Aerobic Composting State Identification Using an IRRTO-Optimized CNN–LSTM–Attention Model

Aerobic composting shows state-dependent dynamics in key parameters such as temperature, moisture content, oxygen concentration, and pH, and these variables are strongly coupled over time. This coupling makes accurate state identification and process regulation challenging when relying on single-parameter thresholds or experience-based control. To enable robust recognition of composting states throughout the process, we propose an IRRTO-optimized CNN–LSTM–attention model (IRRTO–CNN–LSTM–attention). The model uses a convolutional neural network (CNN) to extract discriminative multivariate features, a long short-term memory (LSTM) network to model temporal dependencies, and an attention module to adaptively emphasize informative features. To address the hyperparameter selection challenge, the Rapidly-exploring Random Tree Optimizer (RRTO) was introduced and further enhanced via four strategies (fluctuating attenuation adaptive regulation, dual-mode guided update, dynamic dimension adaptive perturbation, and dual-mechanism adaptive perturbation regulation), forming the improved IRRTO. The proposed approach was validated using sensor data from windrow composting of pig manure and corn straw. The IRRTO–CNN–LSTM–attention model achieved an overall accuracy of 98.31% in classifying the four states (mesophilic/heating, thermophilic, cooling, and abnormal) on the independent test set, which was 3.39 percentage points higher than the RRTO-based model. These results suggest that the proposed method can accurately identify composting states and support early warning and state-specific regulation in practical aerobic composting systems.