Novelty Detection Based Machine Health Prognostics

Filev, Dimitar; Tseng, Finn

doi:10.1109/isefs.2006.251161

Cited by 39 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fuzzy systems play an important role in the automatization of modeling and identification tasks, i.e., they are applied in areas such as identification [2] and system analysis (as they result in accurate models as well as linguistic interpretable models [3] in the form of rule bases, and therefore, may yield a better understanding of some underlying system behaviors than pure black box models), control [4], [5], fault detection [6], novelty detection [7], or classification [8]. In this sense, in order to cope with the online demands mentioned before, various approaches for the so-called evolving fuzzy and neurofuzzy systems were developed in the last decade, such as eTS [9] and its modified version Simp_eTS [10] for rule base simplification, the dynamic evolving neural-fuzzy inference system (DENFIS) [11], [12], online self-organizing fuzzy neural network (SOFNN) [13], statewide automated fingerprint identification system (SAFIS) [14], participatory evolving fuzzy modeling [15], DFNN [16] and its successor GDFNN [17], and the approach presented in [18].…”

Section: B Survey Over Currently Applied Methodsmentioning

confidence: 99%

FLEXFIS: A Robust Incremental Learning Approach for Evolving Takagi–Sugeno Fuzzy Models

Lughofer

2008

IEEE Trans. Fuzzy Syst.

307

105

View full text Add to dashboard Cite

In this paper, we introduce a new algorithm for incremental learning of a specific form of Takagi-Sugeno fuzzy systems proposed by Wang and Mendel in 1992. The new data-driven online learning approach includes not only the adaptation of linear parameters appearing in the rule consequents, but also the incremental learning of premise parameters appearing in the membership functions (fuzzy sets), together with a rule learning strategy in sample mode. A modified version of vector quantization is exploited for rule evolution and an incremental learning of the rules' premise parts. The modifications include an automatic generation of new clusters based on the nature, distribution, and quality of new data and an alternative strategy for selecting the winning cluster (rule) in each incremental learning step. Antecedent and consequent learning are connected in a stable manner, meaning that a convergence toward the optimal parameter set in the least-squares sense can be achieved. An evaluation and a comparison to conventional batch methods based on static and dynamic process models are presented for high-dimensional data recorded at engine test benches and at rolling mills. For the latter, the obtained data-driven fuzzy models are even compared with an analytical physical model. Furthermore, a comparison with other evolving fuzzy systems approaches is carried out based on nonlinear dynamic system identification tasks and a three-input nonlinear function approximation example.Index Terms-Convergence to optimality, incremental clustering, robust evolving fuzzy models, static and dynamic process modeling, Takagi-Sugeno fuzzy systems.

show abstract

Section: B Survey Over Currently Applied Methodsmentioning

confidence: 99%

FLEXFIS: A Robust Incremental Learning Approach for Evolving Takagi–Sugeno Fuzzy Models

Lughofer

2008

IEEE Trans. Fuzzy Syst.

307

105

View full text Add to dashboard Cite

show abstract

“…This section is dedicated to review some of the research work which conducted for this task. The algorithm proposed by Filev and Tseng (2006) can be used for online anomaly detection. It is not based on any learning algorithm, instead, the algorithm decides different operation modes once it starts running on N observations.…”

Section: Anomaly Detectionmentioning

confidence: 99%

Unsupervised Trend Extraction for Prognostics and Condition Assessment

Mosallam

Medjaher

Zerhouni

2012

IFAC Proceedings Volumes

View full text Add to dashboard Cite

Maintenance is becoming more expensive nowadays due to the increased complexity in design and function of industrial systems. Continuous health monitoring is thus of high importance to increase the availability of industrial systems and consequently reduce the costs. This paper presents an algorithm for unsupervised trends extraction from multidimensional sensory data so as to use such trend in machinery health monitoring and maintenance needs. The proposed method does not assume any prior knowledge about the nature and type of the input signals. It is based on extracting successive multi-dimensional features from machinery sensory signals. Then, unsupervised feature selection on the features domain is applied without making any assumptions concerning the source of the signals and the number of the extracted features. Finally, empirical mode decomposition algorithm (EMD) is applied on the projected features with the purpose of following the evolution of data in a compact representation over time. The algorithm is demonstrated on accelerated degradation dataset of bearings acquired from PRONOSTIA experimental platform and a second dataset acquired form NASA repository where it is shown to be able to extract interesting signal trends.

show abstract

“…The baseline characteristics are essentially the means of the features collected during the setup or initialization phase. The diagnostic capabilities of the conventional predictive maintenance systems are based on applying different types of thresholds, templates, and rules to quantify the relationship between the current feature values and their baseline counterparts [15]. During the course of operation of the equipment, the thresholds remain usually unchanged (unless an expert interferes to force their recalculation) although the machine characteristics gradually change resulting in false alarms.…”

Section: Novelty Detection Framework (Ndf)mentioning

confidence: 99%

“…The cause for such a change can be a new OM, and/or an outlier, and/or a fault. NDF employs the procedure described in [15] for the detection and formation of new OM clusters during the creation phase. Essentially, a new OM is created when a number of repetitive observations have fallen into a new region of unoccupied space in OM space, the threshold being a function of the dimensionality of the OM space.…”

Section: Novelty Detection Framework (Ndf)mentioning

confidence: 99%

An Industrial Strength Novelty Detection Framework for Autonomous Equipment Monitoring and Diagnostics

Filev

Chinnam

Tseng

et al. 2010

IEEE Trans. Ind. Inf.

Self Cite

View full text Add to dashboard Cite

This paper presents a practical framework for autonomous monitoring of industrial equipment based on novelty detection. It overcomes limitations of current equipment monitoring technology by developing a "generic" structure that is relatively independent of the type of physical equipment under consideration. The kernel of the proposed approach is an "evolving" model based on unsupervised learning methods (reducing the need for human intervention). The framework employs procedures designed to temporally evolve the critical model parameters with experience for enhanced monitoring accuracy (a critical ability for mass deployment of the technology on a variety of equipment/hardware without needing extensive initial tune-up). Proposed approach makes explicit provision to characterize the distinct operating modes of the equipment, when necessary, and provides the ability to predict both abrupt as well as gradually developing (incipient) changes. The framework is realized as an autonomous software agent that continuously updates its decision model implementing an unsupervised recursive learning algorithm. Results of validation of the proposed methodology by accelerated testing experiments are also discussed.

show abstract

Novelty Detection Based Machine Health Prognostics

Cited by 39 publications

References 6 publications

FLEXFIS: A Robust Incremental Learning Approach for Evolving Takagi–Sugeno Fuzzy Models

FLEXFIS: A Robust Incremental Learning Approach for Evolving Takagi–Sugeno Fuzzy Models

Unsupervised Trend Extraction for Prognostics and Condition Assessment

An Industrial Strength Novelty Detection Framework for Autonomous Equipment Monitoring and Diagnostics

Contact Info

Product

Resources

About