To support in situ lunar regolith resource utilization for a lunar base Controlled Ecological Life Support System (CELSS), this study selected the nitrogen-fixing cyanobacterium Nostoc commune and halophyte Suaeda salsa (L.) Pall. based on extremophile soil amelioration theory. Three cultivation treatments were established: Nostoc commune monoculture (Group A), co-culture of N. commune and S. salsa (Group B), and S. salsa monoculture (Group C). Stratified sampling (0–0.5 cm surface, 1–1.5 cm middle, 2–3 cm deep) was conducted on day 45 to quantify pH, electrical conductivity (EC), organic matter, total nitrogen, available macro/meso/trace elements, and elemental correlation of plant residues. The results showed that both species survived in lunar regolith simulant; co-culture generated significant synergistic growth promotion for S. salsa. All treatments significantly reduced initial alkaline pH (8.80 ± 0.1). Group A neutralized surface/middle layers most effectively and maximized surface available N/K; Group C exhibited superior surface available P activation; Group B achieved uniform vertical pH/EC regulation and stable carbon–nitrogen residue accumulation. Residual biomass acted as a stable C/N reservoir and altered medium/trace element bioavailability via adsorption and complexation. Group A is suitable for N/K-deficient regolith, Group C for P-limited substrates, and Group B provides comprehensive long-term balanced nutrient supply matching CELSS demands. This study verifies extremophile-based lunar regolith bioremediation and provides differentiated amelioration strategies for lunar in situ resource utilization.

Virtual commissioning of discrete assembly lines lacks a unified stage representation and an integrated verification mechanism for PLC control states, virtual execution results, and physical workpiece states, making it difficult to determine whether the control program drives the actual equipment according to the prescribed process sequence. To address this issue, a PLC–vision bilateral stage consistency verification method is proposed. Structured PLC control states are mapped to virtual actions in Unity, and execution-confirmed virtual execution stages are generated based on action-completion feedback. On the physical side, YOLO11 object detection is integrated with process-region mapping and temporal constraints to generate vision-derived physical-stage events. The virtual and physical stages are then compared using unified stage semantics to identify consistent operation, physical-state lag, physical-state lead, missing visual events, and invalid stage transitions. Experiments were conducted at a representative station of a discrete assembly line using a single workpiece and a fixed operating path. The visual-stage event recognition method achieved an F1-score of 98.33%, with an average event-generation latency of 104.21 ms. In 140 tests covering normal and controlled abnormal operating conditions, all system decisions agreed with the predefined condition labels. The proposed method extends conventional one-way verification of PLC-driven virtual models to bilateral verification between virtual execution results and physical workpiece states, thereby providing an effective technical approach for control-program commissioning and operating-state verification in discrete assembly lines.