Mojtaba Kordestani

Design of online soft sensors based on combined adaptive PCA and RBF neural networks

An accurate on-line measurement of important quality variables is essential for successful monitoring and controlling of chemical processes. However, these variables are usually difficult to measure on-line due to the practical limitations such as the time-delay, high cost and reliability considerations. To overcome this problem, two online soft sensors are proposed based upon a combined adaptive principal component analysis (PCA) and a radial basis functions (RBF) artificial neural network. For this purpose, a recursive PCA and a PCA based on a sliding window scheme are presented to adaptively extract the inherent features inside the measurements with high dimensions. The extracted low-dimension features are then used recursively as the main inputs to the RBF neural network. The developed online soft sensors are finally tested on a highly nonlinear distillation column benchmark problem to illustrate their effective performances. The simulation results demonstrate the superiority of the proposed soft sensor based on the combined recursive PCA and the RBF neural network.

Improved power curve monitoring of wind turbines

Wind turbine power output monitoring can detect anomalies in turbine performance which have the potential to result in unexpected failure. This study examines common Supervisory Control And Data Acquisition data over a period of 20 months. It is common to have more than 150 signals acquired by Supervisory Control And Data Acquisition systems, and applying all is neither practical nor useful. Thus, to address the issue, correlation coefficients analysis has been applied in this work to reveal the most influential parameters on wind turbine active power. Then, radial basis function and multilayer perception artificial neural networks are set up, and their performance is compared in two static and dynamic states. The proposed combination of the feature selection method and the dynamic multilayer perception neural network structure has performed well with favorable prediction error levels compared to other methods. Thus, the combination may be a valuable tool for turbine power curve monitoring.

Novel Multiagent Model-Predictive Control Performance Indices for Monitoring of a Large-Scale Distributed Water System

High-order, often distributed, dynamical systems composed of several interconnected subsystems are often referred to as large-scale systems (LSSs). LSSs are often hard to control with a single centralized controller due to the complexity imposed by the systems dimensionality and distributedness. As a result, decentralized or hierarchical control schemes are employed in controlling LSSs. Control performance assessment (CPA) is an important strategy to analyze the efficiency of controllers in LSSs. This paper presents CPA for the Rhine–Meuse Delta water system in The Netherlands. The water system consists of a large number of rivers and sea outlets with barriers and sluices. A flood in this area can damage the ecosystem and cities around it. Thus, it is essential to control this LSS in a way to protect the distributed water system against floods. For this purpose, a multiagent predictive control is developed to control the subsystems in the LSS. Further, two novel control performance indices (CPIs) based on the model-predictive control strategy are introduced to monitor the performance of the controllers and detect any changes in the system. Finally, the root cause of controller deficiencies is diagnosed. The suggested CPIs are compared with a historical performance index. Simulation results show the ability and effectiveness of the proposed CPIs in comparison with the performance measure used in the past.

A new clustering method using wavelet based probability density functions for identifying patterns in time-series data

Clustering is a prominent method to identify similar patterns in large groups of data and can be beneficial in the bioinformatics studies due to this property. Classical methods such as k-means and maximum likelihood consider a mixture of Gaussian probability density function (PDF) of data and find clusters based on maximizing the PDF. However, correlation among different groups of data and existence of noise on the data make it difficult to correctly detect the correct number of clusters. Furthermore, the assumption of the Gaussian distance for the PDF is not necessarily true in real applications. This paper presents a new clustering method via wavelet-based probability density functions. For this purpose, first, a mixture of PDFs is estimated by the wavelet for each feature. After this, a multilevel thresholding method is implemented on the mixture of PDFs of each feature to obtain the clusters. Finally, a forward feature selection with memory is used to cluster the dataset based on combinations of the features. The profile alignment and agglomerative clustering (PAAC) index is applied for evaluating the number of clusters and features. Transcript expression throughout the various stages of prostate cancer is considered as a case study to identify patterns. The experimental results show the ability of the proposed method in detecting patterns of similar transcripts throughout disease progression. The results are promising in comparison with the other methods.

A non-iterative LMI based PID power system stabilizer

This paper presents a new method of designing a robust PID power system stabilizer. This methodology provides an exact way to tune PID parameters and find an optimal controller using non-iterative Linear Matrix Inequality (LMI) approach. The uncertainties inherent in the system model is also taken into account in the design process to increase the robustness of the proposed controller. For this purpose, H∞ control theory is employed in a LMI framework to design a PID controller that damp oscillations in power system and makes it robust against uncertainty. The obtained matrix inequality is nonlinear which is converted to a LMI in the proposed framework. The Simulation results show the superior performance of the controller compared to conventional method in tuning of PID controller.