Romesh Nagarajah

A Neural Network Approach to Fluid Quantity Measurement in Dynamic Environments

Sloshing causes liquid to fluctuate, making accurate level readings difficult to obtain in dynamic environments. The measurement system described uses a single-tube capacitive sensor to obtain an instantaneous level reading of the fluid surface, thereby accurately determining the fluid quantity in the presence of slosh. A neural network based classification technique has been applied to predict the actual quantity of the fluid contained in a tank under sloshing conditions. In A neural network approach to fluid quantity measurement in dynamic environments, effects of temperature variations and contamination on the capacitive sensor are discussed, and the authors propose that these effects can also be eliminated with the proposed neural network based classification system. To examine the performance of the classification system, many field trials were carried out on a running vehicle at various tank volume levels that range from 5 L to 50 L. The effectiveness of signal enhancement on the neural network based signal classification system is also investigated. Results obtained from the investigation are compared with traditionally used statistical averaging methods, and proves that the neural network based measurement system can produce highly accurate fluid quantity measurements in a dynamic environment. Although in this case a capacitive sensor was used to demonstrate measurement system this methodology is valid for all types of electronic sensors. The approach demonstrated in A neural network approach to fluid quantity measurement in dynamic environments can be applied to a wide range of fluid quantity measurement applications in the automotive, naval and aviation industries to produce accurate fluid level readings. Students, lecturers, and experts will find the description of current research about accurate fluid level measurement in dynamic environments using neural network approach useful.

Ultrasonic sensor based defect detection and characterisation of ceramics

Ceramic tiles, used in body armour systems, are currently inspected visually offline using an X-ray technique that is both time consuming and very expensive. The aim of this research is to develop a methodology to detect, locate and classify various manufacturing defects in Reaction Sintered Silicon Carbide (RSSC) ceramic tiles, using an ultrasonic sensing technique. Defects such as free silicon, un-sintered silicon carbide material and conventional porosity are often difficult to detect using conventional X-radiography. An alternative inspection system was developed to detect defects in ceramic components using an Artificial Neural Network (ANN) based signal processing technique. The inspection methodology proposed focuses on pre-processing of signals, de-noising, wavelet decomposition, feature extraction and post-processing of the signals for classification purposes. This research contributes to developing an on-line inspection system that would be far more cost effective than present methods and, moreover, assist manufacturers in checking the location of high density areas, defects and enable real time quality control, including the implementation of accept/reject criteria.

Stakeholders’ involvements in the implementation of proactive environmental practices : Linking environmental practices and environmental performances in SMEs

Purpose – The purpose of this paper is to investigate key causal linkages of proactive environmental practices of small and medium enterprises (SMEs). Specifically, this paper studies the ways that the interactions between different stakeholders such as suppliers and customers could intensify the widespread diffusion and implementation of green technologies. Understanding these linkages provide an opportunity to develop a framework that integrates stakeholders’ involvement, environmental practices and environmental/operational performances. Design/methodology/approach – This paper adopts the quantitative methodology. It uses the survey data collected from 232 Malaysian SMEs. The structural equation modelling (SEM) via AMOS 19 was employed to test the hypotheses. Findings – The empirical results suggest that decisions on environmental practices are influenced significantly by interactions between stakeholders but notably in different ways. While customers and employees involvements are targeted at process ...

Design of a suitable production management system for a manufacturing company

This paper reports on the design of a suitable production management system (PMS) for a manufacturing company, located in Western Australia. The company was experiencing problems in scheduling and plant layout leading to further problems in materials flow, labour control, inventory and purchasing, material handling system, and production space.Group technology (GT) was used to design a new plant layout. A G.T. algorithm was developed to minimise machine duplications. A Kanban system was designed to assist execution of scheduling based on a pull system. The design was tested by simulation using actual data collected on existing operations.

Comparison between different sets of suspension parameters and introduction of new modified skyhook control strategy incorporating varying road condition

This study examines the uncertainties in modelling a quarter car suspension system caused by the effect of different sets of suspension parameters of a corresponding mathematical model. To overcome this problem, 11 sets of identified parameters of a suspension system have been compared, taken from the most recent published work. From this investigation, a set of parameters were chosen which showed a better performance than others in respect of peak amplitude and settling time. These chosen parameters were then used to investigate the performance of a new modified continuous skyhook control strategy with adaptive gain that dictates the vehicles semi-active suspension system. The proposed system first captures the road profile input over a certain period. Then it calculates the best possible value of the skyhook gain (SG) for the subsequent process. Meanwhile the system is controlled according to the new modified skyhook control law using an initial or previous value of the SG. In this study, the proposed suspension system is compared with passive and other recently reported skyhook controlled semi-active suspension systems. Its performances have been evaluated in terms of ride comfort and road handling performance. The model has been validated in accordance with the international standards of admissible acceleration levels ISO2631 and human vibration perception.

Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound

The motivation for this research stems from a need for providing a non-destructive testing method capable of detecting and locating any defects and microstructural variations within armour ceramic components before issuing them to the soldiers who rely on them for their survival. The development of an automated ultrasonic inspection based classification system would make possible the checking of each ceramic component and immediately alert the operator about the presence of defects. Generally, in many classification problems a choice of features or dimensionality reduction is significant and simultaneously very difficult, as a substantial computational effort is required to evaluate possible feature subsets. In this research, a combination of artificial neural networks and genetic algorithms are used to optimize the feature subset used in classification of various defects in reaction-sintered silicon carbide ceramic components. Initially wavelet based feature extraction is implemented from the region of interest. An Artificial Neural Network classifier is employed to evaluate the performance of these features. Genetic Algorithm based feature selection is performed. Principal Component Analysis is a popular technique used for feature selection and is compared with the genetic algorithm based technique in terms of classification accuracy and selection of optimal number of features. The experimental results confirm that features identified by Principal Component Analysis lead to improved performance in terms of classification percentage with 96% than Genetic algorithm with 94%.

Feature extraction for ultrasonic sensor based defect detection in ceramic components

High density silicon carbide materials are commonly used as the ceramic element of hard armour inserts used in traditional body armour systems to reduce their weight, while providing improved hardness, strength and elastic response to stress. Currently, armour ceramic tiles are inspected visually offline using an X-ray technique that is time consuming and very expensive. In addition, from X-rays multiple defects are also misinterpreted as single defects. Therefore, to address these problems the ultrasonic non-destructive approach is being investigated. Ultrasound based inspection would be far more cost effective and reliable as the methodology is applicable for on-line quality control including implementation of accept/reject criteria. This paper describes a recently developed methodology to detect, locate and classify various manufacturing defects in ceramic tiles using sub band coding of ultrasonic test signals. The wavelet transform is applied to the ultrasonic signal and wavelet coefficients in the di...

A novel multiple adaptive fuzzy system for robust nonlinear control

A novel approach using multiple adaptive fuzzy systems for controlling complex nonlinear systems for improved transient response, is developed in this study. The multiple adaptive fuzzy controllers are soft-switched depending on the operating conditions using another fuzzy-based function. Apart from that, a single adaptive fuzzy controller is also developed for comparison studies. These fuzzy setups are used separately in pursuit of robust compensation for the unmodeled dynamics, nonlinearity issues, external disturbances and model uncertainties etc., thus ensuring a globally asymptotically stable system. A Lyapunov-based Kalman-Yakubovich-Popov (KYP) lemma is used to ensure closed loop robust stability of the control systems with the establishment of positive-realness of the error system. A simulation study using a passenger car model, an example of complex nonlinear system, is carried out. The results obtained from these simulation studies demonstrate that the multiple adaptive controller setup results in substantial improvements over the single adaptive system especially in the transient effects with the performance of complex systems.

Capacitive Sensing Technology

This chapter describes the basic properties of capacitive sensor technologies and their use in various kinds of sensors in industrial applications. Physical properties as well as some limitations of capacitive sensing are described here. The use of capacitive sensors with hazardous fluids, such as gasoline based fuels, and various configurations of capacitive sensors used in the application of fluid level measurement in dynamic environments are described. In brief, this chapter provides information on capacitive sensing technology and its use in dynamic and hostile environments.

Particle Swarm Optimization approach to defect detection in armour ceramics

HighlightsPSO not been explored especially in classifying high frequency ultrasonic signals.Binary Particle Swarm Optimization approach is proposed to perform feature selection.Dimensionality of the dataset is reduced and classification performance has been improved.Population data is used as input to ANN that serves as an evaluator of PSO fitness function.This technique do not need prior knowledge of desired number of features to carry out experiments. ABSTRACT In this research, various extracted features were used in the development of an automated ultrasonic sensor based inspection system that enables defect classification in each ceramic component prior to despatch to the field. Classification is an important task and large number of irrelevant, redundant features commonly introduced to a dataset reduces the classifiers performance. Feature selection aims to reduce the dimensionality of the dataset while improving the performance of a classification system. In the context of a multi‐criteria optimization problem (i.e. to minimize classification error rate and reduce number of features) such as one discussed in this research, the literature suggests that evolutionary algorithms offer good results. Besides, it is noted that Particle Swarm Optimization (PSO) has not been explored especially in the field of classification of high frequency ultrasonic signals. Hence, a binary coded Particle Swarm Optimization (BPSO) technique is investigated in the implementation of feature subset selection and to optimize the classification error rate. In the proposed method, the population data is used as input to an Artificial Neural Network (ANN) based classification system to obtain the error rate, as ANN serves as an evaluator of PSO fitness function.