In this paper, a hybrid intelligent parameter estimation algorithm is proposed for predicting the strip temperature during laminar cooling process. The algorithm combines a hybrid genetic algorithm (HGA) with grey case-based reasoning (GCBR) in order to improve the precision of the strip temperature prediction. In this context, the hybrid genetic algorithm is formed by combining the genetic algorithm with an annealing and a local multidimensional search algorithm based on deterministic inverse parabolic interpolation. Firstly, the weight vectors of retrieval features in case-based reasoning are optimised using hybrid genetic algorithm in offline mode, and then they are used in grey case-based reasoning to accurately estimate the model parameters online. The hybrid intelligent parameter estimation algorithm is validated using a set of operational data gathered from a hot-rolled strip laminar cooling process in a steel plant. Experiment results show the effectiveness of the proposed method in improving the precision of the strip temperature prediction. The proposed method can be used in real-time temperature control of hot-rolled strip and has potential for parameter estimation of different types of cooling process.

Papermaking is known as an energy-intensive, but not always efficient industry. This is at least partly due to the fact that the majority of papermaking technologies and procedures were established at a time when energy was both cheap and plentiful. A considerable fraction of the energy required for papermaking is consumed in removing water by the use of steam in the paper machine’s drying section. It is also known that even a small reduction in steam use can result in a significant reduction in production costs and environmental effects. To date, a great deal of research has been undertaken, aimed at improving the performance of the drying section by making more efficient use of dryer steam. This paper investigates a new approach to reducing thermal energy use in paper making by seeking to enhance the amount of water removed in sections of the machine prior to the drying section. The proposed method is focused on sequential modelling of the effect of vacuums used in the forming section on the thermal energy consumption in the drying section. The primary models explain how different vacuum pressures can affect the flow of water from the sheet in the forming section whilst the secondary models describe the effect of increased drainage on the steam requirements in the dryer. Operational data from a UK paper mill are used to illustrate the proposed method. The models developed can have subsequent application to optimising the use of thermal energy in paper making.

Due to the increasing cost of energy and the demand of reducing the environmental footprints, energy saving is becoming an important subject in the industry operation. To realize the energy consumption optimization of papermaking, the energy model should be established while the product quality and process model also need to be constructed, which are taken as the constraints for optimization. This paper describes the identification of a forming section of paper machines with Multilayer Perception (MLP) Neural Networks. The process model, product quality model and energy consumption model are established for the energy saving in papermaking. The real industrial step tests are performed and the data are used to model training and validation. The models are validated by means of mean-squared error (MSE), fit measure and Akaike's Final Prediction Error (FPE). The results show the effectiveness of the established models, which are suitable for the next work of energy optimization.

This study proposes a multi-objective control algorithm for simultaneous process and quality control in non-Gaussian stochastic batch processes. The objective is to control a non-Gaussian process so that each batch is delivered within a pre-specified time. During each batch, the process is controlled by a fixed-parameter PI controller. Between any two adjacent batches the controller parameters are updated by a differential evolution algorithm so that the integral squared of tracking error, entropy of tracking error, integral of absolute processing time error and entropy of processing time error are minimised. the proposed algorithm is applied to a batch continuously stirred tank reactor where promising results have been obtained. The proposed method can be used as a basis for joint probabilistic process/quality control where more complicated quality measures are applied.

A new filtering approach based on the idea of iterative learning control (ILC) is proposed for linear and non-Gaussian stochastic systems. The objective of filtering is to estimate the states of linear systems with non-Gaussian random disturbances so that the entropy of output error is made to monotonically decrease along the progress of batches of process operation. The term Batch is referred to a period of time when the process repeats itself. During a batch, the filter gain is kept fixed and state estimation is performed. Between any two adjacent batches, the filter gain is updated so that the entropy of closed-loop output error is reduced for the next batch. Analysis is carried out to explicitly determine the learning rates which lead to convergence of the overall algorithm. Experiments have been implemented on a laboratory-based process test rig to demonstrate the effectiveness of proposed filtering method.

