Intelligent Diagnostic for PROFIBUS DP Networks

Digital networks for industrial automation applications, or fieldbuses, are highly sensitive to fails related to physical installations. Among all fieldbuses, PROFIBUS is one of the most used network protocol in the industrial automation area, and it is the target protocol for this work. Failing to observe technical requirements, by using excessive long cabling or lacking active bus terminals, for instance, may affect the communication performance and alter electrical characteristic of the transmission system, therefore degrading the quality of the signal being transmitted. This kind of problems can be diagnosed by analyzing the voltage levels of the signals from the network devices, considering their characteristic format, or even analyzing the behavior of the devices on the network, for example, when a device does not respond to requests or when a device sporadically connects and disconnects from the network. This work proposes the use of intelligent systems, such as Artificial Neural Networks (ANN) and Expert Systems, to perform these analyses. Besides displaying diagnostics, the system also allows the user to visually analyze the signals from the network's physical layer using an oscilloscope, and display the devices that are communicating on the network (Live List), among other features. Support provided by this system may minimize eventual false downtime for the plant and, consequently, decrease possible losses from the processes.