Reciprocating compressors are characterized by complex structures and numerousexcitation sources, leading to a severe coupling of fault characteristics in their vibration signals. Therefore, selecting the most discriminative fault features from high-dimensional feature sets is considered highly important. In traditional genetic algorithms, fixed-length encoding is used, which tends to trap the algorithm in local optima. This often results in issues such as over-selection or loss of features within the selected feature subsets. To address these limitations, a feature selection method based on a Bounded Variable Length Sign Coding Genetic Algorithm (BVL-SCGA) is proposed. In this approach, sign coding is applied to high-dimensional datasets. Bounded intervals are set to constrain the search scope, and a repair operator is incorporated to prevent feature redundancy, Combined with feature evaluation criteria, the method accomplishes diagnostic tasks. Evaluations on UCl standard datasets demonstrated that the BVL-SCGA algorithm effectively overcomes the tendency of genetic algorithms to fall into local optima and avoids feature subset redundancy during high-dimensional feature selection. Furthermore, the application of this feature selection method to vibration signals from reciprocating compressor bearings enables accurate diagnosis of large bearing clearance faults. The superiorityof the proposed approach is thus validated.