Stefan Sette

Genetic programming: principles and applications

Abstract Genetic algorithms (GA) has given rise to two new fields of research where (global) optimisation is of crucial importance: ‘ genetic based machine learning ’ (GBML) and ‘ genetic programming ’ (GP). An introduction by the authors to GA and GBML was given in two previous papers (Eng. Appl. Artif. Intell. 9(6) (1996) 681; Eng. Appl. Artif. Intell. 13(4) (2000) 381). In this paper, the last domain (GP) will be introduced, thereby making up a trilogy which gives a general overview of the whole field. In this third part, an overview will be given of the basic concepts of GP as defined by Koza. A first (educational) example of GP is given by solving a simple symbolic regression of a sinus function. Finally, a more complex application is presented in which GP is used to construct the mathematical equations for an industrial process. To this end, the case study ‘fibre-to-yarn production process’ is introduced. The goal of this study is the automatic development of mathematical equations for the prediction of spinnability and (possible) resulting yarn strength. It is shown that (relatively) simple equations can be obtained which describe accurately 90% of the fibre-to-yarn database.

OPTIMIZING THE FIBER-TO-YARN PRODUCTION PROCESS WITH A COMBINED NEURAL NETWORK/GENETIC ALGORITHM APPROACH

An important aspect of the fiber-to-yam production process is the quality of the resulting yarn. The yarn should have optimal product characteristics (and minimal faults). In theory, this objective can be realized using an optimization algorithm. The complexity of a fiber-to-yarn process is very high, however, and no mathematical function is known to exist that represents the whole process. This paper presents a method to simulate and optimize the fiber-to-yam production process using a neural network combined with a genetic algorithm. The neural network is used to model the process, with the machine settings and fiber quality parameters as input and the yarn tenacity and elongation as output. The genetic algorithm is used afterward to optimize the input parameters for obtaining the best yarns. Since this is a multi-objective optimization, the genetic algorithm is enforced with a sharing function and a Pareto optimization. The paper shows that simultaneous optimization of yarn qualities is easily achieved as a function of the necessary (optimal) input parameters, and that the results are considerably better than current manual machine intervention. The last part of the paper is dedicated to finding an optimal mixture of available fiber qualities based on the predictions of the genetic algorithm.

Use of Neural Nets for Determining the Spinnability of Fibres

It is very important for a spinner to be able to predict the degree of spinnability of a given fibre quality. Certain process conditions must be taken into account here. This paper describes how the spinnability or a given fibre quality on a rotor and ring spinning machine can be predicted with a reliability of 95% by means of a neural network. The structure and the characteristics or the neural net used will be considered in greater depth, and a simple method of implementation of such a neural net will be described.

Optimising a production process by a neural network/genetic algorithm approach

Abstract An important aspect of production control is the quality of the resulting end product. The end product should have optimal product characteristics and minimal faults. In theory, both objectives can be realised using an optimisation algorithm. However, the complexity of a production process may be very high. In most cases no mathematical function can be found to represent the production process. In this paper a method is presented to simulate a complex production process using a neural network. The subsequent optimisation is done by means of a genetic algorithm. The method is applied to the case study of a spinning (fibre-yarn) production process. The neural network is used to model the process, with the machine settings and fibre quality parameters as input, and the yarn tenacity (yarn strength) and elongation as output. The genetic algorithm is then used to optimise the input parameters for obtaining the best yarns. Since it is a multiobjective optimisation, the genetic algorithm is enforced with a sharing function and a Pareto optimisation. The paper shows that simultaneous optimisation of yarn qualities is easily achieved as a function of the necessary (optimal) input parameters, and that the results are considerably better than current manual machine intervention. The paper concludes by indicating future research towards making an optimal mixture of available fibre qualities.

Assessment of Set Marks by Means of Neural Nets

Set marks in fabrics can be classified by human visual inspection. An objective way . of measuring set marks is by means of image analysis. Correlation of the output of the image analysis and the visual assessment of the set mark is not clear. Therefore, neural nets are used to find the relationships between the visibility of set marks and the image analysis, taking into account construction parameters of weft yarn and fabric.

The Use of Neural Nets to Simulate the Spinning Process

In a previous paper, a description was given of how the spinnability of a given fibre quality on a rotor- or a ring-spinning machine can be predicted with a reliability of 95% by means of a neural network. This paper goes further. It describes how yarn properties can be deduced from fibre properties and spinning-machine settings. In other words, a description is given of how to construct, train, and use a neural network in order to simulate the spinning process (predict yarn properties) on both rotor- and ring-spinning machines with an accuracy of over 95%.

Using genetic algorithms to design a control strategy of an industrial process

Abstract In this paper a methodology is presented to design a control strategy to optimise a complex spinning (fibre-yarn) production process, using a neural network combined with genetic algorithms. The neural network is used to model the process, with the machine setpoints and raw fibre quality parameters as input, and with the yarn tenacity and elongation as output. Genetic algorithms are used in two ways: • to optimise the architecture and the underlying parameters of the neural network, in order to achieve the most effective model of the production process; • to obtain setpoint values and raw material characteristics for an optimal quality of the spinned yarns.

An implementation of genetic algorithms for rule based machine learning

Abstract Genetic algorithms have given rise to two new fields of research where (global) optimisation is of crucial importance: ‘Genetic Programming’ and ‘Genetic based Machine Learning’ (GBML). In this paper the second domain (GBML) will be introduced. An overview of one of the first GBML implementations by Holland, also known as the Learning Classifier Systems (LCS) will be given. After describing and solving a well-known basic (educational) problem a more complex application of GBML is presented. The goal of this application is the automatic development of a rule set for an industrial production process. To this end, the case study on generating a rule set for predicting the spinnability in the fibre-to-yarn production process will be presented. A largely modified LCS, called Fuzzy Efficiency based Classifier System (FECS), originally designed by one of the authors, is used to solve this problem successfully.

Prediction of arthritis using a modified Kohonen mapping and case based reasoning

Abstract Rheumatoid arthritis and spondyloarthropathy are the two most frequent forms of chronic autoimmune arthritis. These diseases lead to important inflammatory symptoms resulting in an important functional impairment. In this paper we apply a topological mapping combined with a case based reasoning evaluation criterion to predict early arthritis. The first part presents a brief introduction to the problem and self-learning neural networks while the second part of this paper will apply this technique together with a case based reasoning evaluation criterion to diagnostic classification. Finally the paper shows that the Kohonen neural network achieves good performance that exceeds the results of other neural network approaches and decision trees.

Modelling Relaxation Behaviour of Yarns Part II: Back Propagation Neural Network Model

After a short introduction on cumulative back-propagation neural nets, two network connfigurations are presented for fitting time functions. These configurations were used to model relaxation curves of yarns after dynamic loading. It follows that neural networks are a valuable technique for fitting time functions. However, a careful design of the network configuration is indispensable.