Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229359
K. George, V. Venugopal
Graphics processor units (GPU) are specialized hardware accelerators that can be utilized for computations needing high parallelism and high memory bandwidth. Propelled by the attractive Flops/$ ratio and its capability to outperform a CPU cluster at the equivalent cost, large-scale GPU clusters are gaining popularity in the high-performance computing (HPC) community. However, the design challenges associated with the setup and application development process for an efficient HPC cluster includes: a) data movement and locality on the hardware accelerators; b) task mapping and allocation; and c) setting up a well-balanced system. In this paper, we present our experience setting up a GPU cluster for HPC applications; particularly signal processing for digital wideband receivers. We describe the architecture, hardware and software platform of the proposed cluster. The proposed GPU cluster implementing a 1.25 GHz digital wideband receiver was compared and contrasted against a HPC based predecessor receiver system. The adaptability of the GPU cluster was further demonstrated by utilizing it for a multiple receiver implementation that demanded higher data processing capability and throughput.
{"title":"Design and performance measurement of a high-performance computing cluster","authors":"K. George, V. Venugopal","doi":"10.1109/I2MTC.2012.6229359","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229359","url":null,"abstract":"Graphics processor units (GPU) are specialized hardware accelerators that can be utilized for computations needing high parallelism and high memory bandwidth. Propelled by the attractive Flops/$ ratio and its capability to outperform a CPU cluster at the equivalent cost, large-scale GPU clusters are gaining popularity in the high-performance computing (HPC) community. However, the design challenges associated with the setup and application development process for an efficient HPC cluster includes: a) data movement and locality on the hardware accelerators; b) task mapping and allocation; and c) setting up a well-balanced system. In this paper, we present our experience setting up a GPU cluster for HPC applications; particularly signal processing for digital wideband receivers. We describe the architecture, hardware and software platform of the proposed cluster. The proposed GPU cluster implementing a 1.25 GHz digital wideband receiver was compared and contrasted against a HPC based predecessor receiver system. The adaptability of the GPU cluster was further demonstrated by utilizing it for a multiple receiver implementation that demanded higher data processing capability and throughput.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133723580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229384
D. García-Romeo, H. Fuentes, N. Medrano, B. Calvo, S. Celma, D. Antolín
The ever-increasing application of wireless sensor networks in many different fields is causing a growing demand of low-cost energy-efficient sensors for monitoring physical variables such as temperature, pressure or gas concentration. This paper presents a conditioning system for low-cost non-dispersive infrared gas sensors used to measure the CO2 concentration in an open air environment. It mainly consists of an amplification and filtering circuit that adapts the small and noisy signal provided by the sensor to a signal which can be easily read by a low-power microcontroller. The proposed interface presents a good trade-off between energy consumption and accuracy, compatible with the energy requirements of wireless sensor network applications. Test performed connecting the system interface to a node sensor in a wireless sensor network using a simple communications protocol only causes a low reduction in the operating life of the node.
{"title":"An electronic interface for measuring CO2 emissions in embedded systems","authors":"D. García-Romeo, H. Fuentes, N. Medrano, B. Calvo, S. Celma, D. Antolín","doi":"10.1109/I2MTC.2012.6229384","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229384","url":null,"abstract":"The ever-increasing application of wireless sensor networks in many different fields is causing a growing demand of low-cost energy-efficient sensors for monitoring physical variables such as temperature, pressure or gas concentration. This paper presents a conditioning system for low-cost non-dispersive infrared gas sensors used to measure the CO2 concentration in an open air environment. It mainly consists of an amplification and filtering circuit that adapts the small and noisy signal provided by the sensor to a signal which can be easily read by a low-power microcontroller. The proposed interface presents a good trade-off between energy consumption and accuracy, compatible with the energy requirements of wireless sensor network applications. Test performed connecting the system interface to a node sensor in a wireless sensor network using a simple communications protocol only causes a low reduction in the operating life of the node.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124556968","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229562
M. Marcu, C. Cernazanu
Nowadays we are witnessing the fast spreading of smart grid technology deployments. An increase of smart grid services and applications is also expected. Therefore in our work we aim to propose and develop user applications on top of smart grid power infrastructures that monitor, analyze, classify and characterize different electronic devices connected to this infrastructure. The present paper aims to propose a solution for ideal power signature extraction for consumer devices. Power signature may deeply characterize the electronic devices functioning. This signature can be used to identify energy efficiency usage patterns and provide feedback to users in order to reduce energy consumption and increase the lifetime of the products. Power signature of an electronic device is defined as the power consumption response to certain workload or program executed by the device.
