Search results

Monitoring of a process leading to the detection of faults and determination of the root causes are essential for the production of consistent good quality end products with improved yield. The history of process monitoring fault detection (PMFD) strategies can be traced back to 1930s. Thereafter various tools, techniques and approaches were developed along with their application in diversified fields. The purpose of this paper is to make a review to categorize, describe and compare the various PMFD strategies.

Taxonomy was developed to categorize PMFD strategies. The basis for the categorization was the type of techniques being employed for devising the PMFD strategies. Further, PMFD strategies were discussed in detail along with emphasis on the areas of applications. Comparative evaluations of the PMFD strategies based on some commonly identified issues were also carried out. A general framework common to all the PMFD has been presented. And lastly a discussion into future scope of research was carried out.

The techniques employed for PMFD are primarily of three types, namely data driven techniques such as statistical model based and artificial intelligent based techniques, priori knowledge based techniques, and hybrid models, with a huge dominance of the first type. The factors that should be considered in developing a PMFD strategy are ease in development, diagnostic ability, fault detection speed, robustness to noise, generalization capability, and handling of nonlinearity. The review reveals that there is no single strategy that can address all aspects related to process monitoring and fault detection efficiently and there is a need to mesh the different techniques from various PMFD strategies to devise a more efficient PMFD strategy.

The review documents the existing strategies for PMFD with an emphasis on finding out the nature of the strategies, data requirements, model building steps, applicability and scope for amalgamation. The review helps future researchers and practitioners to choose appropriate techniques for PMFD studies for a given situation. Further, future researchers will get a comprehensive but precise report on PMFD strategies available in the literature to date.

The review starts with identifying key indicators of PMFD for review and taxonomy was proposed. An analysis was conducted to identify the pattern of published articles on PMFD followed by evolution of PMFD strategies. Finally, a general framework is given for PMFD strategies for future researchers and practitioners.

The purpose of this paper is to demonstrate the application of the control chart procedure to monitor the characteristics whose profile over time resembles a set of connected line segments.

Fit a regression spline model by taking the subgroup average of the characteristic as response variable and time as the explanatory variable. Then monitor the response variable using the regression spline control chart with the fitted model as center line and upper and lower control limits at three standard deviation units of the response variable above and below the center line.

The proposed chart is successfully deployed to monitor the daily response time profile of a client server of an application support process. The chart ensured the stability of the process as well as detected the assignable cause leading to the slowing down of the server performance.

The methodology can be used to monitor any characteristics whose performance profile over time resembles a set of connected line segments. Some of the examples are the consumption profile of utility providers like power distribution companies, usage profiles of telecom networks, loading profile of airline check-in process, e-commerce websites, etc.

To the best of the author’s knowledge, construction of control charts using regression spline is new. The usage of the control chart to monitor the performance characteristics which exhibits a nonlinear profile over time is also rare.

This paper aims to provide a novel integrated fault detection method for industrial process monitoring.

A novel integrated fault detection method based on the combination of Mallat (MA) algorithm, weight-elimination (WE) algorithm, conjugate gradient (CG) algorithm and multi-dimensional Taylor network (MTN) dynamic model, namely, MA-WE-CG-MTN, is proposed in this paper. First, MA algorithm is taken as data pre-processing. Second, in virtue of approximation ability and low computation complexity owing to the simple structure of MTN, MTN dynamic models are constructed for each frequency band. Furthermore, the CG algorithm is used to discipline the model parameters and the outputs of MTN model of each frequency band are gained. Third, the authors introduce the WE algorithm to cut down the number of middle layer nodes of MTN, reducing the complexity of the network. Finally, the outputs of MTN model for each frequency band are superimposed to achieve outputs of MTN model, and fault detection is proceeded by the residual error generator based on the difference between the output of MTN model and the actual output.

The novel proposed method is used to perform fault detection for industrial process monitoring effectively, such as the Benchmark Simulation Model 1 wastewater treatment process.

The novel proposed method has generality and provides considerably improved performance and effectiveness, which is used to perform fault detection for industrial process monitoring. The proposed method has good robustness, low complexity and easy implementation.

