This article aims to provide a comprehensive review on the condition monitoring techniques of underground storage tanks (UST). Generally, the UST has long been a favourite toxic substance reservation apparatus, thanks to its large capacity and minimum floor space requirement. Recently, attention has been drawn to the safety risks of the complex cylindrical-shaped system and its surrounding environment due to contamination resulting from unwanted subsurface leakage. Studies on related countermeasures shows that numerous efforts have been focused on the damage remediation process and fault detection practice; however, it has also been observed that there are uncertainties in present technical complications involving the effectiveness of corrective actions and the robustness of condition monitoring techniques. As an alternative means to deliver spatial information on structural integrity, the feasibility of integrating non- destructive evaluation (NDE) techniques with machine learning algorithms, on observing the degradation process of UST, so as to enhance condition monitoring competency, is discussed.

Intelligent machinery fault diagnosis commonly utilises statistical features of sensor signals as the inputs for its machine learning algorithm. Due to the abundance of statistical features that can be extracted from raw signals and the accuracy of inserting all the available features into the machine learning algorithm for machinery fault classification, less accurate fault classification may inadvertently result due to overfitting issues. It is therefore only by selecting the most representative features that overfitting outcomes can be avoided and classification accuracy be improved. Currently, the genetic algorithm (GA) is regarded as the most commonly used and reliable feature selection tool for the improvement of accuracy for any machine learning algorithm. However, the greatest challenge for GA is that it may fall into a local optima and be computationally demanding. To overcome this limitation, a feature selection tree (FST) is here proposed. Numerous experimental dataset feature selections were executed using FST and GA; their performance is compared and discussed. Analysis showed that the proposed FST resulted in identical or superior optimal feature subsets when compared to the renowned GA method, but with a 20-time faster simulation period. The proposed FST is therefore more efficient in performing feature selection task than GA.