A novel single ended fault location method , called type F, is presented in this paper, by which the fault location is determined by the time delay measured at the relaying point between fault switching off induced initial travelling wave surge and the corresponding reflected wave from the fault point.

Tault location can be realized using the transient travelling waves caused by circuit breakers(CBs) during fault switching off,through which the effect of the reflected waves coming from the remote discontinuity on the faulty transmission line is removed.

In the aviation,spaceflight and machine fields,system reliability affected with short failure and open failure is due to short failure and open failure of unit occurred.

It is important to research the system reliability which is affected with short failure and open failure in engineering.

Since 1990s, many work has addressed the issue of improving the fault tolerant ability of feedforward neural networks against some kinds of faults such as the single-node open fault where a hidden node and its associated weights in a neural network are out of work at the same time.

Based on the research of fault tolerant neural networks by some precursors, an adaptive fault tolerant neural networks learning algorithm FTART4 is proposed to resolve the multi node open fault problem.

In equipments such as automatic packing machine and bagging machines which required the electric heater to package plastic products,it is common that electric heater is often in open circuit fault.