Search

We present an overview of predictive maintenance (PdM) in industrial operations, highlighting its evolution, benefits, challenges, and potential economic impact. It is assessed that there are considerable benefits associated with PdM but also its practical implementation can prove difficult due to the uncertain benefits of its application, the need for advanced IT infrastructure as well as expert personnel, and, perhaps most importantly, a lack of failure-related data for the PdM model training. We conclude with three PdM case studies to elaborate on some of the issues discussed throughout the paper. [ABSTRACT FROM AUTHOR]

The concurrent use of statistical process control and engineering process control involves monitoring manipulated and controlled variables. One multivariate control chart may handle the statistical monitoring of all variables, but observing the manipulated and controlled variables in separate control charts may improve understanding of how disturbances and the controller performance affect the process. In this article, we illustrate how step and ramp disturbances manifest themselves in a single‐input–single‐output system by studying their resulting signatures in the controlled and manipulated variables. The system is controlled by variations of the widely used proportional‐integral‐derivative(PID) control scheme. Implications for applying control charts for these scenarios are discussed. [ABSTRACT FROM AUTHOR]

Engineering process control and high-dimensional, time-dependent data present great methodological challenges when applying statistical process control (SPC) and design of experiments (DoE) in continuous industrial processes. Process simulators with an ability to mimic these challenges are instrumental in research and education. This article focuses on the revised Tennessee Eastman process simulator providing guidelines for its use as a testbed for SPC and DoE methods. We provide flowcharts that can support new users to get started in the Simulink/Matlab framework, and illustrate how to run stochastic simulations for SPC and DoE applications using the Tennessee Eastman process. [ABSTRACT FROM AUTHOR]

This study compares four models for industrial condition monitoring including a principal components analysis (PCA) approach and three deep learning models, one of which is a new, lightweight version of another. We also propose a simple attention mechanism for enchancing deep learning models with better predictions and feature importance. Two datasets are used, one simulated from the Tennessee Eastman Process, the other from two feedwater pumps at a Danish combined heat and power plant. Our final results show evidence in favour of the PCA-based approach as it has detection ability comparable to the deep learning approaches as well as faster training time, fewer hyperparameters, as well as robustness to changing operating conditions. We conclude the paper by putting into perspective the importance of building up complexity incrementally with a recommendation to start modelling with simpler and well-tested models before the adoption of more advanced, less transparent models. • A statistical model is compared with deep learning techniques for fault detection. • The principal components model's fault detection is as good as deep learning. • Deep learning method, ARGUELite, shows promise for single regime datasets. • A unique dataset from a power plant feedwater pump was used for model evaluation. [ABSTRACT FROM AUTHOR]

When principal component analysis (PCA) is used for statistical process monitoring it relies on the assumption that data are time independent. However, industrial data will often exhibit serial correlation. Dynamic PCA (DPCA) has been suggested as a remedy for high-dimensional and time-dependent data. In DPCA the input matrix is augmented by adding time-lagged values of the variables. In building a DPCA model the analyst needs to decide on (1) the number of lags to add, and (2) given a specific lag structure, how many principal components to retain. In this article we propose a new analyst driven method to determine the maximum number of lags in DPCA with a foundation in multivariate time series analysis. The method is based on the behavior of the eigenvalues of the lagged autocorrelation and partial autocorrelation matrices. Given a specific lag structure we also propose a method for determining the number of principal components to retain. The number of retained principal components is determined by visual inspection of the serial correlation in the squared prediction error statistic, Q (SPE), together with the cumulative explained variance of the model. The methods are illustrated using simulated vector autoregressive and moving average data, and tested on Tennessee Eastman process data. [ABSTRACT FROM AUTHOR]

A basic assumption when using principal component analysis (PCA) for inferential purposes, such as in statistical process control (SPC), is that the data are independent in time. In many industrial processes, frequent sampling and process dynamics make this assumption unrealistic rendering sampled data autocorrelated (serially dependent). PCA can be used to reduce data dimensionality and to simplify multivariate SPC. Although there have been some attempts in the literature to deal with autocorrelated data in PCA, we argue that the impact of autocorrelation on PCA and PCA-based SPC is neither well understood nor properly documented. This article illustrates through simulations the impact of autocorrelation on the descriptive ability of PCA and on the monitoring performance using PCA-based SPC when autocorrelation is ignored. In the simulations, cross-correlated and autocorrelated data are generated using a stationary first-order vector autoregressive model. The results show that the descriptive ability of PCA may be seriously affected by autocorrelation causing a need to incorporate additional principal components to maintain the model's explanatory ability. When all variables have equal coefficients in a diagonal autoregressive coefficient matrix, the descriptive ability is intact, while a significant impact occurs when the variables have different degrees of autocorrelation. We also illustrate that autocorrelation may impact PCA-based SPC and cause lower false alarm rates and delayed shift detection, especially for negative autocorrelation. However, for larger shifts, the impact of autocorrelation seems rather small. © 2015 The Authors. Quality and Reliability Engineering International published by John Wiley & Sons Ltd. [ABSTRACT FROM AUTHOR]

