Khaldi, Belkacem; Harrou, Fouzi; Sun, Ying; Cherif, Foudil(2017 6th International Conference on Systems and Control (ICSC), Institute of Electrical and Electronics Engineers (IEEE), 2017-07-10)[Conference Paper]
Swarm robotics requires continuous monitoring to detect abnormal events and to sustain normal operations. Indeed, swarm robotics with one or more faulty robots leads to degradation of performances complying with the target requirements. This paper present an innovative data-driven fault detection method for monitoring robots swarm. The method combines the flexibility of principal component analysis (PCA) models and the greater sensitivity of the exponentially-weighted moving average control chart to incipient changes. We illustrate through simulated data collected from the ARGoS simulator that a significant improvement in fault detection can be obtained by using the proposed methods as compared to the use of the conventional PCA-based methods.
Harrou, Fouzi; Sun, Ying(2016 IEEE 14th International Conference on Industrial Informatics (INDIN), Institute of Electrical and Electronics Engineers (IEEE), 2017-01-20)[Conference Paper]
Fault detection is important for safe operation of various modern engineering systems. Partial least square (PLS) has been widely used in monitoring highly correlated process variables. Conventional PLS-based methods, nevertheless, often fail to detect incipient faults. In this paper, we develop new PLS-based monitoring chart, combining PLS with multivariate memory control chart, the multivariate exponentially weighted moving average (MEWMA) monitoring chart. The MEWMA are sensitive to incipient faults in the process mean, which significantly improves the performance of PLS methods and widen their applicability in practice. Using simulated distillation column data, we demonstrate that the proposed PLS-based MEWMA control chart is more effective in detecting incipient fault in the mean of the multivariate process variables, and outperform the conventional PLS-based monitoring charts.
Harrou, Fouzi; Madakyaru, Muddu; Sun, Ying(2016 IEEE Symposium Series on Computational Intelligence (SSCI), Institute of Electrical and Electronics Engineers (IEEE), 2017-02-16)[Conference Paper]
This paper proposes an efficient data-based anomaly detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions. The performances of the developed anomaly detection using NLPLS-based HD technique is illustrated using simulated plug flow reactor data.
Madakyaru, Muddu; Harrou, Fouzi; Sun, Ying(2016 IEEE Symposium Series on Computational Intelligence (SSCI), Institute of Electrical and Electronics Engineers (IEEE), 2017-02-16)[Conference Paper]
Process monitoring has a central role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. In this paper, a statistical approach that exploit the advantages of multiscale PLS models (MSPLS) and those of a generalized likelihood ratio (GLR) test to better detect anomalies is proposed. Specifically, to consider the multivariate and multi-scale nature of process dynamics, a MSPLS algorithm combining PLS and wavelet analysis is used as modeling framework. Then, GLR hypothesis testing is applied using the uncorrelated residuals obtained from MSPLS model to improve the anomaly detection abilities of these latent variable based fault detection methods even further. Applications to a simulated distillation column data are used to evaluate the proposed MSPLS-GLR algorithm.
Harrou, Fouzi; Dairi, Abdelkader; Sun, Ying; Kadri, Farid(IEEE Sensors Journal, Institute of Electrical and Electronics Engineers (IEEE), 2018-07-02)[Article]
Air quality management and monitoring are vital to maintaining clean air, which is necessary for the health of human, vegetation, and ecosystems. Ozone pollution is one of the main pollutants that negatively affect human health and ecosystems. This paper reports the development of an unsupervised and efficient scheme to detecting anomalies in unlabelled ozone measurements. This scheme combines a Deep Belief Networks (DBN) model and a one-class support vector machine (OCSVM). The DBN model accounts for nonlinear variations in the ground-level ozone concentrations, while OCSVM detects the abnormal ozone measurements. The performance of this approach is evaluated using real data from Is`ere in France. We also compare the detection quality of DBN-based detection schemes to that of deep stacked auto-encoders, Restricted Boltzmann Machinesbased OCSVM and DBN-based clustering procedures (i.e., Kmeans, Birch and Expectation Maximization). The results show that the developed strategy is able to identify anomalies in ozone measurements.
Abdelhafid, Zeroual; Harrou, Fouzi; Sun, Ying(2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B), Institute of Electrical and Electronics Engineers (IEEE), 2017-12-14)[Conference Paper]
In this paper, we propose an effective approach which has to detect traffic congestion. The detection strategy is based on the combinational use of piecewise switched linear traffic (PWSL) model with exponentially-weighted moving average (EWMA) chart. PWSL model describes traffic flow dynamics. Then, PWSL residuals are used as the input of EWMA chart to detect traffic congestions. The evaluation results of the developed approach using data from a portion of the I210-W highway in Califorina showed the efficiency of the PWSL-EWMA approach in in detecting traffic congestions.
Export search results
The export option will allow you to export the current search results of the entered query to a file. Different
formats are available for download. To export the items, click on the button corresponding with the preferred download format.
By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.
For anonymous users the allowed maximum amount is 50 search results.
To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export.
The amount of items that can be exported at once is similarly restricted as the full export.
After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.