Boltzmann Machine-Based FieldBus Control Case study: Electro-Hydraulic Governor

Fieldbus networks such as Foundation Fieldbus FB, Profibus and Controller Area Network CAN are extensively used in modern control system implementations. The control of electrical power plants ranges from mimic panels to computer based systems. In this paper the impact of fieldbus technology in process control of Electro-Hydraulic Governor (EHG) systems used in thermal power generating plants is considered. Centralized access control in fieldbus systems is characterized by the presence of a processing unit acting as Link Active Scheduler (LAS), whose task is to manage the bandwidth, distributing it among a1l the producing devices, and respecting their time constraints. This paper presents the use of neural networks for process scheduling. The proposed model allows several processes to be scheduled simultaneously. The bandwidth is distributed on the basis of a scheduling table containing transmission instants for the information produced by different processes in the system such as to guarantee correct scheduling. The paper implements Boltzmann Neural Networks (BNNs) in LAS for scheduling, synchronization of accessing and control in hard real time systems considering the EHG as an example.

[1]  Kwei-Jay Lin,et al.  Scheduling distance-constrained real-time tasks , 1992, [1992] Proceedings Real-Time Systems Symposium.

[2]  Vangelis Th. Paschos,et al.  On the Approximation of NP-Complete Problems by Using the Boltzmann Machine Method: The Cases of Some Covering and Packing Problems , 1991, IEEE Trans. Computers.

[3]  Salvatore Cavalieri,et al.  Pre-Run-Time Scheduling to Reduce Schedule Length in the FieldBus Environment , 1995, IEEE Trans. Software Eng..

[4]  Ming Ye.  Novel Field–Bus Real-Time Network Scheduling Method , 2010, 2010 Second International Conference on Computer Modeling and Simulation.

[5]  Zhang Xiang-li,et al.  Study on communication scheduling of fieldbus , 2009, 2009 Chinese Control and Decision Conference.

[6]  Usama M. AIi,et al.  Fieldbus scheduling using Boltzmann machine , 2010, 2010 7th International Multi- Conference on Systems, Signals and Devices.

[7]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[8]  Chung Laung Liu,et al.  Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment , 1989, JACM.

[9]  Michael L. Dertouzos,et al.  Control Robotics: The Procedural Control of Physical Processes , 1974, IFIP Congress.

[10]  Dennis Brandão,et al.  A fieldbus simulator for training purposes. , 2009, ISA transactions.

[11]  Geoffrey E. Hinton,et al.  OPTIMAL PERCEPTUAL INFERENCE , 1983 .

[12]  Maryline Chetto,et al.  Some Results of the Earliest Deadline Scheduling Algorithm , 1989, IEEE Transactions on Software Engineering.

[13]  Jin Jiang,et al.  Evaluation of Delays Induced by Profibus PA Networks , 2011, IEEE Transactions on Instrumentation and Measurement.

[14]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[15]  Alan Burns,et al.  Controller Area Network (CAN) schedulability analysis: Refuted, revisited and revised , 2007, Real-Time Systems.

[16]  Wei-Ming Tong,et al.  A Fieldbus Comprehensive Evaluation and Selection Method Based on Entropy-Ideal Point , 2008, 2008 Eighth International Conference on Intelligent Systems Design and Applications.

[17]  Yuping Zhang,et al.  Research of the scheduling method for fieldbus network real-time information , 2011, Proceedings of 2011 6th International Forum on Strategic Technology.

[18]  Stephen M. Walters,et al.  Neural network architecture for crossbar switch control , 1991 .

[19]  David Lorge Parnas,et al.  On Satisfying Timing Constraints in Hard-Real-Time Systems , 1993, IEEE Trans. Software Eng..

[20]  Salvatore Cavalieri,et al.  Neural networks for process scheduling in real-time communication systems , 1996, IEEE Trans. Neural Networks.

[21]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[22]  R. P. Pantoni,et al.  Fieldbus simulator: Architecture, typical experiment and tool evaluation , 2008, 2008 34th Annual Conference of IEEE Industrial Electronics.

[23]  A. Marrakchi,et al.  A neural net arbitrator for large crossbar packet-switches , 1989 .

[24]  Kwei-Jay Lin,et al.  Scheduling Real-Time Systems with End-to-End Timing Constraints Using the Distributed Pinwheel Model , 2001, IEEE Trans. Computers.