Real-Time Water Treatment Process Control with Artificial Neural Networks

Voltage control of Proton Exchange Membrane Fuel Cell (PEMFC) is necessary for any practical application. This paper considers a state space model for controller design and a Neural Network (NN) feed forward controller with an optimization technique called Harmony Search algorithm is considered to control the output voltage. This paper compares the results of the proposed controller with the NN feed forward controller. The comparison shows the proposed controller follows the reference voltage more closely than NN feed forward controller. Finally the performance of the controller is studied by evaluating Integral Squared Error (ISE), Integral Absolute Error (IAE) and Integral Time-weighted Absolute Error (ITAE) and the results are compared. The system error of the proposed controller is reduced to a least minimum value compared with the other.

To improve drinking water quality while reducing operating costs, many drinking water utilities are investing in advanced process control and automation technologies. The use of artificial intelligence technologies, specifically artificial neural networks, is increasing in the drinking water treatment industry as they allow for the development of robust nonlinear models of complex unit processes. This paper highlights the utility of artificial neural networks in water quality modelling as well as drinking water treatment process modelling and control through the presentation of several case studies at two large-scale water treatment plants in Edmonton, Alberta.Key words: artificial neural networks, water treatment process control, water treatment modelling.

In this study, we determined the removal of a prototype human norovirus (Norwalk virus, NV) by bench-scale alum coagulation, flocculation and sedimentation processes using reverse transcriptase polymerase chain reaction (RT-PCR) for norovirus assays. After determining optimum conditions for the coagulation, flocculation and sedimentation processes in terms of turbidity reduction, jar tests were performed using the same waters seeded with test viruses. For comparison, two other important health-related viruses, poliovirus 1 (PV1) and coliphage MS2, were included in this study. The removal of NV by coagulation, flocculation and sedimentation processes based on RT-PCR assay in this study was 1.5 log10, which was similar to that of PV1 and a little lower than that of coliphage MS2 (2 log10) based on the same RT-PCR assay. The removal of NV in this study (1.5 log10) is considerably higher than the one in a recent study using recombinant norovirus virus-like particles (∼0.7 log10). Overall, the results of this study suggest that human noroviruses can be appreciably reduced by a properly-operated coagulation, flocculation and sedimentation processes and the contamination of drinking water by noroviruses should be controlled by conventional water treatment processes with conventional physico-chemical processes and disinfection.

This paper describes the design and implementation of a neural network controller capable of printing designs and drawings on paper using a Cartesian Plotter. The Cartesian plotter uses two dc motors with incremental encoders for motion along x and y-axis while third dc motor along z-axis controls the pen assembly for drawing the text and graphics data. The motion commands for the motors are generated with the help of a simple feed forward neural network controller trained with back propagation algorithm. The nine inputs, two output neural controller employs four neurons in the hidden layer with tangent sigmoid being activation function for hidden neurons while linear function is used for output neurons. The proposed neural controller can drive the pen assembly in one of the eight possible directions and thus produces similar results to the famous Bresenham's algorithm. Simulations and practical results validate the neural controller for use with Cartesian plotters.

This benchmark suite presents a detailed description of a series of closed-loop control systems with artificial neural network controllers. In many applications, feed-forward neural networks are heavily involved in the implementation of controllers by learning and representing control laws through several methods such as model predictive control (MPC) and reinforcement learning (RL). The type of networks that we consider in this manuscript are feed-forward neural networks consisting of multiple hidden layers with ReLU activation functions and a linear activation function in the output layer. While neural network con- trollers have been able to achieve desirable performance in many contexts, they also present a unique challenge in that it is difficult to provide any guarantees about the correctness of their behavior or reason about the stability a system that employs their use. Thus, from a controls perspective, it is necessary to verify them in conjunction with their corresponding plants in closed-loop. While there have been a handful of works proposed towards the verification of closed-loop systems with feed-forward neural network controllers, this area still lacks attention and a unified set of benchmark examples on which verification techniques can be evaluated and compared. Thus, to this end, we present a range of closed-loop control systems ranging from two to six state variables, and a range of controllers with sizes in the range of eleven neurons to a few hundred neurons in more complex systems.

Process control in the field of chemical engineering has always been a challenging task for the chemical engineers. Hence, the majority of processes found in the chemical industries are non-linear and in these cases the performance of the linear models can be inadequate. Recently a promising alternative modelling technique, artificial neural networks (ANNs), has found numerous applications in representing non-linear functional relationships between variables. A feedforward multi-layered neural network is a highly connected set of elementary non-linear neurons. Model-based control techniques were developed to obtain tighter control. Many model-based control schemes have been proposed to incorporate a process model into a control system. Among them, model predictive control (MPC) is the most common scheme. MPC is a general and mathematically feasible scheme to integrate our knowledge about a target, process controller design and operation, which allows flexible and efficient exploitation of our understanding of a target, and thus produces optimal performance of a system under various constraints. The need to handle some difficult control problems has led us to use ANN in MPC and has recently attracted a great deal of attention. The efficacy of the neural predictive control with the ability to perform comparably to the non linear neural network strategy in both set point tracking and disturbance rejection proves to have less computation expense for the neural predictive control. The neural network model predictive control (NNMPC) method has less perturbations and oscillations when dealing with noise as compared to the PI controllers.