Reducing energy consumption is a major challenge for "energy-intensive" industries such as papermaking. A commercially viable energy saving solution is to employ data-based optimization techniques to obtain a set of "optimized" operational settings that satisfy certain performance indices. The difficulties of this are: 1) the problems of this type are inherently multicriteria in the sense that improving one performance index might result in compromising the other important measures; 2) practical systems often exhibit unknown complex dynamics and several interconnections which make the modeling task difficult; and 3) as the models are acquired from the existing historical data, they are valid only locally and extrapolations incorporate risk of increasing process variability. To overcome these difficulties, this paper presents a new decision support system for robust multiobjective optimization of interconnected processes. The plant is first divided into serially connected units to model the process, product quality, energy consumption, and corresponding uncertainty measures. Then multiobjective gradient descent algorithm is used to solve the problem in line with user's preference information. Finally, the optimization results are visualized for analysis and decision making. In practice, if further iterations of the optimization algorithm are considered, validity of the local models must be checked prior to proceeding to further iterations. The method is implemented by a MATLAB-based interactive tool DataExplorer supporting a range of data analysis, modeling, and multiobjective optimization techniques. The proposed approach was tested in two U.K.-based commercial paper mills where the aim was reducing steam consumption and increasing productivity while maintaining the product quality by optimization of vacuum pressures in forming and press sections. The experimental results demonstrate the effectiveness of the method.

This paper reports the application of Advanced Process Control (APC) techniques for improving the thermal energy efficiency of a paperboard-making process by regulating the Machine Direction (MD) profile of the basis weight and moisture content of the paper-board. A Model Predictive Controller (MPC) is designed so that the sheet moisture and basis weight tracking errors along with variations of the sheet moisture and basis weight are reduced. Also, the drainage is maximised through improved wet-end stability which can facilitate driving the sheet moisture set-point closer to its upper specification limit over time. It is shown that the proposed strategy can result in reducing steam usage by 8–10%. A simulation study based on a UK board machine is presented to show the effectiveness of the proposed technique.

Papermaking is considered as an energy-intensive industry partly due to the fact that the machinery and procedures have been designed at the time when energy was both cheap and plentiful. A typical paper machine manufactures a variety of different products (grades) which impose variable per-unit raw material and energy costs to the mill. It is known that during a grade change operation the products are not market-worthy. Therefore, two different production regimes, i.e. steady state and grade transition can be recognised in papermaking practice. Among the costs associated with paper manufacture, the energy cost is ‘more variable’ due to (usually) day-to-day variations of the energy prices. Moreover, the production of a grade is often constrained by customer delivery time requirements. Given the above constraints and production modes, the product scheduling technique proposed in this paper aims at optimising the sequence of orders in a single machine so that the cost of production (mainly determined by the energy) is minimised. Simulation results obtained from a commercial board machine in the UK confirm the effectiveness of the proposed method.

Over the last two or three years, the increasing costs of energy and worsening market conditions have focussed even greater attention within paper mills than before, on considering ways to improve efficiency and reduce the energy used in paper making. Arising from a multivariable understanding of paper machine operation, Advanced Process Control (APC) technology enables paper machine behaviour to be controlled in a more coherent way, using all the variables available for control. Furthermore, with the machine under better regulation and with more variables used in control, there is the opportunity to optimise machine operation, usually providing very striking multi-objective performance improvement benefits of a number of kinds. Traditional three term control technology does not offer this capability. The paper presents results from several different paper machine projects we have undertaken around the world. These projects have been aimed at improving machine stability, optimising chemicals usage and reducing energy use. On a brown paperboard machine in Australasia, APC has reduced specific steam usage by 10%, averaged across the grades; the controller has also provided a significant capacity to increase production. On a North American newsprint machine, the APC system has reduced steam usage by more than 10%, and it provides better control of colour and much improved wet end stability. The paper also outlines early results from two other performance improvement projects, each incorporating a different approach to reducing the energy used in paper making. The first of these two projects is focussed on optimising sheet drainage, aiming to present the dryer with a sheet having higher solids content than before. The second project aims to reduce specific steam usage by optimising the operation of the dryer hood. 1. INTRODUCTION: THE ENERGY USED IN PAPER MAKING

Flow line are one of the most commonly encountered layouts in manufacturing industries, where several product types (grades) are manufactured using a sequence of sub-systems or machinery with different tasks. With increasing prices of energy and specific customer demands employing effective product scheduling strategies has become essential for manufacturing industries to maintain their business viability. In this paper, a new product scheduling method is proposed for multi-machine, multi-product flow lines. The objective here is to control the production start time for each grade so that the product delivery time errors are minimised. It is also desired to minimise the overall makespan variability caused by non-Gaussian uncertainties formulated by the entropy of the delivery time errors. Therefore, the proposed product scheduling strategy is a nonlinear multi-objective optimisation problem with non-Gaussian uncertainties. To solve this problem, the nonlinear dynamic flow line model is converted to a linear dynamic equivalent using a (Max,+) algebraic approach. Then, a Proportional-Integral (PI) scheduling controller is used to control the production start time for each grade. The scheduling controller coefficients are tuned by a Multi-Objective Differential Evolution (MODE) algorithm. Simulation results show the effectiveness of the proposed technique and a comparison is made between MODE, Genetic Algorithm (GA) and Particle Swarm Optimisation (PSO).