{"title":"Dynamic analysis of electronic devices' power signatures","authors":"M. Marcu, C. Cernazanu","doi":"10.1109/I2MTC.2012.6229562","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229562","url":null,"abstract":"Nowadays we are witnessing the fast spreading of smart grid technology deployments. An increase of smart grid services and applications is also expected. Therefore in our work we aim to propose and develop user applications on top of smart grid power infrastructures that monitor, analyze, classify and characterize different electronic devices connected to this infrastructure. The present paper aims to propose a solution for ideal power signature extraction for consumer devices. Power signature may deeply characterize the electronic devices functioning. This signature can be used to identify energy efficiency usage patterns and provide feedback to users in order to reduce energy consumption and increase the lifetime of the products. Power signature of an electronic device is defined as the power consumption response to certain workload or program executed by the device.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114309303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229371
Richard Neumayr, M. Harker, P. O’Leary, Johann Golser
The paper describes the design and manufacturing of optical components; calibration and evaluation procedures; together with thermally stable housings. All these elements are required for the implementation of accurate optical displacement and orientation sensors. Printed hexagonal and rectangular dot-patterns on optical glass are investigated with respect to their spatial scattering properties of an incident laser beam, and as a means of implementing semi-transparent windows to image laser spots on two parallel targets. The positions of the laser spots are observed by two cameras. The mapping from pixel coordinates to real world coordinates is implemented via a bivariate tensor polynomial product, whereby the calibration coefficients are determined in a manner such that the distortion associated with the optical component, e.g., lens distortion is compensated. The covariance propagation is explicitly computed for the calibration process and used to optimize the selection of the polynomial degree. This reflects the trade-off minimizing between the systematic and stochastic errors. The new technique and methods are demonstrated in the design of and implementation of an active optical laser target for machine guidance control. This measurement instrument, rigidly fixed on a Tunnel Boring Machine (TBM), measures the orientation and position of the machine where an off-vehicle reference laser beam is projecting its laser spots on two parallel targets. Precise vision-based measurements of the laser spot positions are achieved, yielding a standard deviation of the displacement error of 0.05 [mm] and for yaw and pitch of 0.02 [degree].
{"title":"New approaches to machine vision based displacement analysis","authors":"Richard Neumayr, M. Harker, P. O’Leary, Johann Golser","doi":"10.1109/I2MTC.2012.6229371","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229371","url":null,"abstract":"The paper describes the design and manufacturing of optical components; calibration and evaluation procedures; together with thermally stable housings. All these elements are required for the implementation of accurate optical displacement and orientation sensors. Printed hexagonal and rectangular dot-patterns on optical glass are investigated with respect to their spatial scattering properties of an incident laser beam, and as a means of implementing semi-transparent windows to image laser spots on two parallel targets. The positions of the laser spots are observed by two cameras. The mapping from pixel coordinates to real world coordinates is implemented via a bivariate tensor polynomial product, whereby the calibration coefficients are determined in a manner such that the distortion associated with the optical component, e.g., lens distortion is compensated. The covariance propagation is explicitly computed for the calibration process and used to optimize the selection of the polynomial degree. This reflects the trade-off minimizing between the systematic and stochastic errors. The new technique and methods are demonstrated in the design of and implementation of an active optical laser target for machine guidance control. This measurement instrument, rigidly fixed on a Tunnel Boring Machine (TBM), measures the orientation and position of the machine where an off-vehicle reference laser beam is projecting its laser spots on two parallel targets. Precise vision-based measurements of the laser spot positions are achieved, yielding a standard deviation of the displacement error of 0.05 [mm] and for yaw and pitch of 0.02 [degree].","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114904115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229304
F. Rastrello, P. Placidi, A. Scorzoni, E. Cozzani, M. Messina, I. Elmi, S. Zampolli, G. Cardinali
The aim of this paper is to present an acquisition system and experimental measurements of a new micromachined Thermal Conductivity Detector (μTCD), applied downstream of a gas-chromatography (GC) system. We describe a simple and innovative electronics for sensor control and data acquisition, outlining its resistance control, native imbalance compensation and automatic gain control (AGC) algorithm. Measurements and sensitivity tests have been carried out by connecting our TCD and acquisition system downstream of the microfluidic section and GC column of a commercial GC system. Comparing the results with those of a complete commercial GC system we observed a similar response and noise. Sensitivity measurements on toluene masses gave very good results, having observed a sensitivity of 15.2±0.6 μVs/ng. This high sensitivity will enable the use of the μTCD in many portable applications like in-line quality control, industrial security and safety. We also show the good operation of the AGC algorithm.