The Sixth International Symposium on Neural Networks (ISNN 2009)

This article analyses the dynamic behaviour of a beam structure containing multiple transverse cracks using neural network controller. The first three natural frequencies and mode shapes have been calculated using theoretical, finite-element, and experimental analysis for the cracked and un-cracked beam. Comparisons of the results among theoretical, finite-element, and experimental analysis have also been presented. The calculated vibration signatures were used to train the feed-forward multi-layered neural network controller with back-propagation technique for the prediction of cracks. Relative crack locations and relative crack depths are the output of the neural controller. Results obtained from the various analyses are validated using the developed experimental set-up. Results from neural controller have been presented for comparison with the output from theoretical, finite-element, and experimental analysis. From the evaluation of the performance of the neural network controller it is observed that the developed method can be used as a crack diagnostic tool in the domain of dynamically vibrating structures.

Development of computational intelligence allows to combine some conventional approaches with artificial intelligence modules, like Artificial Neural Networks (ANNs). The combination leads to so-called Intelligent Systems which potential is practically unlimited. ANNs based models for electrodes positioning, prediction of the electric energy consumption and end-of-heat in electric arc furnaces were implemented by number of authors and they have obtained applicable practical results. The present paper describes methods of intelligent control of the EAF steelmaking process, particularly neural control. The elaborated neural network models for smelting control in the EAF are discussed. The goal is to provide a compact review of neural modeling and control methods and their capabilities for the EAF steelmaking process.

On-line adaptive control for inverted pendulum balancing based on feedback-error-learning

Because of the complex nature of drinking water treatment unit processes, utilities have difficulty quantifying the interactions and relationships that exist between process inputs and process outputs. Process models, where they exist, are often site specific and are unable to simultaneously handle continuous variations in more than one or two key process variables. The artificial neural network (ANN) technology is a robust artificial intelligence technology that can handle the complex and dynamic nature of treatment processes. As such, the technology has been gradually gaining acceptance in the drinking water treatment industry as a tool for process modelling and control. While publications on modelling results and applications abound, a detailed account of ANN modelling methodology is lacking. Presented is a detailed methodology for developing successful ANN models of drinking water treatment processes. The utility and applicability of this methodology is demonstrated through a case study where a successful ANN model to predict filtration performance was developed. Key words: artificial neural networks, process modelling, process optimization, water treatment.

Due to its simple structure and robustness, the traditional proportional-integral-derivative (PID) controller is commonly used in the field of industrial automation and process control, but it does not function well with nonlinear systems, time-delayed linear systems and time-varying systems. A new type of PID controller based on artificial neural networks and evolutionary algorithms is presented in this paper. An powerful instrument for a highly nonlinear system is the Artificial Neural Network. The interest in the study of the nonlinear system has increased through the implementation of a high-speed computer system,. In complex systems such as robotics and process control systems, the Neuro Control Algorithm is often applied. Systems of process management is also nonlinear and hard to control consistently.. This paper presents a comprehensive analysis in Which is offline trained by a multilayered feed forward back propagation neural network to act as a process control system controller, That is to say, a temperature control device without prior knowledge of its dynamics. Via the implementation of a range of input vectors to the neural network, the inverse dynamics model is developed. Based on these input vectors, the output of the neural network It is being studied by explicitly configuring it to monitor the operation. In this paper, based on set-point adjustment, impact of disturbances in load and variable dead time, compassion between the PID controller and ANN is conducted. The outcome shows that ANN outperforms the controller of the PID.

A two-mode coupled compound pendulum is used to compare a computed-torque-type model reference adaptive controller and a feedforward neural network controller. A derived globally asymptotically stable adaptation law for the neural net controller shows that the back error propagation scheme used is, in some cases, also asymptotically stable. Computer simulations of the two controllers demonstrate their relative performance. This comparison shows that the derived adaptation law compares favorably with the performance of the model reference adaptive controller. It also lends insight into the required input signal frequency content in order to guarantee proper convergence of the neural network. The convergence and stability properties of the neural network when it is used as a feedforward computed-torque controller are analyzed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

This paper describes the visual feedback positional control of the XY piezo actuator stage (PAS). The XY PAS control system consists of four main components, i.e. XY PAS as controlled object, supply electronics for piezoelectric actuators (PEAs), microscope with digital camera for visualization and for measuring the actual position and a vision processing module in combination with a desktop PC, as processing hardware. XY PAS is fabricated by a photo structuring process from photosensitive glass, and PEAs are built-onto meet the request for its precise movement. It is evident from the electromechanical model of XY PAS, that accurate positioning of XY PAS is an exacting piece of work, due to the nonlinear hysteresis inherent in PEAs. Accordingly, two neural network control techniques were developed, i.e. the feedforward neural network controller (FFNNC) and the feedforward/feedback neural network controller (FF/FBNNC). Proposed neural network controllers are compared with the traditional linear controllers.

Artificial neural networks (ANNs) have been widely used in modelling and control of many practical industrial nonlinear processes. However, most of them have focused on a general approach for input selection. In this paper, a hierarchical hybrid approach of partial least squared (PLS) analysis and ANNs has been applied for predictive control of a real drying process in ceramic tile manufacturing. This approach is employed in order to promote the reliability of neural network model via reduction of the input set dimension. First, PLS analysis is done to arrive at the significant factors that influence the spray drying quality the most. Also, the significant factors are used to construct the predictive neural network model so called the Focus-NN model. Next, the reliability of the Focus-NN model is compared with the ANN model. In order to develop a predictive-control strategy using a more reliable model, i.e. the Focus-NN model, several scenarios as an accurate, fast running and inexpensive method are deployed to identify the optimal process settings considering the desired output.