The National Technical University of Athens Unit of Process Control and Informatics

1. The National Technical University of Athens Unit of Process Control and Informatics Bucharest, February 2009

2. NTUA- The University The National Technical University of Athens The National Technical University (NTUA) is the oldest and most prestigious educational institution of Greece in the field of technology, and has contributed unceasingly to the country's scientific, technical and economic development since its foundation in 1836. • The University comprises nine departments, each one covering a different aspect of the engineering field, from electrical engineering and computer science to civil engineering. Over 700 academic staff members are involved in the education of more than 12,000 students in NTUA undergraduate, postgraduate and continuing education programs. • During the last three decades, NTUA has developed an extensive research and development activity in numerous fields, with all departments contributing to the evolution of new theories, technologies and solutions for problems broadly related to the engineering sciences.

3. NTUA Unit of Process Control and Informatics The Unit of Process Control and Informatics The Unit of Process Control and Informatics is part of the School of Chemical Engineering at NTUA. It involves two faculty member, three research associates at Ph.D. level and several postgraduate and undergraduate students. The Unit of Process Control and Informatics covers all process control courses in the curriculum of the School of Chemical Engineering. In recent years, the Laboratory’s research profile has grown and diversified, to follow the rapid evolution of system modeling, identification, optimization and control. The Laboratory’s research activities span the full range of directions, from production planning and inventory control to the development of chemo-informatics tools. This activity has led to over 60 publications in top scientific journals and numerous presentations in international conferences.

4. NTUA Unit of Process Control and Informatics Research projects in the Unit of Process Control and Informatics The Unit of Process Control and Informatics has participated in a large number of research projects partially funded by the E.U. and national organisations, in co-operation with other Universities and companies.The Unit is already participating in an FP7 project: Development of systems for sales volume prediction and plant production planning using artificial intelligence methodologies (PENED) Robust optimal control and convex optimization: A Unified approach (LEFKIPPOS) Solving mixed integer and nonlinear programming problems by genetic algorithms (THALIS) Stochastic optimal control of constrained jump linear systems: Explicit solution via dynamic programming and multi-parametric optimization (EPAN) Development of chemoinformatics software: Modelling, Virtual screening and design of new molecules with desired (PLHPI) An Operational System for Planning and Decision Support in Wildfire Management (EPAN) OpenTox – An Open Source Predictive Toxicology Framework (FP7-Coopearation-Health)

5. NTUA Unit of Process Control and Informatics Research interests in the Unit of Process Control and Informatics Mathematical modeling of systems and processes:We have developed a numbers of machine learning and artificial intelligence methodologies for modeling and classifications. These methods and other standard statistical learning and machine learning methods (such as support vector machines and chemometrics tools) have been used for the development of mathematical models for the following systems: Identification of industrial process Development of Quantitative-Structure-Analysis-Relationships which are very useful in the process of designing new pharmaceutical molecules Prediction of fuel and polymer properties Extraction of time-series models Development of image processing tools Simulation of forest fire propagation Mathematical optimization:Development of mathematical programming models for systems and processes and evolutionary stochastic algorithms for locating their solution. Minimization of production cost and energy consumption in industries Solution of Vehicle Routing problems Determination of nucleotide sequences in DNA analysis. Process Control:New process control methodologies have been developed with emphasis on Model Predictive Control methodologies which are of particular interest for the chemical industry: Fuzzy model predictive control methodology. MPC based on neural network dynamic models Robust MPC for non-square systems Adaptive MPC MPC and H control for distributed parameter systems Production planning and inventory control Optimal management and control of energy systems

6. NTUA Unit of Process Control and Informatics Research directions Optimal control of hybrid systemsWe have developed multiparametric optimization algorithms and solved optimal control problems for a variety of discrete-time dynamical systems such as markov jump linear systems and switched linear systems subject to control and state constraints. The approach relies on the formulation of the optimal control problems in a dynamic programming framework and the solution of the dynamic programming subproblems via in-house developed multiparametric programming algorithms. The methods led to the solution of some optimal control problems that have never been tackled in the literature or thought to be intractable. Furthermore, the solution to these optimal control problems is computed off-line thus making the techniques applicable to systems with fast dynamics.

