Birmingham, United Kingdom
Birmingham, United Kingdom

Time filter

Source Type

Pai S.,NMAM Institute of Technology | Rao R.B.K.N.,COMADEM International
Machining Science and Technology | Year: 2012

The monitoring of tool wear is a most difficult task in the case of various metal-cutting processes. Artificial Neural Networks (ANN) has been used to estimate or classify certain wear parameters, using continuous acquisition of signals from multi-sensor systems. Most of the research has been concentrated on the use of supervised neural network types like multi-layer perceptron (MLP), using back-propagation algorithm and Radial Basis Function (RBF) network. In this article, a new constructive learning algorithm proposed by Fritzke, namely Growing Cell Structures (GCS) has been used for tool wear estimation in face milling operations, thereby monitoring the condition of the tool. GCS generates compact network architecture in less training time and performs well on new untrained data. The performance of this network has been compared with that of another constructive learning algorithm-based neural network, namely the Resource Allocation Network (RAN). For the sake of establishing the effectiveness of GCS, results obtained have been compared with those obtained using Multi Layer Perceptron (MLP), which is a standard and widely used neural network. © 2012 Copyright Taylor and Francis Group, LLC.


Rao B.K.N.,COMADEM International | Pai P.S.,NMAMTT
International Journal of COMADEM | Year: 2013

Rolling-element bearings are extensively used in almost all global industries. Any critical failures in these vitally important components would not only affect the overall systems performance but also its reliability, safety, availability and cost-effectiveness. Proactive strategies do exist to minimise impending failures in real time and at a minimum cost. Continuous innovative developments are taking place in the field of Artificial Neural Networks (ANNs) technology. Significant research and development are taking place in many universities, private and public organizations and a wealth of published literature is available highlighting the potential benefits of employing ANNs in intelligently monitoring, diagnosing, prognosing and managing rollingelement bearing failures. This paper attempts to critically review the recent trends in this topical area of interest.


Rao B.K.N.,COMADEM International | Srinivasa Pai P.,NMAMIT
Journal of Physics: Conference Series | Year: 2012

Rolling - Element Bearings are extensively used in almost all global industries. Any critical failures in these vitally important components would not only affect the overall systems performance but also its reliability, safety, availability and cost-effectiveness. Proactive strategies do exist to minimise impending failures in real time and at a minimum cost. Continuous innovative developments are taking place in the field of Artificial Neural Networks (ANNs) technology. Significant research and development are taking place in many universities, private and public organizations and a wealth of published literature is available highlighting the potential benefits of employing ANNs in intelligently monitoring, diagnosing, prognosing and managing rolling-element bearing failures. This paper attempts to critically review the recent trends in this topical area of interest.


Obeid N.,University of Jordan | Rao R.B.K.N.,COMADEM International
Knowledge and Information Systems | Year: 2010

We develop, in this paper, a representation of time and events that supports a range of reasoning tasks such as monitoring and detection of event patterns which may facilitate the explanation of root cause(s) of faults. We shall compare two approaches to event definition: the active database approach in which events are defined in terms of the conditions for their detection at an instant, and the knowledge representation approach in which events are defined in terms of the conditions for their occurrence over an interval. We shall show the shortcomings of the former definition and employ a three-valued temporal first order nonmonotonic logic, extended with events, in order to integrate both definitions. © Springer-Verlag London Limited 2009.


Rao B.K.N.,COMADEM International
COMADEM 2010 - Advances in Maintenance and Condition Diagnosis Technologies Towards Sustainable Society, Proc. 23rd Int. Congr. Condition Monitoring and Diagnostic Engineering Management | Year: 2010

Too much data but very less intelligent information is the main problem facing the COMADEM community. The magnitude of this problem multiplies with the increase in system's complexity. We know that the data contains all the symptoms of 'health' and 'ill-health' of the system. We also know that there are considerable advantages to be gained by separating these symptoms from the bulk of raw data before processing them any further. Fortunately, techniques do exist to transform the raw data into reduced representation set of features. The process of transforming the input data into a set of features (also called features vector) is called feature extraction. Expert knowledge and general dimensionality reduction techniques are needed to detect, select and extract application-dependent features. In principle, any Feature Detection, Selection, Extraction and Classification (FSDEC) process should involve dimensionality reduction techniques that generate a subset of new features from the original set by means of some functional mapping, securing as much intelligent information in the data as possible. This way, FSDEC process results in a much smaller and richer set of attributes. Fundamental goals of FSDEC are compactness, discrimination power, low computation complexity, reliability and robustness. This paper presents a brief tutorial on this topic of interest.