The stochastic distribution control is important for certain industrial applications and cases where non-Gaussian noises exist. The problem has been initially solved by controlling the dynamical system formed by neural networks which approximate the output probability density function (PDF). Also, a modified version of iterative learning control (ILC) has been previously introduced by the authors to solve the output PDF shaping problem for linear weight dynamical systems. Looking into unknown non-linear weight dynamics, this paper presents a model reference neuro-adaptive control (MRNAC) approach for PDF shaping in non-Gaussian stochastic systems. The method is based on ILC and employs a neural network framework for modelling and controller. The time domain is first split up to batches. Then the proposed ILC method is implemented in two main domains namely within each batch and between any two adjacent batches. The design is carried out in three stages: a) NN-based non-linear dynamic system identification; b) MRNAC of the weight control loop within each batch; c) tuning the NN centres and widths between any two adjacent batches. Simulations confirm the effectiveness of the method.

In this paper, a new architecture for automation in manufacturing systems is proposed. The architecture “intelligent Distributed Control System (iDCS)” is focused on the distribution of control resources so that the intelligent control and condition monitoring can be performed locally with maximum level of autonomy. In this regard, the powerful framework of Multi Agent Systems (MAS) is employed to conceptually model the manufacturing platform. Also, considering the event-driven dynamics of the plant, an automata language is used to formally represent the agents and their interactions. In order to enhance the fault tolerance of the agent-based community, a fuzzy redundancy management scheme has been introduced to the supervisory level of iDCS. Simulations have been performed to demonstrate the iDCS model and redundancy policy of a flow line comprised of four agents.

Minimum variance control is an established method in control of systems corrupted by noise. In these cases, as it is not possible to directly control the actual value of the system variables, one aims to reduce the variations instead. However, when the system noises are non-Gaussian, this approach fails because non-Gaussian noise cannot be characterised by simple measures such as variance. In these cases, the Entropy is proposed as a generalisation of the variance measure and the control objective becomes that of minimising the Entropy. Previously a limited form of this problem has been solved using first order Newtonian methods. In this paper, the control objective is first expanded to also include an error term related to the closed loop tracking performance, and the combined problem is then solved using a fast global optimisation search algorithm. The effectiveness of the approach is demonstrated through a case study based on a first principle model of a nonlinear heat exchanger.

In this paper, a new method for adaptive control of general nonlinear and non-Gaussian unknown stochastic systems has been proposed. The method applies the minimum entropy control scheme to decrease the closed-loop randomness of the output under an iterative learning control (ILC) basis. Both modeling and control of the plant are performed using dynamic neural networks. For this purpose, the whole control horizon is divided into a certain number of time domain subintervals called batches and a pseudo-D-type ILC law is employed to train the plant model and controller parameters so that the entropy of the closed-loop tracking error is made to decrease batch by batch. The method has the advantage of decreasing the output uncertainty versus the advances of batches along the time horizon. The analysis on the proposed ILC convergence is made and a set of demonstrable experiment results is also provided to show the effectiveness of the obtained control algorithm, where encouraging results have been obtained.

This paper presents Model Reference Adaptive Control (MRAC) approach to control the shape of output distribution in non-Gaussian stochastic systems. The method is based on Iterative Learning Control (ILC) and employs a Neural Network framework for controller design. The output Probability Density Function (PDF) tracking problem is first reduced to dynamic Neural Network (NN) weight control. It is assumed that the dynamic behaviour of such weights is nonlinear and unknown. To apply the ILC-based tuning, the control horizon is split up to certain number of intervals hereinafter called batches. The proposed ILC method is comprised of two main modes, namely within each batch and between any two adjacent batches, and includes three stages; (a) NN-based nonlinear dynamic system identification (b) MRAC of the weight control loop within each batch, and (c) Tuning the RBF centers, widths, and controller neural network parameters between any two adjacent batches. Simulation results confirm the effectiveness of the method.