Detecting and preventing industrial machine failures are significant in the modern manufacturing industry because machine failures substantially increase both maintenance and manufacturing costs. Recently, state-of-the-art deep learning techniques that use acoustic signals have been widely applied to solve industrial machine malfunction detection problems in order to reduce maintenance and manufacturing costs. The authors of this research propose a deep learning-based industrial machine malfunction detection model that uses acoustic signals to classify normal and abnormal conditions of industrial machines. In particular, a weighted ensemble model based on EfficientNet-B0, B5, and B7 is considered to improve classification performance. Case studies involving an open dataset for Malfunctioning Industrial Machine Investigation and Inspection (MIMII) validate that the proposed EfficientNet-based weighted ensemble model provides better classification performance than individual classifiers and other ensemble models.