Rao B.K.N.,COMADEM International
COMADEM 2010 - Advances in Maintenance and Condition Diagnosis Technologies Towards Sustainable Society, Proc. 23rd Int. Congr. Condition Monitoring and Diagnostic Engineering Management | Year: 2010

Higher-level decision making is a pre-requisite requirement to design and improve modern decision support systems (DSSs). Emphasis on continuous performance improvement, quality, safety, security and reliability is increasingly becoming a top-priority requirement for any competitive global organization. With the increasing role of rapidly developing ICTs more companies are investing in the development of efficient and competitive business ICT-based DSSs that can integrate and enhance or even replace the existing infrastructure. Modern Decision support systems constitute a class of computer-based information systems including knowledge-based systems that support decisionmaking activities. However, there is an urgent requirement to fully explore and exploit the rich experiences/evidences of past and present designers, engineers, technicians, specialists, managers, policy decision makers, philosophers and end-users to minimise costly failures and enhance the efficiency and effectiveness of modern DSSs. There are many modern tools, techniques and (flexible, adaptive, and robust) strategies, available to assist decision support system engineers to design smart DSSs. New concepts and technologies are continuously evolving. The aim of this paper and the interactive International Workshop is to highlight the issues related to this holistic interdisciplinary area of inquiry and to discuss/share the global ideas and experiences. It is hoped that the outcome of this workshop will reveal the "best practices" available and the challenges facing in designing failure-free, intrinsically safe, fool-proof and secure modern DSSs using Artificial Intelligence philosophy, science and technology.


Vijay G.S.,Manipal University India | Pai S.P.,NMAM Institute of Technology | Sriram N.S.,Vidya Vikas Institute of Engineering and Technology | Rao R.B.K.N.,COMADEM International
Proceedings of the Institution of Mechanical Engineers, Part J: Journal of Engineering Tribology | Year: 2013

This article uses the cluster dependent weighted fuzzy C-means based radial basis function neural network for comparing the different dimensionality reduction techniques for the fault diagnosis in the rolling element bearing. The vibration signals from normal bearing, bearing with defect on the inner race, and bearing with defect on the outer race were acquired under one radial load and two shaft speeds. These signals were subjected to the wavelet transform based denoising from which several time and frequency domain features were extracted. Dimensionality reduction techniques, namely, principal component analysis, Fisher's criterion, and separation index, have been used to select the sensitive features. The selected features were used to train and test the radial basis function neural network, where the centers of the radial basis function units have been optimized by the cluster dependent weighted fuzzy C-means and the widths of the radial basis function units have been fixed by trial and error. Finally, a comparison of the dimensionality reduction techniques based on the radial basis function neural network performance is presented. © IMechE 2012.


Vijay G.S.,Manipal University India | Kumar H.S.,NMAM Institute of Technology | Srinivasa P.P.,NMAM Institute of Technology | Sriram N.S.,Vidya Vikas Institute of Engineering and Technology | Rao R.B.K.N.,COMADEM International
Computational Intelligence and Neuroscience | Year: 2012

The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal. © 2012 Vijay G. S. et al.


Modera Tribological systems (such as aerospace vehicles, industrial processes, manufacturing systems, transportation systems, electrical and electronic systems, etc) have moving parts of one type or other and are becoming increasingly sophisticated and complex. These are subjected to various known and unknown failure modes which impact adversely their reliability, availability, safety and maintainability. Tribology has played a significant role in reducing friction, wear and extending the Remaining Useful Life (RUL) of modern engineering systems. In the past few decades, system designers and thinkers are increasingly becoming aware of the proactive concept of intelligent-based failure diagnosis and prognosis as the way forward to continuously improve the health and performance of their valuable assets. This change in philosophical attitude from reactive to proactive diagnosis/prognosis and a greater appreciation of assessing the 'state of health' and 'overall operational efficiency' of complex engineering systems should bring immense long term performance improvement and socio-economic benefits to global economy. In this state-of-the-art review paper, some condition monitoring and diagnostic engineering management (COMADEM) strategies are identified with specific reference to modern Tribological systems ISSN 1363-7681© 2013 COMADEM International.


Ramachandran K.P.,Caledonian College of Engineering | Fathi K.,Caledonian College of Engineering | Rao B.K.N.,COMADEM International
IEEM2010 - IEEE International Conference on Industrial Engineering and Engineering Management | Year: 2010

Modern engineering systems are becoming increasingly complex, sophisticated, demanding and globally distributed. Maintaining and sustaining such systems healthy, reliably, safely wherever and whenever needed efficiently and economically is a challenging task facing the 21st century. It is gratifying to note that significant advances are being made by researchers from academia, public and private R & D establishments, hardware/software vending organizations, professional and ISO to resolve a number of problem areas facing industrial sectors in maintaining their valuable assets. This paper presents some of the recent trends in the fast-growing holistic, proactive-based and topical area of systems performance monitoring and failure diagnosis. ©2010 IEEE.

Loading COMADEM International collaborators
Loading COMADEM International collaborators