Behaviour-based Manufacturing Control with Soft Computing Techniques

Abstract

Soft Computing methods have been widely used in recent years to address the challenges posed by disturbances handling and uncertainty management in Manufacturing Execution Systems (MES). The focus of this research paper is on the application of Soft Computing methods for classification problems in Behaviour Based Control.
 The paper proposes the use of classification techniques to determine the behavior of a production system. This is an important task as it enables the detection of anomalous behavior and allows for the implementation of appropriate corrective measures. The proposed classification method is based on the use of Neural Networks and Fuzzy logic. Neural Networks are a powerful tool for classification tasks due to their ability to learn from data and make predictions based on patterns. The proposed method uses a feedforward neural network with a single hidden layer to classify the behavior of the production system. The inputs to the network are features extracted from the production system, while the output is the classification result. Fuzzy logic is also used in the proposed classification method to handle uncertainty in the input data. In conclusion, this research paper presents a novel approach to classification problems in Behaviour Based Control using Soft Computing methods. The proposed method shows promising results in handling disturbances and uncertainty in manufacturing systems. Further research in this area could lead to the development of more advanced Soft Computing methods for manufacturing systems, enabling more efficient and effective control and management of production processes.