A field bus network with can protocol and a fuzzy neural petri net controller

Abstract EN

In field bus systems different smart sensors are functionally interconnected, requiring exchange of information accurately with a specified communication latency and sample time.

This paper describes implementation methodologies of efficient distributed real time controllers for monitoring and actuation.

Software for these controllers with CAN communication protocol are written.

CAN-Based embedded microcontrollers and transceivers are used for the practical implementation.

Temperature control by a robust neural fuzzy Petri net (RNFPN) controller based on an indirect forward control structure is also proposed.

After offline learning to get the initial weights, the RNFPN is online constructed by concurrent structure / parameter learning.

The RNFPN has many advantages when applied to temperature control plants such as : high learning ability which reduces the controller training time, no a priori knowledge of the plant is required which simplifies the design task, and lastly the high control performance.

As a case study, the field bus system is tested with a water bath temperature control system.

The RNFPN control of the plant is implemented in the host computer connected to the master controller via the RS232 port.

Implementation results provide a good indication that the CAN protocol is a high reliable and can be potentially adopted in numerous industrial applications.

Also, the RNFPN intelligent controller has a reasonable robustness against disturbance, rapidity and good dynamic performance.