Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods

Aldrich, Chris; Auret, Lidia

doi:10.1007/978-1-4471-5185-2

Cited by 93 publications

(73 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this equation, y = ∑ ( ) ⁄ and = ∑ { ( ) − y } ( − 1) ⁄ are the sample (time series) mean and sample (time series) variance. This approach is often used to estimate the minimum lag in a sense such that the time series y( ), = 1, 2, … , and its lagged counterpart y( − ) become independent of one another [11].…”

Section: Segmentation Of Time Series Datamentioning

confidence: 99%

“…. , N and its lagged counterpart y(n − b) become independent of one another [11]. Alternatively, the value of b can be determined empirically as a problem-dependent parameter that needs to be optimized over a certain range [1, N − 1].…”

Section: Segmentation Of Time Series Datamentioning

confidence: 99%

“…The observations of the variables and their lagged copies yield a so-called lagged trajectory matrix that represents a trajectory of the evolution of the dynamical system represented by the observed time series [11].…”

Section: Delay Vector or Lagged Trajectory Coordinatesmentioning

confidence: 99%

See 2 more Smart Citations

Predicting the Operating States of Grinding Circuits by Use of Recurrence Texture Analysis of Time Series Data

2018

Self Cite

View full text Add to dashboard Cite

Abstract:Grinding circuits typically contribute disproportionately to the overall cost of ore beneficiation and their optimal operation is therefore of critical importance in the cost-effective operation of mineral processing plants. This can be challenging, as these circuits can also exhibit complex, nonlinear behavior that can be difficult to model. In this paper, it is shown that key time series variables of grinding circuits can be recast into sets of descriptor variables that can be used in advanced modelling and control of the mill. Two real-world case studies are considered. In the first, it is shown that the controller states of an autogenous mill can be identified from the load measurements of the mill by using a support vector machine and the abovementioned descriptor variables as predictors. In the second case study, it is shown that power and temperature measurements in a horizontally stirred mill can be used for online estimation of the particle size of the mill product.

show abstract

Section: Segmentation Of Time Series Datamentioning

confidence: 99%

Section: Segmentation Of Time Series Datamentioning

confidence: 99%

See 1 more Smart Citation

Predicting the Operating States of Grinding Circuits by Use of Recurrence Texture Analysis of Time Series Data

2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, Willersrud et al [12] developed the GLRT to make efficient downhole drilling washout detection with the multivariate t-distribution; Reñones et al [6] used the CUSUM analysis for multi-tooth machine tool fault detection. Although these methods have been experimentally demonstrated the effectiveness in various fields, due to the requirement of data after change point, a large detection delay is an essential limitation of these methods for real applications [13]. On the other hand, real-time change detection aims to detect changes as soon as possible when a change occurs, this requirement is crucial in many real-life scenarios such as security monitoring [14,15], health care [16,17], automated factory [18,19] as well as machine operation monitoring studied in this paper.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Change Detection for Long-Term Machinery Monitoring Using Incremental Sliding-Window

Wang

Liu

et al. 2017

Chin. J. Mech. Eng.

View full text Add to dashboard Cite

Detection of structural changes from an operational process is a major goal in machine condition monitoring. Existing methods for this purpose are mainly based on retrospective analysis, resulting in a large detection delay that limits their usages in real applications. This paper presents a new adaptive real-time change detection algorithm, an extension of the recent research by combining with an incremental sliding-window strategy, to handle the multi-change detection in long-term monitoring of machine operations. In particular, in the framework, Hilbert space embedding of distribution is used to map the original data into the Re-producing Kernel Hilbert Space (RKHS) for change detection; then, a new adaptive threshold strategy can be developed when making change decision, in which a global factor (used to control the coarse-to-fine level of detection) is introduced to replace the fixed value of threshold. Through experiments on a range of real testing data which was collected from an experimental rotating machinery system, the excellent detection performances of the algorithm for engineering applications were demonstrated. Compared with state-ofthe-art methods, the proposed algorithm can be more suitable for long-term machinery condition monitoring without any manual re-calibration, thus is promising in modern industries.

show abstract

“…The data-driven-based multivariate statistical process control (MSPC) techniques show superiority in industrial process monitoring [1][2][3][4][5][6][7]. Numerous process variables in chemical processes can been totally measured, which provide reliable basis for characterizing the process condition.…”

Section: Introductionmentioning

confidence: 99%

Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection

Miao

Song

et al. 2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Unsupervised Process Monitoring and Fault Diagnosis with Machine Learning Methods

Cited by 93 publications

References 0 publications

Predicting the Operating States of Grinding Circuits by Use of Recurrence Texture Analysis of Time Series Data

Predicting the Operating States of Grinding Circuits by Use of Recurrence Texture Analysis of Time Series Data

Adaptive Change Detection for Long-Term Machinery Monitoring Using Incremental Sliding-Window

Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection

Contact Info

Product

Resources

About