7. NTUA Unit of Process Control and Informatics Research directions Optimal control of nonlinear distributed parameter systemsThe radial basis function neural network architecture has been used to model the dynamics of Distributed Parameter Systems (DPSs). Two pure data driving schemes which do not require knowledge of the governing equations have been developed. In the first method, the neural network methodology generates the full model of the system that is able to predict the process outputs at any spatial point. Past values of the process inputs and the coordinates of the specific location provide the input information to the model. The second method uses empirical basis functions produced by the Singular Value Decomposition (SVD) on the snapshot matrix to describe the spatial behavior of the system, while the neural network model is used to estimate only the temporal coefficients. The models produced by both methods are then implemented in Model Predictive Control (MPC) configurations, suitable for constrained DPSs.  An alternative control strategy has been developed by transforming the nonlinear model into a nonlinear state space formulation, which in turn is used for deriving a robust H∞ control law.

8. NTUA Unit of Process Control and Informatics Research directions Fuzzy model predictive control A popular methodology has been developed based on a dynamic fuzzy model of the process to be controlled, which is used for predicting the future behavior of the output variables. A nonlinear optimization problem is then formulated, which minimizes the difference between the model predictions and the desired trajectory over the prediction horizon and the control energy over a shorter control horizon. The problem is solved on line using a specially designed genetic algorithm, which has a number of advantages over conventional nonlinear optimization techniques. The method can be used with any type of fuzzy model and is particularly useful when a direct fuzzy controller cannot be designed due to the complexity of the process and the difficulty in developing fuzzy control rules.

9. NTUA Unit of Process Control and Informatics Research directions Development of training algorithms for artificial neural networks and fuzzy logic systems Three training algorithms for radial basis function neural networks have been developed. The fuzzy means algorithm uses a fuzzy partition of the input space and combines self-organized and supervised learning. For a given fuzzy partition of the input space, the proposed method is able to determine the proper network structure, without using a trial and error procedure. The second method is based on the subtractive clustering technique. Both methods are characterized by low computational complexities. The third training method is based on a specially designed Genetic Algorithm (GA), which is used to auto-configure the structure of the networks and obtain the model parameters. This technique formulates a complete optimization problem, which includes the network structure into the set of free variables that are used to minimize the prediction error. An additional algorithm has been developed for training fuzzy systems from numerical data. The main advantage of the method is the lack of complicated iterative mechanisms and therefore, its implementation is carried out easily. The suggested algorithm employs a fuzzy model with simplified rules, assuming a fuzzy partition of the input space into fuzzy subspaces. The output is inferred by expanding the model into fuzzy basis functions (FBFs), where each FBF corresponds to a certain fuzzy subspace. The number of rules and the respective premise parts (fuzzy subspaces) are determined using the nearest neighbor approach.

10. NTUA Unit of Process Control and Informatics Research directions Development of evolutionary algorithms A complete framework has been presented for solving nonlinear constrained optimization problems, based on the line-up differential evolution (LUDE) algorithm which solves unconstrained problems. Linear and/or non-linear constraints are handled by embodying them in an augmented Lagrangian function, where the penalty parameters and multipliers are adapted as the execution of the algorithm proceeds. The LUDE algorithm maintains a population of solutions, which is continuously improved as it thrives from generation to generation. In each generation the solutions are lined up according to the corresponding objective function values. The position of each solution in the line-up is very important, since it determines to what extent the crossover and mutation operators are applied to each solution.  A stochastic algorithm has been developed for solving hierarchical multiobjective optimization problems. The algorithm is based on the simulated annealing concept and returns a single solution that corresponds to the lexicographic ordering approach. The algorithm optimizes simultaneously the multiple objectives by assigning a different initial temperature to each one, according to its position in the hierarchy. A major advantage of the proposed method is its low computational cost. This is very critical, especially for on line applications, where the time available for decision making is limited. A new heuristic method for solving instances of the travelling salesman problem. The proposed algorithm uses a variant of the Threshold Accepting method, enhanced with intense Local Search, while the candidate solutions are produced through an Insertion Heuristic scheme.