One of the basic assumptions for traditional univariate and multivariate control charts is that the data are independent in time. For the latter, in many cases, the data are serially dependent (autocorrelated) and cross-correlated because of, for example, frequent sampling and process dynamics. It is well known that the autocorrelation affects the false alarm rate and the shift-detection ability of the traditional univariate control charts. However, how the false alarm rate and the shift-detection ability of the Hotelling T² control chart are affected by various autocorrelation and cross-correlation structures for different magnitudes of shifts in the process mean is not fully explored in the literature. In this article, the performance of the Hotelling T² control chart for different shift sizes and various autocorrelation and cross-correlation structures are compared based on the average run length using simulated data. Three different approaches in constructing the Hotelling T² chart are studied for two different estimates of the covariance matrix: (i) ignoring the autocorrelation and using the raw data with theoretical upper control limits; (ii) ignoring the autocorrelation and using the raw data with adjusted control limits calculated through Monte Carlo simulations; and (iii) constructing the control chart for the residuals from a multivariate time series model fitted to the raw data. To limit the complexity, we use a first-order vector autoregressive process and focus mainly on bivariate data. [ABSTRACT FROM AUTHOR]

• An unsupervised fault detection and diagnosis scheme based on orthogonal autoencoders is proposed for the monitoring of industrial and chemical processes. • The use of integrated gradients allows for exploration of the bottleneck of the autoencoder, providing candidate variables for the root cause analysis. • The proposed method performs well compared to traditional methods in offering compelling and interpretable results. • The analysis shows how the difference in the way faults are introduced affects the detection and diagnosis performances of principal component analysis-based control charts. In recent years, there have been studies focusing on the use of different types of autoencoders (AEs) for monitoring complex nonlinear data coming from industrial and chemical processes. However, in many cases the focus was placed on detection. As a result, practitioners are encountering problems in trying to interpret such complex models and obtaining candidate variables for root cause analysis once an alarm is raised. This paper proposes a novel statistical process control (SPC) framework based on orthogonal autoencoders (OAEs). OAEs regularize the loss function to ensure no correlation among the features of the latent variables. This is extremely beneficial in SPC tasks, as it allows for the invertibility of the covariance matrix when computing the Hotelling T 2 statistic, significantly improving detection and diagnosis performance when the process variables are highly correlated. To support the fault diagnosis and identification analysis, we propose an adaptation of the integrated gradients (IG) method. Numerical simulations and the benchmark Tennessee Eastman Process are used to evaluate the performance of the proposed approach by comparing it to traditional approaches as principal component analysis (PCA) and kernel PCA (KPCA). In the analysis, we explore how the information useful for fault detection and diagnosis is stored in the intermediate layers of the encoder network. We also investigate how the correlation structure of the data affects the detection and diagnosis of faulty variables. The results show how the combination of OAEs and IG represents a compelling and ready-to-use solution, offering improved detection and diagnosis performances over the traditional methods. [ABSTRACT FROM AUTHOR]

The article focuses on the importance of time series analysis on modern quality monitoring and control. It discusses the effect of autocorrelation on statistical process control procedures based on a number of modern feedback control concepts and algorithms. A detailed analysis of a time series example, the Series C, from the seminal book on time series by G. E. Box and G. M. Jenkins is provided. Several charts are also supplied to illustrate how a time series plot can be used as a functional tool for determining stationarity.

*Edited by Søren Bisgaard [ABSTRACT FROM AUTHOR]

Demonstrates the use of an alternative tool called the variogram which can be helpful in determining whether a process is stationary or not in statistical quality control. Temperature readings from a ceramic furnace; Periodicities in stationary processes; Time series of furnace temperature.

*Edited by George Box and Søren Bisgaard [ABSTRACT FROM AUTHOR]

This paper presents a case study on condition monitoring of power generators at offshore wind turbines. Two fault detection models are proposed for detecting sudden changes in the sensed value of metallic debris at the generator. The first model uses an exponentially weighted moving average, while the second monitors first-order derivatives using a fixed threshold. This is expected to improve the maintenance activities by avoiding late or early part replacement. The economic impact of the proposed approach is also provided with a realistic depiction of the cost structure associated with the corresponding maintenance plan. While the specifics of the case study are supported by real-life data, considering the prevalence of the use of generators not only in offshore wind turbines but also in other production environments, we believe the case study covered in this paper can be used as a blueprint for similar studies in other applications. • Large scale condition monitoring demonstrates economic benefits. • Case study from real wind turbine population with economic impact assessment. • Sensor for monitoring fault mode results in lead time for maintenance planning. • Sensitivity analysis assesses results despite downtime and power price uncertainty. [ABSTRACT FROM AUTHOR]