Different real cases indicate that the quality of a process is better monitored by a functional relationship rather than the traditional statistical process control (SPC) methods. This approach is referred to as profile monitoring. A serious objective in profile monitoring is the sensitivity of a model to very small changes of the process. The rapid progress of the precision manufacturing also indicates the importance of identifying very small shift types of a process/product profile curve. This sensitivity allows one to identify the fault of a process sooner compared to the case of lack of the capability.

This paper proposed a new method to monitor very small shift types of a polynomial profile for phase II of the SPC. The proposed method was named as MGWMA-PF. The performance capability of the proposed approach was evaluated through several numerical examples. A real case study was also used to investigate the capability of the proposed model.

The results addressed that the proposed method was capable of detecting very small shift types effectively. The numerical report based on the average run length (ARL) term revealed the more sensitivity of the proposed model compared to other existing methods of the literature.

This paper proposes a new method to monitor very small shift types of a polynomial profile for phase II of the SPC. The proposed method provides detecting a very small change manifested itself to the process.

This paper aims to enhance the reliability of self-validating multifunctional sensors.

An effective fault detection, isolation and data recovery (FDIR) strategy by using kernel principal component analysis (KPCA) coupled with gray bootstrap and fault reconstruction methods.

The proposed FDIR strategy is able to the address fault detection, isolation and data recovery problem of self-validating multifunctional sensors efficiently.

A KPCA-based model which can overcome the limitation of existing linear-based models is used to achieve the fault detection task. By using gray bootstrap method, the position of all faulty sensitive units can be calculated even under the multiple faults situation. A reconstruction-based contribution method is adopted to evaluate the amplitudes of the fault signals, and the fault-free output of the faulty sensitive units can be used to replace the fault output.

The purpose of this paper is to propose a approach for data visualization and industrial process monitoring.

A deep enhanced t-distributed stochastic neighbor embedding (DESNE) neural network is proposed for data visualization and process monitoring. The DESNE is composed of two deep neural networks: stacked variant auto-encoder (SVAE) and a deep label-guided t-stochastic neighbor embedding (DLSNE) neural network. In the DESNE network, SVAE extracts informative features of the raw data set, and then DLSNE projects the extracted features to a two dimensional graph.

The proposed DESNE is verified on the Tennessee Eastman process and a real data set of blade icing of wind turbines. The results indicate that DESNE outperforms some visualization methods in process monitoring.

This paper has significant originality. A stacked variant auto-encoder is proposed for feature extraction. The stacked variant auto-encoder can improve the separation among classes. A deep label-guided t-SNE is proposed for visualization. A novel visualization-based process monitoring method is proposed.

When a process experiences an out-of-control condition, identification of the change point is capable of leading practitioners to an effective root cause analysis. The change point addresses the time when a special cause(s) manifests itself into the process. In the statistical process monitoring when the chart signals an out-of-control condition, the change point analysis is an important step for the root cause analysis of the process. This paper attempts to propose a model approaching the artificial neural network to identify the change point of a multistage process with cascade property in the case that the process is modeled properly by a simple linear profile.

In practice, many processes can be modeled by a functional relationship rather than a single random variable or a random vector. This approach of modeling is referred to as the profile in the statistical process control literature. In this paper, two models based on multilayer perceptron (MLP) and convolutional neural network (CNN) approaches are proposed for identifying the change point of the profile of a multistage process.

The capability of the proposed models are evaluated and compared using several numerical scenarios. The numerical analysis of the proposed neural networks indicates that the two proposed models are capable of identifying the change point in different scenarios effectively. The comparative sensitivity analysis shows that the capability of the proposed convolutional network is superior compared to MLP network.

To the best of the authors' knowledge, this is the first time that: (1) A model is proposed to identify the change point of the profile of a multistage process. (2) A convolutional neural network is modeled for identifying the change point of an out-of-control condition.

This paper aims to evaluate innovation capability of companies based on comprehensive methods.

This paper used principal component analysis (PCA), kernel principal component analysis (KPCA) and principal component cluster (PCC) analysis to analyze the listed companies’ innovation capability. On these bases, mean method, Borda method, Copeland method, alienation coefficient method and fuzzy Borda method were used separately for the comprehensive evaluation.

The results show that the comprehensive evaluation can overcome the shortage of the single method and improve the reliability of the innovation ability evaluation. In addition, the method also reveals that the innovation ability of the listed companies is closely related to the innovation investment and their industry and further regional economic development level of each province (city and area).

