A Simulation Environment for Self-Propelled Gun Failure Prediction Based on Probabilistic Neural Network

Abstract:

This paper presents the development of a simulation environment in Matlab/Simulink for the analysis of the Sub-System of a kind of self-propelled gun and the design of fault tolerant control laws for this configuration. The environment includes the input module, output module and Simulation Nucleus and modeling of several types of engine failure. The simulation environment capable of implementing failure prediction has been implemented successfully as groundwork for analysis of the engine subsystem of self-propelled gun. Preliminary simulation results show the simulation environment is efficient for the Probabilistic neural network. Both abnormal oil pressure and rotate speed failures have been simulated. The simulation environment provides the necessary tools for the development and testing of advanced fault tolerant control laws.

• Periodical: Advanced Materials Research (Volumes 466-467)
• Pages: 1424-1428
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.466-467.1424
• Online since: February 2012
• Authors: Guang Hong, Shuai Zhang
• Keywords: Probabilistic Neural Network, Self-Propelled Gun, Simulation Environment

References

[1] D.F Specht. Probabilistic Neural Networks. Neural Networks. 1990( l) : 109- 118.

[2] Sergio Tamayo, Mario G. Perhinschi, A Simulation Environment for Individual Blade Control Helicopters, AIAA Modeling and Simulation Technologies Conference, 2009.

DOI: 10.2514/6.2009-5693

[3] Huang Deshuang, Ma Songde. A New Radial Basis Probabilistic Neural Network Model. Proceeding of ICSP. 1996:1449～1452

DOI: 10.1109/icsigp.1996.571134

[4] M.T. Musavi, K. Kalantri, W. Ahmed. Improving the Performance of Probabilistic Neural Networks. 1992IEEE:595～600

[5] Anthony Zaknich, Yianni Attikiouzel. A Tunable Approximately Piecewise Linear Model From the Modified Probabilistic Neural Network. 1996IEEE:45～53

DOI: 10.1109/nnsp.2000.889361