{"title":"Thermal Conductivity Detector for gas-chromatography: Acquisition system and experimental measurements","authors":"F. Rastrello, P. Placidi, A. Scorzoni, E. Cozzani, M. Messina, I. Elmi, S. Zampolli, G. Cardinali","doi":"10.1109/I2MTC.2012.6229304","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229304","url":null,"abstract":"The aim of this paper is to present an acquisition system and experimental measurements of a new micromachined Thermal Conductivity Detector (μTCD), applied downstream of a gas-chromatography (GC) system. We describe a simple and innovative electronics for sensor control and data acquisition, outlining its resistance control, native imbalance compensation and automatic gain control (AGC) algorithm. Measurements and sensitivity tests have been carried out by connecting our TCD and acquisition system downstream of the microfluidic section and GC column of a commercial GC system. Comparing the results with those of a complete commercial GC system we observed a similar response and noise. Sensitivity measurements on toluene masses gave very good results, having observed a sensitivity of 15.2±0.6 μVs/ng. This high sensitivity will enable the use of the μTCD in many portable applications like in-line quality control, industrial security and safety. We also show the good operation of the AGC algorithm.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115079285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229552
D. Fontanelli, D. Macii
Time synchronization in wireless sensor networks (WSN) is essential to schedule communication and distributed measurement tasks. In this paper a consensus-based synchronization algorithm is used to compensate dynamically both time offsets and clock frequency skews, thus driving all WSN clocks towards a common time scale. The proposed approach does not require either the election of a master node as a time reference for the whole network, or a specific synchronization protocol. Some simulation results show that the algorithm converges within a reasonable time, regardless of timestamping jitter, random communication latencies and incomplete node visibility.
{"title":"Master-less time synchronization for wireless sensor networks with generic topology","authors":"D. Fontanelli, D. Macii","doi":"10.1109/I2MTC.2012.6229552","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229552","url":null,"abstract":"Time synchronization in wireless sensor networks (WSN) is essential to schedule communication and distributed measurement tasks. In this paper a consensus-based synchronization algorithm is used to compensate dynamically both time offsets and clock frequency skews, thus driving all WSN clocks towards a common time scale. The proposed approach does not require either the election of a master node as a time reference for the whole network, or a specific synchronization protocol. Some simulation results show that the algorithm converges within a reasonable time, regardless of timestamping jitter, random communication latencies and incomplete node visibility.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123635792","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229275
R. Gelagaev, P. Jacqmaer, J. Everts, J. Driesen
For determining the dynamic on-resistance Rdyn,on of a power transistor, the voltage and current waveforms have to be measured during the switching operation. In measurements of voltage waveforms, using an oscilloscope, the characteristics of an amplifier inside the oscilloscope are distorted when the range of the measurement channel is not set wide enough to measure both on-state and off-state voltage, resulting in failure to accurately measure the voltage waveforms. A novel voltage clamp circuit improving the accuracy of the transistor on-state voltage measurement is presented. The measurement accuracy is improved by clamping the off-state voltage across the transistor to a lower voltage that is still greater than the on-state voltage. Unlike traditional clamping circuit, the presented voltage clamp circuit does not introduce delay caused by RC time constants keeping the voltage waveform clear even during state transitions of the evaluated semiconductor device for frequencies up to 1MHz.
{"title":"A novel voltage clamp circuit for the measurement of transistor dynamic on-resistance","authors":"R. Gelagaev, P. Jacqmaer, J. Everts, J. Driesen","doi":"10.1109/I2MTC.2012.6229275","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229275","url":null,"abstract":"For determining the dynamic on-resistance Rdyn,on of a power transistor, the voltage and current waveforms have to be measured during the switching operation. In measurements of voltage waveforms, using an oscilloscope, the characteristics of an amplifier inside the oscilloscope are distorted when the range of the measurement channel is not set wide enough to measure both on-state and off-state voltage, resulting in failure to accurately measure the voltage waveforms. A novel voltage clamp circuit improving the accuracy of the transistor on-state voltage measurement is presented. The measurement accuracy is improved by clamping the off-state voltage across the transistor to a lower voltage that is still greater than the on-state voltage. Unlike traditional clamping circuit, the presented voltage clamp circuit does not introduce delay caused by RC time constants keeping the voltage waveform clear even during state transitions of the evaluated semiconductor device for frequencies up to 1MHz.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123684285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229390
J. D. S. de Souza Neto, E. C. T. de Macedo, M. L. Batista, T. C. M. Cavalcanti, E. C. Guedes, J. S. da Rocha Neto, I. Glover
A low-cost, free-standing, radiometric, partial discharge wireless sensor network (PD WSN) is described for application to real-time condition monitoring, asset management and operations optimization in the future smart grid. The proposed PD WSN uses a novel approach to PD location which obviates the need for synchronization between sensors thereby improving scalability. Progress in the development of several components for a prototype PD WSN is described.
