In many industrial sectors, such as the chemical industry, weight measures are used in order to control the quantity of consumed raw material. This parameter also takes a fundamental part in the product quality, as the correct transformation process is based upon a given percentage of each essence. Thus, weight regulation increases the global productivity of the system by decreasing the quantity of rejected products. This paper presents an approach based on a new modelling tool: the Interval Constrained Petri Nets. This tool is introduced in order to extend some properties of p-time PN to nontemporal constraints. A robust static weight setting in a tobacco fabric is presented as an application on a real workshop, using real production data. Then, a reactive control, facing the variations in input quality, provides a significant improvement in the quality of the final production.
A novel neural architecture for prediction in industrial control: the 'Double Recurrent Radial Basis Function network' (R2RBF) is introduced for dynamic monitoring and prognosis of industrial processes. Three applications of the R2RBF network on the prediction values confirmed that the proposed architecture minimizes the prediction error. The proposed R2RBF is excited by the recurrence of the output looped neurons on the input layer which produces a dynamic memory on both the input and output layers. Given the learning complexity of neural networks with the use of the back-propagation training method, a simple architecture is proposed consisting of two simple Recurrent Radial Basis Function networks (RRBF). Each RRBF only has the input layer with looped neurons using the sigmoid activation function. The output of the first RRBF also presents an additional input for the second RRBF. An unsupervised learning algorithm is proposed to determine the parameters of the Radial Basis Function (RBF) nodes. The K-means unsupervised learning algorithm used for the hidden layer is enhanced by the initialization of these input parameters by the output parameters of the RCE algorithm.
This paper proposes a modeling method of these control laws for manufacturing system. The robustness for these categories of system is discussed. Our approach consists in managing the disturbances of the drifts type of quality of the product. The Intervals Constrained Petri Net (ICPN) are used for the modeling of the no temporal constraints. A methodology of construction of a robust control system generating the margins of passive and active robustness is elaborated. The redundancy of the robustness of the elementary parameters between passive and active leads us to define the ways ensuring the total robustness of the system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.