MONITORING

摘要

The operation of an engine (2) or other assembly is monitored by detecting the sound it makes and deriving from this, in conjunction with its speed, temperature and control settings, a multi-dimension condition vector. The vector changes during operation of the engine (2) and is supplied to a processor (4) which builds up a model of the engine (2) at different stages of operation such as by a sequence-learning neural net or by a hidden Markov model. When an atypical condition vector is received, the processor (4) generates an alert signal to a display (41).