11. NTUA Unit of Process Control and Informatics Research directions Dynamic portfolio allocation A framework has been developed based on coherent risk measures and multiparametric programming for the formulation and solution of multi-stage stochastic optimization problems that arise in the context of dynamic portfolio allocation. To address mean-risk trade-off we have used a mean-risk function based on CV@R. We show that this risk measure inherits coherence of CV@R. We have developed dynamic programming equations for the problem and have obtained the explicit feedback control law via solving a sequence of multiparametric linear programs.

12. NTUA Unit of Process Control and Informatics Research directions Chemoinformatics and bioinformatics Development of mathematical relationships linking chemical structure and pharmacological activity in a quantitative manner for a series of compounds. Standard statistical tools as well as advanced machine learning methodologies (neural networks, kernel methods, evolutionary algorithms) have been employed. Emphasis is given in the development of Quantitative Structure Activity Relationships for drug design. We have also introduced a metaheuristic method for the reconstruction of the DNA string from its l-mer content in the presence of large amounts of positive and negative errors, based on the formulation of an Asymmetric Traveling Salesman problem.

13. NTUA Unit of Process Control and Informatics Chemoinformatics and bioinformatics Model ΔA

14. NTUA Unit of Process Control and Informatics Research directions Production planning and inventory control New methodologies based on control theory have been developed. An adaptation method for the online identification of lead time is incorporated in production-inventory control systems. Based on the lead time estimate, the tuning parameters are updated in real time to improve the efficiency of the system. Combination of the adaptive scheme with a proportional control law is able to eliminate the inventory drift that appears when the actual lead time is not known in advance or when it varies with time. An adaptive MPC configuration has also been developed for the identification and control of production-inventory systems. The time varying dynamic behavior of the production process is approximated by an adaptive Finite Impulse Response (FIR) model. The well known Recursive Least Squares (RLS) method is used for the on line identification of the model coefficients. The adapted model along with a smoothed estimation of the future customer demand, are used to predict inventory levels over the optimization horizon. The proposed scheme is able to eliminate the inventory drift and suppress the bullwhip effect. We have developed software tools for obtaining optimal production plans for the food, petrochemical and pulp and paper industries.

15. Past Future Set point, TInv Future outputs Inv(t) OV(t+j|t) Future inputs OV(t) t-n t t+ch t+j t+ph Control horizon Prediction horizon NTUA Unit of Process Control and Informatics Production planning and inventory control

16. NTUA Unit of Process Control and Informatics Research directions Optimal management and control of energy systems Methodologies have been developed for managing large-scale energy systems and hybrid renewable energy systems, which are expected to become competitive in the near future and, thus, optimization of their operation is of particular interest. The methodologies are based on the rolling horizon philosophy. An important innovation for renewable energy systems is that the weather forecast is taken into account. We have also developed an MPC strategy for the real time control of fuel cell systems, which satisfies standard control targets (set-point tracking, disturbance rejection), but at the same time minimizes the hydrogen consumption

17. NTUA Unit of Process Control and Informatics Optimal management and control of energy systems PDir (kW) Consumer ELIn (kW) ELOut (m3/h) FCIn (m3/h) FCOut (kW) INVIn (kW) INVOut (kW) CS (kW) Metal Hydride Tanks 1 2 3 Electrolyzer Fuel Cells Inverter ETG (kW) Inventory Purchased Electricity Sold Electricity

18. NTUA Research directions Development of a forest fire simulation tool Our laboratory has contributed in the development of a forest fire simulation tools based on two fold reasoning; a discrete contour propagation model for estimating fire consequences and a fuzzy / neural system for the estimation of fire spread as a function of influencing factors such as terrain characteristics, vegetation type and density and meteorological conditions.

19. NTUA Unit of Process Control and Informatics Development of a forest fire simulation tool

20. NTUA QSAR Group – Activities and Objectives SWOT Analysis

21. (x1-cj(1) )2 (x2-cj(2) )2 w1 Radial Basis Function (x3-cj(3) )2 w2 w3 w4 NTUA QSAR Group – The RBF neural network topology The RBF neural network topology c2 x1 x2 x3 c=[c1 c2 c3 c4] c1 c4 x=[x1 x2 x3] c3 Σ Input Layer Hidden layer Output layer