Fig 1.
LSTM regulation principle.
Fig 2.
BiLSTM internal network update method.
Fig 3.
WOA process.
Fig 4.
The variation of a with t (take T = 100 for example).
Table 1.
Pseudo-code of MWOA algorithm.
Table 2.
Description of unimodal benchmark functions.
Table 3.
Description of multimodal benchmark functions.
Table 4.
Description of fixed-dimenstion multimodal benchmark functions.
Table 5.
The initial parameter settings for the corresponding algorithms.
Table 6.
Scenarios of the tuning parameters.
Table 7.
The influence of the MWOA parameters (i.e., k and α) on CEC2005 functions.
Fig 5.
Convergence curve of MWOA and other traditional algorithms.
Table 8.
Experimental comparison of MWOA with other algorithms.
Fig 6.
Boxplots of TTAO and 7 comparison algorithms on CEC2005 functions.
Table 9.
Wilcoxon rank sum test results from MWOA and 7 comparison algorithms on CEC2005 functions.
Fig 7.
MWOA-BiLSTM machine fault detection process.
Table 10.
The attribution of the predictive maintenance dataset.
Fig 8.
Fault interval.
Fig 9.
Fault classification proportion.
Fig 10.
Comparison of evaluation indicators of different metaheuristic algorithm classifiers.