San Francisco, CA, United States
San Francisco, CA, United States
Time filter
Source Type

Zhang L.,Shanghai JiaoTong University | Cao Q.,Shanghai JiaoTong University | Lee J.,Intelligent Maintenance
Applied Soft Computing Journal | Year: 2013

Ant-based clustering is a type of clustering algorithm that imitates the behavior of ants. To improve the efficiency, increase the adaptability to non-Gaussian datasets and simplify the parameters of the algorithm, a novel ant-based clustering algorithm using Renyi Entropy (NAC-RE) is proposed. There are two aspects to application of Renyi entropy. Firstly, Kernel Entropy Component Analysis (KECA) is applied to modify the random projection of objects when the algorithm is run initially. This projection can create rough clusters and improve the algorithm's efficiency. Secondly, a novel ant movement model governed by Renyi entropy is proposed. The model takes each object as an ant. When the object (ant) moves to a new region, the Renyi entropy in its local neighborhood will be changed. The differential value of entropy governs whether the object should move or be moveless. The new model avoids complex parameters that have influence on the clustering results. The theoretical analysis has been conducted by kernel method to show that Renyi entropy metric is feasible and superior to distance metric. The novel algorithm was compared with other classic ones by several well-known benchmark datasets. The Friedman test with the corresponding Nemenyi test are applied to compare and conclude the algorithms' performance The results indicate that NAC-RE can get better results for non-linearly separable datasets while its parameters are simple. © 2012 Elsevier B.V. All rights reserved.

Siegel D.,Intelligent Maintenance | Ly C.,U.S. Army | Lee J.,Intelligent Maintenance
IEEE Transactions on Reliability | Year: 2012

The enhanced ability to predict the remaining useful life of helicopter drive train components offers potential improvement in the safety, maintainability, and reliability of a helicopter fleet. Current existing helicopter health and usage monitoring systems provide diagnostic information that indicates when the condition of a drive train component is degraded; however, prediction techniques are not currently used. Although various algorithms exist for providing remaining life predictions, prognostic techniques have not fully matured. This particular study addresses remaining useful life predictions for the helicopter oil-cooler bearings. The paper proposes a general methodology of how to perform rolling element bearing prognostics, and presents the results using a robust regression curve fitting approach. The proposed methodology includes a series of processing steps prior to the prediction routine, including feature extraction, feature selection, and health assessment. This approach provides a framework for including prediction algorithms into existing health and usage monitoring systems. A case study with the data collected by Impact Technology, LLC. is analysed using the proposed methodology. Future work would consider using the same methodology, but comparing the accuracy of this prediction method with Bayesian filtering techniques, usage based methods, and other time series prediction methods. © 1963-2012 IEEE.

Rezvanizaniani S.M.,Intelligent Maintenance | Liu Z.,Intelligent Maintenance | Chen Y.,Intelligent Maintenance | Lee J.,Intelligent Maintenance
Journal of Power Sources | Year: 2014

As hybrid and electric vehicle technologies continue to advance, car manufacturers have begun to employ lithium ion batteries as the electrical energy storage device of choice for use in existing and future vehicles. However, to ensure batteries are reliable, efficient, and capable of delivering power and energy when required, an accurate determination of battery performance, health, and life prediction is necessary. This paper provides a review of battery prognostics and health management (PHM) techniques, with a focus on major unmet needs in this area for battery manufacturers, car designers, and electric vehicle drivers. A number of approaches are presented that have been developed to monitor battery health status and performance, as well as the evolution of prognostics modeling methods. The goal of this review is to render feasible and cost effective solutions for dealing with battery life issues under dynamic operating conditions. © 2014 Elsevier B.V. All rights reserved.

Lee J.,Intelligent Maintenance | Ghaffari M.,Intelligent Maintenance | Elmeligy S.,Intelligent Maintenance
Annual Reviews in Control | Year: 2011

This paper discusses the state-of-the-art research in the areas of self-maintenance and engineering immune systems (EIS) for machines with smarter adaptability to operating regime changes in future manufacturing systems. Inspired by the biological immune and nervous systems, the authors are introducing the transformation of prognostics and health management (PHM) to engineering immune systems (EIS). First, an overview on PHM is introduced. Its transformation toward resilient systems, self-maintenance systems, and engineering immune systems is also discussed. Finally, new concepts in developing future biological-based smarter machines based on autonomic computing and cloud computing are discussed. © 2010 Elsevier Ltd. All rights reserved.

