This study investigates the development of a new inter-enginevariation analysis method for the purpose of Equipment healthmonitoring, in which the similarity - in both system behaviourand external disturbances - across multiple (sister) engines isleveraged. The sister engine provides a baseline descriptionof the engine under observation, such that the challenge becomesthe differentiation between normal inter-engine variationand the anomalous behaviour, bypassing the need todescribe highly complex engine dynamics. The inter-engineresiduals are modelled directly with input data from both engines,using previous healthy data for training. The trainedmodel is used to compensate known differences between realengines. Anomalous data is detected by comparison of thesimulated output with the true residuals. The method is demonstratedon a real data set containing both nominal, healthy enginedata, and engine data containing anomalies.

This paper investigates the problem of condition monitoring of complex dynamic systems, specifically the detection, localisation and quantification of transient faults. A data driven approach is developed for fault detection where the multidimensional data sequence is viewed as a stochastic process whose behaviour can be described by a hidden Markov model with two hidden states — i.e. ‘healthy / nominal’ and ‘unhealthy / faulty’. The fault detection is performed by first clustering in a multidimensional data space to define normal operating behaviour using a Gaussian-Uniform mixture model. The health status of the system at each data point is then determined by evaluating the posterior probabilities of the hidden states of a hidden Markov model. This allows the temporal relationship between sequential data points to be incorporated into the fault detection scheme. The proposed scheme is robust to noise and requires minimal tuning. A real-world case study is performed based on the detection of transient faults in the variable stator vane actuator of a gas turbine engine to demonstrate the successful application of the scheme. The results are used to demonstrate the generation of simple and easily interpretable analytics that can be used to monitor the evolution of the fault across time.