Anomaly detection for industrial diesel generators, in which unexpected faults could lead to severe consequences, is still challenged due to their complex structure and nonstationary operation. Maintenance engineers who manually audit diesel generators for anomaly detection require significant expertise and knowledge. This study proposes a real-time intelligent AIoT system-based convolution neural network long short-term memory (CNN-LSTM) to enhance efficiency and decrease labor costs of industrial diesel generator maintenance service. The AIoT system could autonomously classify abnormal conditions of industrial diesel generators through supervised learning techniques. Several anomaly failure conditions are identified by maintenance experts and are simulated in the laboratory to collect the working parameters based on developed IoT modules. Pearson product-moment coefficients are computed to effectively evaluate the interdependence between collected variables and the target anomaly types. The proposed CNN-LSTM structure is hyperparameter fine-tuning for identifying the most critical configurations in failure-diagnosing applications. The developed approach is comprehensively analyzed and evaluated with other state-of-the-art individual deep learning algorithms, including recurrent neural network (RNN), LSTM, gate-recurrent unit (GRU), and CNN. The experiment results indicate that the proposed hybrid CNN-LSTM could achieve distinguished diagnosis precision of anomaly conditions of industrial diesel generators and significantly improve the classified performance in Industry 4.0.