control methodology and its influence in recovering the engine operation in the presence of faults occurring within the communication network. The complete DNCS was tested on the MAPSS turbine engine simulation model. The test results showed that the developed DNCS with ANFIS state estimators improved turbine engine performance even under severe network delay conditions. As a result, the developed control system proved to be a viable alternative to the current engine control system. The research demonstrates that DNCS technology yields a reduction in engine weight leading to a reduction in energy consumption and a corresponding increase in engine efficiency and performance.