Table 15.

Advantages and limitations of the latent variable models employed for mechanical fault detection and fault prognosis

Publication	Advantages	Limitations
[47]	Algorithm: suitable to handle data generated from multimodal distributions.	Algorithm: assumes the data was generated from a mixture of finite Gaussian distributions.
[65]	Proposed approach: real-time analytics; scalable distributed implementation.	Not identified
[54]	Algorithm: cluster centers can adapt to new data; capable of classifying data despite noise and outliers.	Not identified
	Proposed approach: capable of gaining a deep understanding about the equipment’s performance.
[64]	Algorithm: interpretability; suitable for small sample size and high-dimensional data.	Not identified
	Proposed approach: Produces stable and consistent results.
[60]	Algorithm: high computational efficiency; greater adaptability; robust to noise; uncovers patterns in raw time series data.	Not identified
	Proposed approach: superior periodic impulse extraction.
[62]	Algorithm: can handle raw multi-dimensional time series; solves the problem of empty cluster creation.	Algorithm: the time-series must be synchronous