Abstract
The base principles of a technique of application of 3-layer feedforward fullconnected artificial neural network for execution of adaptive algorithms of testing of digital microprocessor devices are considered. The method of change of weight coefficients and thresholds of artificial neurons in the mode of operation of artificial neural network realized at the hardware level is considered. The application of this method provides implementation of adaptive algorithms of testing of the large complexity with the limited hardware resources of artificial neural network.
Highlights
Increase of a degree of integration and the complication of an inner structure of digital microprocessor devices predetermines fixed rise of the requirements to their diagnosis equipment
By problem, which arises at execution of adaptive algorithms of diagnosing according to the described approach, there is an implementation of multiple comparing of returnes
The given technique is founded on usage of ability of artificial neural networks simultaneously to check several conditions of adaptive algorithm of testing
Summary
Increase of a degree of integration and the complication of an inner structure of digital microprocessor devices predetermines fixed rise of the requirements to their diagnosis equipment. The existing equipment of complete hardware implementation of adaptive algorithms select a way of continuation of the process of testing as a result of comparing on coincidence of two values of vectors of returns. The tops of a tree ti (Fig. 1) correspond to test vectors, which give on unit under test, and the arcs reflect possible transitions during testing depending on coincidence of obtained value of a vector of returns ri with standard ei The shortcoming of such comparing is that it does not permit to take into account tags of manifestation of a fault, which have brought to an. It does not permit beforehand to forecast quantity of standard values, which can compare with a vector of returnes of unit under test by diagnosis equipment In such situation it is heavy to define optimal quantity of the necessary blocks of comparing. Hardware realized ANN (fig. 3) is a basis of the block of neural network control of process of testing
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