This paper uses PCA, KPCA and PCC to evaluate and study their innovation ability. On the basis of these, five methods (mean method, Copeland method, Borda method, divorced coefficient method and fuzzy Borda method) are applied respectively to combine the sort results of PCA, KPCA and PCC. The results show that combination methods have better theoretical and practical significance for innovation ability.

This study constructs time series model, artificial neural networks (ANNs) and statistical topologies to examine the volatility and forecast foreign exchange rates. The Mauritian forex market has been utilized as a case study, and daily data for nominal spot rate (during a time period of five years spanning from 2014 to 2018) for EUR/MUR, GBP/MUR, CAD/MUR and AUD/MUR have been applied for the predictions.

Autoregressive integrated moving average (ARIMA) and generalized autoregressive conditional heteroskedasticity (GARCH) models are used as a basis for time series modelling for the analysis, along with the non-linear autoregressive network with exogenous inputs (NARX) neural network backpropagation algorithm utilizing different training functions, namely, Levenberg–Marquardt (LM), Bayesian regularization and scaled conjugate gradient (SCG) algorithms. The study also features a hybrid kernel principal component analysis (KPCA) using the support vector regression (SVR) algorithm as an additional statistical tool to conduct financial market forecasting modelling. Mean squared error (MSE) and root mean square error (RMSE) are employed as indicators for the performance of the models.

The results demonstrated that the GARCH model performed better in terms of volatility clustering and prediction compared to the ARIMA model. On the other hand, the NARX model indicated that LM and Bayesian regularization training algorithms are the most appropriate method of forecasting the different currency exchange rates as the MSE and RMSE seemed to be the lowest error compared to the other training functions. Meanwhile, the results reported that NARX and KPCA–SVR topologies outperformed the linear time series models due to the theory based on the structural risk minimization principle. Finally, the comparison between the NARX model and KPCA–SVR illustrated that the NARX model outperformed the statistical prediction model. Overall, the study deduced that the NARX topology achieves better prediction performance results compared to time series and statistical parameters.

The foreign exchange market is considered to be instable owing to uncertainties in the economic environment of any country and thus, accurate forecasting of foreign exchange rates is crucial for any foreign exchange activity. The study has an important economic implication as it will help researchers, investors, traders, speculators and financial analysts, users of financial news in banking and financial institutions, money changers, non-banking financial companies and stock exchange institutions in Mauritius to take investment decisions in terms of international portfolios. Moreover, currency rates instability might raise transaction costs and diminish the returns in terms of international trade. Exchange rate volatility raises the need to implement a highly organized risk management measures so as to disclose future trend and movement of the foreign currencies which could act as an essential guidance for foreign exchange participants. By this way, they will be more alert before conducting any forex transactions including hedging, asset pricing or any speculation activity, take corrective actions, thus preventing them from making any potential losses in the future and gain more profit.

This is one of the first studies applying artificial intelligence (AI) while making use of time series modelling, the NARX neural network backpropagation algorithm and hybrid KPCA–SVR to predict forex using multiple currencies in the foreign exchange market in Mauritius.

The purpose of this paper is to develop a comprehensive approach to efficiently integrate maintenance and operation by combining process and condition monitoring data with performance measures.

Intelligent stress, condition and health indicators have been developed for control and condition monitoring by combining generalised moments and norms with efficient nonlinear scaling. The data analysis resulting nonlinear scaling functions can also be used to handle performance measures used for management. The generalised norms provide limits for an advanced statistical process control.

The data‐driven analysis methodology demonstrates that management‐oriented indicators can be presented in the same scale as intelligent condition and stress indices. Control, condition monitoring, maintenance and performance monitoring are represented as interactive feedback loops.

Performance analysis can be based on real‐time information by using various stress, condition and health indices as inputs. Similar approaches can be used for outputs: quality indices, harmonised indices, key performance indicators, process capability indices and overall equipment effectiveness. Since consistent linguistic explanations based on nonlinear scaling are available for all these indices, the analysis can be further deepened with LE modelling. Efficient monitoring with intelligent indices provides a good basis for control and condition‐based maintenance and performance monitoring.

The paper extends the nonlinear scaling methodology and linguistic equations to intelligent performance measures. The methodology provides a consistent way to also represent all information with linguistic terms.