Future diagnostics technology
暂无分享,去创建一个
Abstract Army maintenance management practices have changed little within the last 50 years. Despite continual attempts to improve upon its doctrine and efficiency; prevailing Army maintenance processes are still reactive rather than proactive. Said another way, the Army's maintenance infrastructure remains in stasis before it can diagnose the symptoms of any system or component failure. This is true regardless of whether a mechanic is troubleshooting a suspected failure or determining the condition status of a system prior to operation. In either case, the current diagnostic paradigm is essentially a de facto process. It does not allow for real-time assessment of a system's operating state; nor is it capable of predicting failures. The current maintenance system is designed to verify current operational states—whether they are within or out of tolerance with design parameters. It is this legacy which results in the current “just-in-case” focus of supply and maintenance, rather than the “just-in-time” support envisioned for Force XXI.
[1] Vince L. Wiggins,et al. Statistical Neural Network Analysis Package (SNNAP) Overview and Demonstration of Facilities , 1992 .
[2] Terrence J. Sejnowski,et al. Analysis of hidden units in a layered network trained to classify sonar targets , 1988, Neural Networks.
[3] Lee A. Feldkamp,et al. Automotive diagnostics using trainable classifiers: statistical testing and paradigm selection , 1990, 1990 IJCNN International Joint Conference on Neural Networks.