Zhang J.,Intelligent Maintenance | Lee J.,Intelligent Maintenance
Journal of Power Sources | Year: 2011

The functionality and reliability of Li-ion batteries as major energy storage devices have received more and more attention from a wide spectrum of stakeholders, including federal/state policymakers, business leaders, technical researchers, environmental groups and the general public. Failures of Li-ion battery not only result in serious inconvenience and enormous replacement/repair costs, but also risk catastrophic consequences such as explosion due to overheating and short circuiting. In order to prevent severe failures from occurring, and to optimize Li-ion battery maintenance schedules, breakthroughs in prognostics and health monitoring of Li-ion batteries, with an emphasis on fault detection, correction and remaining-useful-life prediction, must be achieved. This paper reviews various aspects of recent research and developments in Li-ion battery prognostics and health monitoring, and summarizes the techniques, algorithms and models used for state-of-charge (SOC) estimation, current/voltage estimation, capacity estimation and remaining-useful-life (RUL) prediction. © 2011 Elsevier B.V. All rights reserved.

Abuali M.,Intelligent Maintenance
International Journal of Advanced Manufacturing Technology | Year: 2011

In recent times, globalization has brought us not only new opportunities but also new challenges. The theme of innovation has become a mandatory topic for all industries-it has become a focal point for the enterprise, society, and the world. The goal of innovation is to create business value by developing worthwhile ideas into a customer-centric marketable reality. This, for most companies, is difficult to achieve due to the lack of a methodology and tools for systematic innovative thinking. This article presents an operating system for innovation by offering a methodology for systematic innovative thinking and a toolbox of interconnected tools that can aid in the transformation of core product competencies into effective product-service amalgamations. Brief reviews of product innovation and emerging concepts of product-service systems are presented. Then, a methodology for systematic thinking is proposed, relying on the integration of the novel innovation matrix, application space mapping, and quality function deployment tools. Furthermore, a case study is presented with concluding remarks and future work. © 2010 Springer-Verlag London Limited.

Yang L.,Intelligent Maintenance | Lee J.,Intelligent Maintenance
Robotics and Computer-Integrated Manufacturing | Year: 2012

Semiconductor manufacturing is a complex process in that it requires different types of equipments (also referred to as tools in semiconductor industry) with various control variables under monitoring. As the number of sensors grows, a huge amount of data are collected from the production; and yet, the relations among these control variables and their effects on finished wafer are to be fully understood for both equipment monitoring and quality assurance. Meanwhile, as the wafer goes through multiple periods with different recipes, failure that occurs during the process can both cause tremendous loss to manufacturer and compromise product quality. Therefore, occurred failure should be detected as soon as possible, and root cause need to be identified so that corrections can be made in time to avoid further loss. In this paper, we propose to apply Bayesian Belief Network (BBN) to investigate the causal relationship among process variables on the tool and evaluate their influence on wafer quality. By building BBN models at different periods of the process, the causal relation between control parameters, and their influence on wafer can be both qualitatively indicated by the network structure and quantitatively measured by the conditional probabilities in the model. In addition, with the BBN probability propagation, one can diagnose root causes when bad wafer is produced; or predict the wafer quality when abnormal is observed during the process. Our tests on a Chemical Vapor Deposition (CVD) tool show that the BBN model achieves high classification rate for wafer quality, and accurately identifies problematic sensors when bad wafer is found. © 2011 Elsevier Ltd.

Liao L.,Intelligent Maintenance | Lee J.,Intelligent Maintenance
Expert Systems with Applications | Year: 2010

For decades, researchers and practitioners have been trying to develop and deploy prognostics technologies with ad hoc and trial-and-error approaches. These efforts have resulted in limited success, due to the fact that it lacks a systematic approach and platform in deploying the right prognostics tools for the right applications. This paper introduces a methodology for designing a reconfigurable prognostics platform (RPP) which can be easily and effectively used to assess and predict the performance of machine tools. RPP can be installed on the equipment and it has the prognostic capabilities to convert the data into performance-related information. The equipment performance information can then be integrated into the enterprise asset management system for maintenance decision making through the Internet. Two industrial cases are used to validate the effectiveness of applying the RPP for different prognostic applications as well as the reconfigurable capabilities of the proposed RPP. © 2009 Elsevier Ltd. All rights reserved.

Agency: GTR | Branch: Innovate UK | Program: | Phase: Feasibility Study | Award Amount: 23.26K | Year: 2015

The objectives of this study are to develop novel dynamic control systems which optimise the energy use of food refrigeration systems. These systems are known to consume in the order of 12TWh of energy per year, and comprise approximately one third of a typical retailers energy cost. Current control systems operate around very static control temperatures. In this proposal we will develop new algorithms to control refrigeration temperatures within strict (for food safety reasons) but variable temperature control bands. Large retailers now have centralised control of all refrigeration systems within a typical estate. This high level of control provides an unrivalled opportunity to manage and control energy consumption in proportion to grid availability. The challenge is though significant and will require the development of mutliple objective control mechanisms which also consider essential food safety parameters. The opportunity to market the control algorithms across the rest of the World is significant.

Loading Intelligent Maintenance collaborators
Loading Intelligent Maintenance collaborators