{"title":"Early progress in the development of a radiometric PD location system","authors":"J. D. S. de Souza Neto, E. C. T. de Macedo, M. L. Batista, T. C. M. Cavalcanti, E. C. Guedes, J. S. da Rocha Neto, I. Glover","doi":"10.1109/I2MTC.2012.6229390","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229390","url":null,"abstract":"A low-cost, free-standing, radiometric, partial discharge wireless sensor network (PD WSN) is described for application to real-time condition monitoring, asset management and operations optimization in the future smart grid. The proposed PD WSN uses a novel approach to PD location which obviates the need for synchronization between sensors thereby improving scalability. Progress in the development of several components for a prototype PD WSN is described.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124007536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229336
G. Betta, D. Capriglione, M. Corvino, C. Liguori, A. Paolillo
Nowadays, the matter of uncertainty in face recognition based biometric systems is a relevant issue for the scientific community. This is due to the even more increasing deployment of such systems in critical applications as safety, security and access control, to cite a few. In this context, the authors are engaged in the design of general methods for uncertainty modeling and evaluation aimed at realizing face recognition based biometric systems with built-in uncertainty evaluation capability. In this way, the output of a recognition system will not be the identity of the observed subject, but a confidence level for each possible subject. In previous papers the authors have identified the quantities of influence and have proposed a suitable uncertainty model. Core of the proposed model is the knowledge of the value assumed by the quantities of influence with respect to the corresponding values achieved in suitable reference conditions. This paper mainly analyzes these measurement issues, a fundamental step toward the development of such systems with built-in uncertainty evaluation capability. First results show a good agreement between statistical indicators and a priori estimations achieved with the proposed method.
{"title":"Estimation of influence quantities in face recognition","authors":"G. Betta, D. Capriglione, M. Corvino, C. Liguori, A. Paolillo","doi":"10.1109/I2MTC.2012.6229336","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229336","url":null,"abstract":"Nowadays, the matter of uncertainty in face recognition based biometric systems is a relevant issue for the scientific community. This is due to the even more increasing deployment of such systems in critical applications as safety, security and access control, to cite a few. In this context, the authors are engaged in the design of general methods for uncertainty modeling and evaluation aimed at realizing face recognition based biometric systems with built-in uncertainty evaluation capability. In this way, the output of a recognition system will not be the identity of the observed subject, but a confidence level for each possible subject. In previous papers the authors have identified the quantities of influence and have proposed a suitable uncertainty model. Core of the proposed model is the knowledge of the value assumed by the quantities of influence with respect to the corresponding values achieved in suitable reference conditions. This paper mainly analyzes these measurement issues, a fundamental step toward the development of such systems with built-in uncertainty evaluation capability. First results show a good agreement between statistical indicators and a priori estimations achieved with the proposed method.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124422993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2012-05-13DOI: 10.1109/I2MTC.2012.6229667
Weihua Li, Lijun Zhang, Yabing Xu
Many intelligent learning methods have been successfully applied in the gearbox fault diagnosis. Self-organizing map (SOM) is one of such learning methods which have been used effectively as it preserves the topological relationships of the data. A novel distance preserving SOM is investigated in mechanical fault diagnosis, and a LDA-DPSOM (linear discrimination analysis and distance preserving SOM) based diagnosis method is presented for gear incipient fault detection. Firstly, LDA is used to realize feature selection of the data set, so the dimension of produced data is much fewer than that of original data. Then the DPSOM method is applied to classifying the selected data and visualizing the classification result. Experiment results indicate the effectiveness of LDA-DPSOM for gearbox incipient fault diagnosis.
{"title":"Gearbox pitting detection using linear discriminant analysis and distance preserving self-organizing map","authors":"Weihua Li, Lijun Zhang, Yabing Xu","doi":"10.1109/I2MTC.2012.6229667","DOIUrl":"https://doi.org/10.1109/I2MTC.2012.6229667","url":null,"abstract":"Many intelligent learning methods have been successfully applied in the gearbox fault diagnosis. Self-organizing map (SOM) is one of such learning methods which have been used effectively as it preserves the topological relationships of the data. A novel distance preserving SOM is investigated in mechanical fault diagnosis, and a LDA-DPSOM (linear discrimination analysis and distance preserving SOM) based diagnosis method is presented for gear incipient fault detection. Firstly, LDA is used to realize feature selection of the data set, so the dimension of produced data is much fewer than that of original data. Then the DPSOM method is applied to classifying the selected data and visualizing the classification result. Experiment results indicate the effectiveness of LDA-DPSOM for gearbox incipient fault diagnosis.","PeriodicalId":387839,"journal":{"name":"2012 IEEE International Instrumentation and Measurement Technology Conference Proceedings","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125838878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}